v2.1.241 (+182 tokens)

This commit is contained in:
Mike
2026-08-22 19:50:48 -06:00
parent 391175e566
commit 0260612c8d
4 changed files with 12 additions and 5 deletions
+2 -1
View File
@@ -34,7 +34,7 @@ Download it and try it out for free! **https://piebald.ai/**
> [!tip]
> **NEW (June 12, 2026):** We've greatly expanded this list with many more of Claude Code's prompts—**from 350 to 515 (+165)**—our most complete coverage yet.
This repository contains an up-to-date list of all Claude Code's various system prompts and their associated token counts as of **[Claude Code v2.1.240](https://www.npmjs.com/package/@anthropic-ai/claude-code/v/2.1.240) (August 22nd, 2026).** It also contains a [**CHANGELOG.md**](./CHANGELOG.md) for the system prompts across 265 versions since v2.0.14. From the team behind [<img src="https://github.com/Piebald-AI/piebald/raw/main/assets/logo.svg" width="15"> **Piebald.**](https://piebald.ai/)
This repository contains an up-to-date list of all Claude Code's various system prompts and their associated token counts as of **[Claude Code v2.1.241](https://www.npmjs.com/package/@anthropic-ai/claude-code/v/2.1.241) (August 22nd, 2026).** It also contains a [**CHANGELOG.md**](./CHANGELOG.md) for the system prompts across 266 versions since v2.0.14. From the team behind [<img src="https://github.com/Piebald-AI/piebald/raw/main/assets/logo.svg" width="15"> **Piebald.**](https://piebald.ai/)
**This repository is updated within minutes of each Claude Code release. See the [changelog](./CHANGELOG.md), and follow [@PiebaldAI](https://x.com/PiebaldAI) on X for a summary of the system prompt changes in each release.**
@@ -254,6 +254,7 @@ The content of various template files embedded in Claude Code.
- [Data: SDK register device hooks request schema](./system-prompts/data-sdk-register-device-hooks-request-schema.md) (**271** tks) - Schema description for the internal register_device_hooks request used by Claude cloud device clients to register forwarded hooks and vetted templates with a session worker.
- [Data: SDK request user dialog kind field](./system-prompts/data-sdk-request-user-dialog-kind-field.md) (**210** tks) - Schema description for the open dialog_kind field on SDK request_user_dialog control requests and its client capability contract.
- [Data: SDK result message schema](./system-prompts/data-sdk-result-message-schema.md) (**173** tks) - Schema description for the turn-complete SDK result message, including success, API-error, and early-stop outcomes.
- [Data: SDK set max thinking tokens request schema](./system-prompts/data-sdk-set-max-thinking-tokens-request-schema.md) (**182** tks) - Schema description for the SDK set_max_thinking_tokens control request, including token-budget reset behavior and session-scoped thinking display overrides.
- [Data: SDK subagent stats schema](./system-prompts/data-sdk-subagent-stats-schema.md) (**339** tks) - Schema description for cumulative per-session Agent-tool subagent counts, launch modes, types, nesting, outcomes, refusals, and lifecycle caveats on SDK result messages.
- [Data: Sandbox TLS termination setting](./system-prompts/data-sandbox-tls-termination-setting.md) (**199** tks) - Describes the experimental sandbox.network.tlsTerminate setting, certificate behavior, Windows trust requirements, source precedence, and initialization validation.
- [Data: Sandbox credential environment no-match setting](./system-prompts/data-sandbox-credential-environment-no-match-setting.md) (**188** tks) - Describes sandbox credential environment-variable onExtractNoMatch behavior, including warn, deny, error, and decode-path constraints.
@@ -0,0 +1,6 @@
<!--
name: "Data: SDK set max thinking tokens request schema"
description: "Schema description for the SDK set_max_thinking_tokens control request, including token-budget reset behavior and session-scoped thinking display overrides"
ccVersion: "2.1.241"
-->
Sets the maximum number of thinking tokens for extended thinking. When max_thinking_tokens is omitted or null, thinking resets to the session default: any mid-session budget override is cleared (back to the spawn-time budget, if one was set), and thinking stays off for sessions that have it disabled. thinking_display optionally sets the thinking display mode for the rest of the session: a value replaces the session display mode, null clears that override so Claude Code's default display handling applies again, and when omitted the display mode from session start (--thinking-display) is kept.
@@ -10,7 +10,7 @@ variables:
- "MEMORY_INDEX_POINTER_INSTRUCTIONS"
- "MEMORY_SAVE_EXCLUSIONS"
- "RECALLED_MEMORY_VERIFICATION_GUIDANCE"
- "TEAM_MEMORY_SCOPE_NOTE"
- "MEMORY_CITATION_INSTRUCTIONS"
- "HAS_PROJECT_SKILL_UPKEEP_INSTRUCTIONS_FN"
- "PROJECT_SKILL_UPKEEP_INSTRUCTIONS"
-->
@@ -34,6 +34,6 @@ ${MEMORY_LINKING_INSTRUCTIONS.join(`
${MEMORY_TYPE_DESCRIPTIONS}${TEAM_MEMORY_SCOPE_NOTE}${MEMORY_INDEX_POINTER_INSTRUCTIONS}
${MEMORY_SAVE_EXCLUSIONS} ${RECALLED_MEMORY_VERIFICATION_GUIDANCE}${TEAM_MEMORY_SCOPE_NOTE}${HAS_PROJECT_SKILL_UPKEEP_INSTRUCTIONS_FN()?`
${MEMORY_SAVE_EXCLUSIONS} ${RECALLED_MEMORY_VERIFICATION_GUIDANCE}${MEMORY_CITATION_INSTRUCTIONS}${HAS_PROJECT_SKILL_UPKEEP_INSTRUCTIONS_FN()?`
${PROJECT_SKILL_UPKEEP_INSTRUCTIONS}`:""}
@@ -9,7 +9,7 @@ variables:
- "ACTIVE_WORKSHOP_INSTRUCTIONS_BLOCK"
- "PROTOTYPE_ARTIFACT_OPTION_BLOCK"
- "PLAN_MODE_PHASE_1_INITIAL_UNDERSTANDING"
- "PLAN_MODE_PHASE_3_REVIEW"
- "PLAN_MODE_PHASE_2_DESIGN"
- "PLAN_MODE_PHASE_3_REVIEW"
- "PLAN_MODE_PHASE_4_FINAL_PLAN_FN"
- "PLAN_MODE_CONTEXT"
@@ -27,7 +27,7 @@ You should build your plan incrementally by writing to or editing this file. NOT
${PLAN_MODE_PHASE_1_INITIAL_UNDERSTANDING}
${PLAN_MODE_PHASE_3_REVIEW}
${PLAN_MODE_PHASE_2_DESIGN}
${PLAN_MODE_PHASE_3_REVIEW}