Captured System Prompts

A system prompt is the text that Claude Code sends to the model before your first message. It tells the model who it is, how to behave, and what the session looks like. The model reads it on every request.

Claude Code has no single system prompt. It builds one from parts. The parts depend on the model, on flags, on env vars, on your output style, and on whether the request comes from the main agent or a subagent. This section shows every variant that you can pick, in full, with a diff against the default.

The text on these pages is Anthropic's. It is shown here only to describe how the program works. See the notice on the home page.

Status badges:

Documented: An official docs page names this item.

means an official docs page names the switch.

Undocumented: Only the program shows this item. It can change without notice.

means only the program shows it.

Differs: The official docs and the program disagree. The row says how. example

means the docs and the program disagree.

Gated: Works only behind a flag or a server gate. example

means a flag or a server gate is needed.

Every Prompt and How to Change It

A condition in parentheses after a prompt name is the condition that makes the prompt apply.

Prompt	Can You Change It?	Turn On or Off	Where It Lives	Status
Default, Lean Prompt (Every session on a lean model gets it)	✅ Yes. Use the flags and settings on the other pages.	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0 switches to the full prompt.	Built into the program. Nothing on disk.	Undocumented: Only the program shows this item. It can change without notice.
Default, Sonnet 5.5 (Every Sonnet 5.5 session gets it)	✅ Yes. Use the flags and settings on the other pages.	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0 switches to the full prompt.	Built into the program. Nothing on disk.	Documented: An official docs page names this item.
Default, Haiku 5.5 (Every Haiku 5.5 session gets it)	✅ Yes. Use the flags and settings on the other pages.	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0 switches to the full prompt.	Built into the program. Nothing on disk.	Undocumented: Only the program shows this item. It can change without notice.
Full Prompt	✅ Yes. Set or unset the env var.	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0 (also false, no, off).	Environment variable. Put it under env in settings.json to keep it.	Documented: An official docs page names this item.
Simple Prompt Switch on Sonnet	✅ Yes. Set or unset the env var.	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=1.	Environment variable.	Documented: An official docs page names this item.
Simple Prompt Switch on Haiku	✅ Yes. Set or unset the env var.	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=1.	Environment variable.	Documented: An official docs page names this item.
Simple Prompt Switch on Opus	✅ Yes. Set or unset the env var.	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=1.	Environment variable.	Documented: An official docs page names this item.
Bare Mode	❌ No. The two lines are fixed.	--bare or CLAUDE_CODE_SIMPLE=1.	Command-line flag.	Documented: An official docs page names this item.
Simple Mode Env Var	❌ No. The two lines are fixed.	CLAUDE_CODE_SIMPLE=1.	Environment variable.	Documented: An official docs page names this item.
Exclude Dynamic Sections	❌ No. It only moves text.	--exclude-dynamic-system-prompt-sections.	Command-line flag.	Documented: An official docs page names this item.
Exclude Dynamic Sections, Full Prompt	❌ No. It only moves text.	--exclude-dynamic-system-prompt-sections.	Command-line flag.	Documented: An official docs page names this item.
Output Style, Explanatory	Not the built-in text. You can write a custom style.	/output-style or the outputStyle setting.	outputStyle in any settings scope.	Documented: An official docs page names this item.
Output Style, Learning	Not the built-in text. You can write a custom style.	/output-style or the outputStyle setting.	outputStyle in any settings scope.	Documented: An official docs page names this item.
Output Style, Proactive	Not the built-in text. You can write a custom style.	/output-style or the outputStyle setting.	outputStyle in any settings scope.	Documented: An official docs page names this item.
Output Style, Concise	Not the built-in text. You can write a custom style.	/output-style or the outputStyle setting.	outputStyle in any settings scope.	Documented: An official docs page names this item.
Custom Output Style	✅ Yes. You write the file.	/output-style or the outputStyle setting.	~/.claude/output-styles/*.md or .claude/output-styles/*.md.	Documented: An official docs page names this item.
Custom Output Style on the Full Prompt	✅ Yes. You write the file.	/output-style or the outputStyle setting.	~/.claude/output-styles/*.md or .claude/output-styles/*.md.	Documented: An official docs page names this item.
Custom Output Style with Keep Coding Instructions	✅ Yes. You write the file.	keep-coding-instructions in the style's front matter.	~/.claude/output-styles/*.md or .claude/output-styles/*.md.	Documented: An official docs page names this item.
Custom Output Style with Keep Coding Instructions, Lean Prompt	✅ Yes. You write the file.	keep-coding-instructions in the style's front matter.	~/.claude/output-styles/*.md or .claude/output-styles/*.md.	Documented: An official docs page names this item.
Append System Prompt	✅ Yes. You give the text.	--append-system-prompt or --append-system-prompt-file.	Command-line flags.	Documented: An official docs page names this item.
Replace System Prompt	✅ Yes. You give the text.	--system-prompt or --system-prompt-file.	Command-line flags.	Documented: An official docs page names this item.
Replace and Append Together	✅ Yes. You give the text.	The two flags.	Command-line flags.	Documented: An official docs page names this item.
With a CLAUDE.md File	✅ Yes. You write the file.	Add or remove the file. CLAUDE_CODE_DISABLE_CLAUDE_MDS=1 skips them.	CLAUDE.md, .claude/CLAUDE.md, ~/.claude/CLAUDE.md.	Documented: An official docs page names this item.
Inside a Git Repository (It happens on its own)	❌ No.	includeGitInstructions in settings controls the git rules. The status text always appears in a repo.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Main Thread Custom Agent	✅ Yes. You write the agent file.	--agent or the agent setting.	.claude/agents/*.md or ~/.claude/agents/*.md.	Documented: An official docs page names this item.
Permission Mode, Plan	❌ No.	--permission-mode or defaultMode in settings.	Flag or settings.	Documented: An official docs page names this item.
Permission Mode, Accept Edits	❌ No.	--permission-mode or defaultMode in settings.	Flag or settings.	Documented: An official docs page names this item.
Permission Mode, Don't Ask	❌ No.	--permission-mode or defaultMode in settings.	Flag or settings.	Documented: An official docs page names this item.
Brief Mode	❌ No.	--brief.	Command-line flag.	Undocumented: Only the program shows this item. It can change without notice.
Compaction Prompt	Partly. You can add focus text after /compact.	/compact, or automatic when the context fills.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Subagent, General Purpose (The model starts subagents)	Not the built-in text. You can write custom agents.	--disallowedTools Agent stops all subagents.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Subagent, Explore (The model starts subagents)	Not the built-in text. You can write custom agents.	--disallowedTools Agent stops all subagents.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Subagent, Plan (The model starts subagents)	Not the built-in text. You can write custom agents.	--disallowedTools Agent stops all subagents.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Subagent, Custom Agent	✅ Yes. You write the agent file.	Add or remove the file.	.claude/agents/*.md or ~/.claude/agents/*.md.	Documented: An official docs page names this item.
Subagent, Statusline Setup	✅ Yes. A user agent file with the same name replaces it.	--disallowedTools Agent stops all subagents.	Built into the program. Override in .claude/agents/<name>.md.	Undocumented: Only the program shows this item. It can change without notice.
Subagent, Claude (FleetView)	✅ Yes. A user agent file with the same name replaces it.	--disallowedTools Agent stops all subagents.	Built into the program. Override in .claude/agents/<name>.md.	Undocumented: Only the program shows this item. It can change without notice.
Subagent, Web Fetch	✅ Yes. A user agent file with the same name replaces it.	CLAUDE_CODE_WEB_FETCH_AGENT=1 adds it. CLAUDE_CODE_DISABLE_WEB_FETCH removes it.	Built into the program. Override in .claude/agents/web-fetch.md.	Undocumented: Only the program shows this item. It can change without notice.
Subagent, Claude Code Guide	✅ Yes. A user agent file with the same name replaces it.	Not offered in -p or the SDK entry points. --disallowedTools Agent stops all subagents.	Built into the program. Override in .claude/agents/claude-code-guide.md.	Undocumented: Only the program shows this item. It can change without notice.
Override a Built-in Agent with a File	✅ Yes. You write the agent file.	Add or remove the file.	.claude/agents/*.md or ~/.claude/agents/*.md.	Undocumented: Only the program shows this item. It can change without notice.
Override a Built-in Agent with --agents	✅ Yes. You give the JSON.	--agents.	Command-line flag.	Documented: An official docs page names this item.
Append to Every Subagent Prompt	✅ Yes. You give the text.	--append-subagent-system-prompt or --append-subagent-system-prompt-file (print mode only).	Command-line flags.	Undocumented: Only the program shows this item. It can change without notice.
Turn Off the Explore and Plan Agents	✅ Yes. It removes text.	CLAUDE_CODE_DISABLE_EXPLORE_PLAN_AGENTS=1.	Environment variable.	Undocumented: Only the program shows this item. It can change without notice.
Turn Off All Built-in Agents	✅ Yes. It removes text.	CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS=1.	Environment variable.	Undocumented: Only the program shows this item. It can change without notice.
Command, /init	✅ Yes. A command or skill file with the same name may replace it.	Type /init.	Built into the program.	Documented: An official docs page names this item.
Command, /security-review	✅ Yes. A command or skill file with the same name may replace it.	Type /security-review.	Built into the program.	Documented: An official docs page names this item.
Skill, /simplify	✅ Yes. A command or skill file with the same name may replace it.	Type /simplify.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Skill, /debug	✅ Yes. A command or skill file with the same name may replace it.	Type /debug.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Override /init with a Command File	✅ Yes. A command or skill file with the same name may replace it.	Type /init.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Override /simplify with a Skill File	✅ Yes. A command or skill file with the same name may replace it.	Type /simplify.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Prompt Hook Request	Partly. You write the prompt and pick the model. The system text is fixed.	Add or remove the hook.	hooks in any settings scope.	Documented: An official docs page names this item.
Agent Hook Request	Partly. You write the prompt and pick the model. The system text is fixed.	Add or remove the hook.	hooks in any settings scope.	Documented: An official docs page names this item.
Auto Mode Classifier	Partly. The autoMode setting edits the rule lists.	--permission-mode auto or defaultMode: "auto".	autoMode in user, flag, or managed settings.	Documented: An official docs page names this item.
Auto Mode Classifier, Custom Rules	✅ Yes. You write the rules.	autoMode setting.	autoMode in user, flag, or managed settings.	Documented: An official docs page names this item.
Compaction Prompt, Custom Instructions	✅ Yes. You add focus text. The base summary rules stay.	/compact <text>.	The command line, CLAUDE.md, or a PreCompact hook.	Documented: An official docs page names this item.
Plan Mode, Custom Workflow	✅ Yes. You give the workflow text. The read-only rules and the ExitPlanMode rule stay.	--plan-mode-instructions.	Command-line flag.	Undocumented: Only the program shows this item. It can change without notice.
Git Instructions Turned Off	✅ Yes. It removes text.	includeGitInstructions or CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS=1.	Any settings scope, or an environment variable.	Documented: An official docs page names this item.
Auto Memory Turned Off	✅ Yes. It removes text.	CLAUDE_CODE_DISABLE_AUTO_MEMORY=1 or autoMemoryEnabled.	Environment variable or any settings scope.	Documented: An official docs page names this item.
Custom Output Style with a Built-in Name	✅ Yes. You write the file.	/output-style or the outputStyle setting.	~/.claude/output-styles/*.md or .claude/output-styles/*.md.	Undocumented: Only the program shows this item. It can change without notice.
Subagent with --system-prompt and --append-system-prompt	Not for the subagent. Use --append-subagent-system-prompt.	The flags.	Command-line flags.	Undocumented: Only the program shows this item. It can change without notice.
Prompt Hook on Stop	Partly. You write the prompt and pick the model. The system text is fixed.	Add or remove the hook.	hooks in any settings scope.	Documented: An official docs page names this item.
All Tools Sent Upfront	✅ Yes. It adds the deferred tools to the request.	ENABLE_TOOL_SEARCH.	Environment variable, or env in any settings scope.	Documented: An official docs page names this item.
Override a Prompt	✅ Yes. The page lists each prompt you can replace, append to, or turn off.	Per prompt. See the page.	Flags, env vars, settings, and files.	Undocumented: Only the program shows this item. It can change without notice.
Tool Descriptions (Every request carries them)	✅ Yes. A Mod API tool.describe hook replaces a description.	ENABLE_TOOL_SEARCH, --tools, --disallowedTools.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.
Built-In Skills (The main agent reads one line for each)	✅ Yes. A skill or command with the same name replaces one.	--disable-slash-commands.	Built into the program. Override in .claude/skills/<name>/SKILL.md.	Documented: An official docs page names this item.
Built-In Agents (The main agent reads one line for each)	✅ Yes. An agent with the same name replaces one.	CLAUDE_CODE_DISABLE_EXPLORE_PLAN_AGENTS, CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS.	Built into the program. Override in .claude/agents/<name>.md.	Documented: An official docs page names this item.
Tools per Variant (Every request carries the list)	✅ Yes. Use --tools, --allowedTools, --disallowedTools, or settings.	--bare and CLAUDE_CODE_SIMPLE=1 cut the list to three tools.	Built into the program.	Undocumented: Only the program shows this item. It can change without notice.

How the Captures Were Made

Every prompt on these pages was captured offline, with no model call and no cost.

1. A script starts the installed program (version 2.1.312) in print mode (-p) once per variant.
2. The program talks to a small fake Messages API on 127.0.0.1. The fake server writes each request body to a file and sends back a canned reply.
3. The run uses a fake API key, a dead proxy (HTTPS_PROXY and HTTP_PROXY point to a closed port), CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1, DISABLE_TELEMETRY=1, and a temporary home, config folder, and project folder. No login token is used. The script checks that every request went to the local server.
4. A second script reads the saved request bodies, replaces machine-specific values with placeholders, and writes these pages. It makes the diffs with diff -u, not by hand.

For the subagent pages, the fake server answers the first turn with an Agent tool call. The program then starts a real subagent and sends its request to the fake server.

For the compaction page, the script runs twice in the same folders: once with Reply with 'OK'., then with --continue and /compact.

The Three System Blocks

Each request has a system field with three blocks, then messages. This is what the captures show.

Block	What it holds	Cache marker
system[0]	A billing header line with the program version and entry point (cc_entrypoint=sdk-cli in -p mode).	None
system[1]	The identity line.	ephemeral
system[2]	The body: the rules, the memory section, and your appended text.	ephemeral

Not everything that the model reads as instructions is in system. Claude Code also sends the following in the messages list, before your own text:

• A reminder with the git attribution lines (first user message).
• Project memory files, git status, and (with --exclude-dynamic-system-prompt-sections) the memory section.
• A message with the role system. It holds the environment details, the output style text, the agent types, the skills list, and the date.

Every variant page shows all of these parts, in the order they are sent, with a === line before each part.

Identity Line

In -p mode the identity line is the SDK line: You are a Claude agent, built on Anthropic's Claude Agent SDK. Every capture here uses -p, so every page shows that line, except pages where it changes (see below).

The program has three identity lines. Two more appear in its text:

• You are Claude Code, Anthropic's official CLI for Claude. This is the line for the interactive terminal app. It could not be captured offline: the full-screen app did not accept typed input in the test harness, so no request was sent. Setting CLAUDE_CODE_ENTRYPOINT=cli in -p mode does not change the line.
• You are Claude Code, Anthropic's official CLI for Claude, running within the Claude Agent SDK. Print mode sends this one when you use --append-system-prompt. See Append System Prompt.

How Claude Code Picks the Variant

The chart shows what the captures prove. The order of the first three checks was not tested with every combination of flags.

Subagents skip this chart. They get their own body and notes (see Subagent, general-purpose).

Captures disagree with the old wiki in one place: the wiki says models with sonnet or haiku in the name get the full prompt. In 2.1.312 they get the lean prompt, and only CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0 gives the full one.

All Variants

Size is the number of characters in everything shown on the variant page, after placeholders are in place. The last column lists the # headings found in the system body.

Variant	How to select it	Characters	Tools	Sections
Default, Lean Prompt	Default on Opus 5.5	15,721	12	Harness, Session-specific guidance, Memory, Environment, Context management
Default, Sonnet 5.5	Default on Sonnet 5.5	15,727	12	Harness, Session-specific guidance, Memory, Environment, Context management
Default, Haiku 5.5	Default on Haiku 5.5	18,516	12	Harness, Session-specific guidance, Memory, Environment, Context management
Full Prompt	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0	37,105	12	System, Doing tasks, Executing actions with care, Using your tools, Tone and style, Text output (does not apply to tool calls), Session-specific guidance, auto memory, Environment, Context management
Simple Prompt Switch on Sonnet (same text as default-sonnet)	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=1 on Sonnet	15,727	12	Harness, Session-specific guidance, Memory, Environment, Context management
Simple Prompt Switch on Haiku (same text as default-haiku)	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=1 on Haiku	18,516	12	Harness, Session-specific guidance, Memory, Environment, Context management
Simple Prompt Switch on Opus (same text as default-lean)	CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=1 on Opus	15,721	12	Harness, Session-specific guidance, Memory, Environment, Context management
Bare Mode	--bare	376	3	none
Simple Mode Env Var (same text as bare)	CLAUDE_CODE_SIMPLE=1	376	3	none
Exclude Dynamic Sections	--exclude-dynamic-system-prompt-sections	15,616	12	Harness, Environment, Context management
Exclude Dynamic Sections, Full Prompt	--exclude-dynamic-system-prompt-sections plus the full prompt	37,115	12	System, Doing tasks, Executing actions with care, Using your tools, Tone and style, auto memory, Text output (does not apply to tool calls), Session-specific guidance, Environment, Context management
Output Style, Explanatory	Output style Explanatory	16,908	12	Harness, Session-specific guidance, Memory, Environment, Context management
Output Style, Learning	Output style Learning	20,767	12	Harness, Session-specific guidance, Memory, Environment, Context management
Output Style, Proactive	Output style Proactive	17,227	12	Harness, Session-specific guidance, Memory, Environment, Context management
Output Style, Concise	Output style Concise	17,261	12	Harness, Session-specific guidance, Memory, Environment, Context management
Custom Output Style	Custom style file	15,939	12	Harness, Session-specific guidance, Memory, Environment, Context management
Custom Output Style on the Full Prompt	Custom style, full prompt	34,002	12	System, Executing actions with care, Using your tools, Tone and style, Text output (does not apply to tool calls), Session-specific guidance, auto memory, Environment, Context management
Custom Output Style with Keep Coding Instructions	Custom style with keep-coding-instructions	37,323	12	System, Doing tasks, Executing actions with care, Using your tools, Tone and style, Text output (does not apply to tool calls), Session-specific guidance, auto memory, Environment, Context management
Custom Output Style with Keep Coding Instructions, Lean Prompt (same text as style-custom)	Custom style with keep-coding-instructions, lean	15,939	12	Harness, Session-specific guidance, Memory, Environment, Context management
Append System Prompt	--append-system-prompt	15,778	12	Harness, Session-specific guidance, Memory, Environment, Context management
Replace System Prompt	--system-prompt	10,120	12	none
Replace and Append Together	--system-prompt plus --append-system-prompt	10,177	12	none
With a CLAUDE.md File	A CLAUDE.md file	16,110	12	Harness, Session-specific guidance, Memory, Environment, Context management
Inside a Git Repository	A git repository	16,337	12	Harness, Session-specific guidance, Memory, Environment, Context management
Main Thread Custom Agent	--agent <name>	10,222	12	none
Permission Mode, Plan	--permission-mode plan	20,600	12	Harness, Session-specific guidance, Memory, Environment, Context management
Permission Mode, Accept Edits (same text as default-lean)	--permission-mode acceptEdits	15,721	12	Harness, Session-specific guidance, Memory, Environment, Context management
Permission Mode, Don't Ask (same text as default-lean)	--permission-mode dontAsk	15,721	12	Harness, Session-specific guidance, Memory, Environment, Context management
Brief Mode (same text as default-lean)	--brief	15,721	12	Harness, Session-specific guidance, Memory, Environment, Context management
Compaction Prompt	/compact	22,575	12	Harness, Session-specific guidance, Memory, Environment, Context management
Subagent, General Purpose	Agent tool, general-purpose	11,135	8	none
Subagent, Explore	Agent tool, Explore	11,665	5	none
Subagent, Plan	Agent tool, Plan	11,972	5	none
Subagent, Custom Agent	Custom agent file	9,759	8	none
Subagent, Statusline Setup	Agent tool, statusline-setup	15,535	2	none
Subagent, Claude (FleetView)	Agent tool, claude	11,534	8	none
Subagent, Web Fetch	CLAUDE_CODE_WEB_FETCH_AGENT=1, Agent tool, web-fetch	5,525	1	none
Subagent, Claude Code Guide	Interactive session, Agent tool, claude-code-guide	29,062	4	none
Override a Built-in Agent with a File	Agent file with a built-in name	9,772	8	none
Override a Built-in Agent with --agents	--agents with a built-in name	9,753	8	none
Append to Every Subagent Prompt	--append-subagent-system-prompt	11,693	5	none
Turn Off the Explore and Plan Agents	CLAUDE_CODE_DISABLE_EXPLORE_PLAN_AGENTS=1	14,816	12	Harness, Session-specific guidance, Memory, Environment, Context management
Turn Off All Built-in Agents	CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS=1	14,083	12	Harness, Session-specific guidance, Memory, Environment, Context management
Command, /init	/init	17,366	12	Harness, Session-specific guidance, Memory, Environment, Context management
Command, /security-review	/security-review	16,246	12	Harness, Session-specific guidance, Memory, Environment, Context management
Skill, /simplify	/simplify	18,598	12	Harness, Session-specific guidance, Memory, Environment, Context management
Skill, /debug	/debug	17,368	12	Harness, Session-specific guidance, Memory, Environment, Context management
Override /init with a Command File	/init	15,830	12	Harness, Session-specific guidance, Memory, Environment, Context management
Override /simplify with a Skill File	/simplify	15,783	12	Harness, Session-specific guidance, Memory, Environment, Context management
Prompt Hook Request	Hook type: prompt	1,478	0	none
Agent Hook Request	Hook type: agent	2,362	10	none
Auto Mode Classifier	--permission-mode auto	140,718	0	none
Auto Mode Classifier, Custom Rules	autoMode setting	76,028	0	none
Compaction Prompt, Custom Instructions	/compact <text>, CLAUDE.md, or PreCompact hook	23,085	12	Harness, Session-specific guidance, Memory, Environment, Context management
Plan Mode, Custom Workflow	--plan-mode-instructions	17,217	12	Harness, Session-specific guidance, Memory, Environment, Context management
Git Instructions Turned Off	includeGitInstructions: false	15,083	12	Harness, Session-specific guidance, Memory, Environment, Context management
Auto Memory Turned Off	CLAUDE_CODE_DISABLE_AUTO_MEMORY=1	13,658	12	Harness, Session-specific guidance, Environment, Context management
Custom Output Style with a Built-in Name	Style file with a built-in name	15,936	12	Harness, Session-specific guidance, Memory, Environment, Context management
Subagent with --system-prompt and --append-system-prompt	Prompt flags plus a subagent	11,697	5	none
Prompt Hook on Stop	Hook type: prompt on Stop	12,622	0	none
All Tools Sent Upfront	ENABLE_TOOL_SEARCH=false	15,352	21	Harness, Session-specific guidance, Memory, Environment, Context management

See also Tools per Variant.

Placeholders

Placeholder	Replaces
<cwd>	The project folder (a temporary folder in each run).
<config-dir>	The Claude config folder (CLAUDE_CONFIG_DIR, a temporary folder).
<home>	The home folder (a temporary folder).
<project-slug>	The project folder name as used inside the config folder, with / and . turned into -.
<config-slug>	The same kind of name for the config folder.
<date>	Any date such as the day of the run.
<platform>, <shell>, <os-version>	Your operating system, shell, and OS version.
<build>	The build suffix of cc_version in the billing header.
<sha>	A git commit hash.
<uuid-1>, <uuid-2>, ...	A random id, such as a session id, numbered by first use in each capture. The same number is the same id.
<robot-emoji>	A robot emoji in the pull request line of the attribution reminder. The site shows no emojis.
<plan-name>	The random plan file name in plan mode.

Strings such as PROBE-CUSTOM-STYLE-TEXT and APPENDED-TEXT-FROM-FLAG are test text that the script supplies, so you can see where your own text lands.

How to Regenerate

Run these from the repository root. Both steps use bun only.

bun tools/capture-prompts/capture.ts          # capture every variant, then write the pages
bun tools/capture-prompts/capture.ts --only default-lean,bare   # capture some variants
bun tools/capture-prompts/render.ts           # rebuild the pages from saved captures

Raw requests go to captures/<version>/prompts/ (not committed). Normalized text goes to tools/capture-prompts/out/. The variant list is in tools/capture-prompts/variants.ts. For a new release, update src/version.ts (or pass --bin and --out) and run it again.