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 commands/unclecode/claude-code-tools/pp-triagegit 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 | $0.01500 |
| Opus 5 | $0.00000 | $0.00750 |
| Sonnet 5 | $0.00000 | $0.00300 |
| Haiku 4.5 | $0.00000 | $0.00150 |
Grade A, and why
pp-triage 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Issue or Feature Request
Root cause investigation and solution design for issues, bugs, or feature requests.
Arguments
$ARGUMENTS
Description of the issue or feature. Can include error messages, URLs, or attach screenshots.
Purpose
Deep investigation to find ROOT CAUSES, not just symptoms. Uses triage-agent for systematic analysis.
Philosophy: Don't just treat the rash, find the root cause (diet, stress, etc.) and fix both.
Execution Instructions
Step 1: Collect Issue Information
From user query, gather:
- Issue description (what's happening)
- Error messages (if any)
- Steps to reproduce (if provided)
- Expected vs actual behavior
- Screenshots/links (if attached)
- Affected area (frontend, backend, API, etc.)
If critical info missing, ask clarifying questions:
- "What error message do you see?"
- "When does this happen?"
- "Which part of the system is affected?"
Step 2: Read PP Context First
IMPORTANT: Before launching agent, gather context from PP files:
Read these files:
.context/project/INDEX.md- Identify active subproject.context/project/{active}/CODEBASE.md- Understand file structure.context/project/{active}/STATUS.md- Current state, known issues.context/project/{active}/CHANGELOG.md(last 5-10 entries) - Recent changes.context/project/{active}/LESSONS.md- Past solutions.context/project/PRINCIPLES.md- Project principles
This context is passed to the agent so it doesn't re-explore everything.
Step 3: Launch Triage Agent
Spawn the triage-agent with:
- Issue description
- PP context (from Step 2)
- Specific focus area (if mentioned)
Use Task tool with subagent_type: "triage-agent"
Prompt: Investigate this issue using PP context:
Issue: {user's issue description}
PP Context:
- Active subproject: {from INDEX.md}
- Codebase structure: {from CODEBASE.md}
- Current status: {from STATUS.md}
- Recent changes: {from CHANGELOG.md}
- Past lessons: {from LESSONS.md}
- Principles: {from PRINCIPLES.md}
Find ROOT CAUSE and provide solution or debugging plan.
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 · 247 lines · 0 tokens per session scan A 9e92b683b609
pp-triage is a command 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 1,500 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.