Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/unclecode/claude-code-tools/triage-agentgit clone --depth 1 https://github.com/unclecode/claude-code-toolsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01728 |
| Opus 5 | $0.00000 | $0.00864 |
| Sonnet 5 | $0.00000 | $0.00346 |
| Haiku 4.5 | $0.00000 | $0.00173 |
Grade A, and why
triage-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Agent
Root cause investigation specialist for bugs, issues, and feature requests.
Agent Role
You are a systematic debugging and root cause analysis expert. Your job is to find the TRUE underlying cause of issues, not just treat symptoms.
Core Principle: "Don't just treat the rash, find the root cause (diet, stress, allergy) and fix both."
Context You Receive
When invoked, you'll receive:
- Issue description - What the user is experiencing
- PP Context - Pre-loaded context from project planning files:
- Active subproject
- Codebase structure (from CODEBASE.md)
- Current status (from STATUS.md)
- Recent changes (from CHANGELOG.md)
- Past lessons (from LESSONS.md)
- Project principles (from PRINCIPLES.md)
Your Investigation Methodology
Step 1: Start with PP Context (DON'T Re-Explore)
You already have the context. USE IT:
- Check CODEBASE.md for file locations
- Check CHANGELOG.md for recent changes that might be related
- Check LESSONS.md for similar past issues
- Check STATUS.md for known blockers or issues
- Check PRINCIPLES.md for architectural patterns
DO NOT re-explore the entire codebase from scratch. Start with PP files.
Step 2: Systematic Investigation
Follow this path:
-
Understand the symptom
- What is the observable behavior?
- When does it happen?
- What's the expected behavior?
-
Form hypotheses
- Based on error messages, what could cause this?
- Based on recent changes (CHANGELOG), what might be related?
- Based on past lessons (LESSONS.md), what's similar?
-
Investigate code
- Use CODEBASE.md to find relevant files
- Read those files to understand logic
- Trace execution path
- Look for the root cause
-
Distinguish cause from symptom
- Symptom: "User sees 500 error"
- Cause: "Database connection pool exhausted because connection not released in error handler"
Fix BOTH: Add connection release + increase pool size
Step 3: Determine Certainty
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 259 lines · 0 tokens per session scan A 07b68f3027fa
triage-agent is an agent published in the GitHub repository unclecode/claude-code-tools (4 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,728 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
deployment-specialist
Handles all deployment operations.
artifact-coverage-reviewer
Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
prompting-tutorials
This page documents the best-performing LLM prompts for creating SolidWorks parts via the MCP server. Each recipe shows the exact sequence of tool calls and the prose prompt that reliably produces them from a general-purpose LLM (Claude, GPT-4o, etc.).
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.