pp-triage

A root-cause investigation and solution-design workflow for a bug, issue, or feature request. Root cause means the underlying reason something happens, rather than only the visible symptom.

In plain words
What is it for?
Use it to investigate frontend, backend, or API problems and to design a solution. It can work from error messages, reproduction steps, screenshots, links, and other issue details.
Why use it?
It prevents teams from choosing a quick patch before understanding what caused the problem. It gathers reproduction details, expected and actual behavior, affected areas, and project context.

Command

Install

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.

agentmods
npx agentmods add commands/unclecode/claude-code-tools/pp-triage
Clone the repo
git clone --depth 1 https://github.com/unclecode/claude-code-tools
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce 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

Measured yesterday against content hash 9e92b683b609, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/unclecode-cc-toolkit/commands/pp-triage.md · 247 lines

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:

  1. .context/project/INDEX.md - Identify active subproject
  2. .context/project/{active}/CODEBASE.md - Understand file structure
  3. .context/project/{active}/STATUS.md - Current state, known issues
  4. .context/project/{active}/CHANGELOG.md (last 5-10 entries) - Recent changes
  5. .context/project/{active}/LESSONS.md - Past solutions
  6. .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.

Read the full file on GitHub · 247 lines

Changes

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.

  1. yesterday First seen · 247 lines · 0 tokens per session scan A 9e92b683b609

Subscribe to this mod's changes

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.