Files

T

jpmschweitzerandClaude Opus 4.5 47eff4ecd1 docs: expand agent and tool documentation with detailed descriptions

agents/README.md:
- Added detailed descriptions for Explore, Plan, and Task agents
- Documented capabilities, when to use, and tools available
- Added utilities/ section for shared prompts

tools/README.md:
- Added detailed descriptions for file, shell, and search tools
- Documented key parameters and behaviors
- Added security notes for bash/sandbox

agents/utilities/:
- todowrite-prompt.md - Task list management
- askuserquestion-prompt.md - User clarification
- conversation-summarization-prompt.md - Context compaction
- session-title-prompt.md - Title/branch generation
- security-review-prompt.md - Security analysis

Source: gitea:library/claude-code-system-prompts

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-09 20:05:23 +01:00

1.4 KiB

Raw Blame History

Agent Utilities

Reference prompts for utility functions used across agents.

Prompts

todowrite-prompt.md

Purpose: Task list management for tracking progress.

Use for:

Complex multi-step tasks (3+ steps)
User provides multiple tasks
Tracking progress on implementation
Breaking down large features

States: pending, in_progress, completed

askuserquestion-prompt.md

Purpose: Interactive clarification during execution.

Use for:

Gathering user preferences
Clarifying ambiguous instructions
Getting decisions on implementation choices
Offering direction choices

conversation-summarization-prompt.md

Purpose: Compacting long conversations for context management.

Creates detailed summaries preserving:

Primary request and intent
Key technical concepts
Files and code sections
Errors and fixes
Problem-solving steps
Pending tasks

session-title-prompt.md

Purpose: Generate concise session titles and git branch names.

Output format:

Title: 3-6 words, no quotes
Branch: kebab-case, 2-4 words (e.g., add-user-auth)

security-review-prompt.md

Purpose: Comprehensive security analysis of code changes.

Reviews for:

Authentication/authorization flaws
Injection vulnerabilities (SQL, command, XSS)
Secrets exposure
Path traversal
SSRF vulnerabilities
Cryptographic issues

Only reports exploitable vulnerabilities with clear attack paths.

1.4 KiB Raw Blame History