triage-bug

triage-bug is a skill for Claude Code, Codex from mattmre/EVOKORE-MCP-PUBLIC. It costs 60 tokens per session (1,832 once invoked), scanned A, original, MIT.

A guide to investigating a bug from saved session evidence such as test failures, telemetry, or replay logs, rather than from a user's verbal report. It produces a test-driven development (TDD) fix plan and a written triage record.

In plain words
What is it for?
Use it to analyze captured failures, identify likely root causes, define tests for the fix, and record the result in a project bug document.
Why use it?
It gives bug reports a consistent evidence-based process and prevents agents from guessing when the original problem has not been captured. TDD means writing a failing test first, then planning the code change that should make it pass.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to analyze captured failures, identify likely root causes, define tests for the fix, and record the result in a project bug document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mattmre/evokore-mcp-public/triage-bug
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.

Any agent
npx skills add mattmre/EVOKORE-MCP-PUBLIC --skill triage-bug
Clone the repo
git clone --depth 1 https://github.com/mattmre/EVOKORE-MCP-PUBLIC

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for triage-bug

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/triage-bug/github.svg)](https://agentmods.dev/skills/mattmre/evokore-mcp-public/triage-bug)
Your own site
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/triage-bug"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/triage-bug/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for triage-bug

Your own site · 80×15
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/triage-bug"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/triage-bug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,832 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00060 $0.01832
Opus 5 $0.00030 $0.00916
Sonnet 5 $0.00012 $0.00366
Haiku 4.5 $0.00006 $0.00183

Measured 7d ago against content hash 04a98f902bf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

triage-bug 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 7d ago.

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.

SKILLS/QA/triage-bug/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

triage-bug — Triage a Bug From Evidence, Not From a User

When to use this skill

Use when there is a bug signal that needs root-cause analysis and a TDD fix plan, and the source of that signal is not a live user description. EVOKORE-MCP is agent-driven; bugs surface through:

  • tool_error rows in ~/.evokore/sessions/*-evidence.jsonl
  • test_failure rows in ~/.evokore/sessions/*-evidence.jsonl
  • abnormal call sequences in ~/.evokore/sessions/*-replay.jsonl
  • branch / worktree / control-plane drift surfaced by npm run repo:audit
  • telemetry anomalies via the get_telemetry native tool

If a human reported the bug verbally and the signal hasn't been captured yet, escalate to HITL: stop, ask the orchestrator to file a triage:new issue, and re-enter this skill once evidence rows exist.

Adapted From Upstream

This skill is adapted from mattpocock/skills/triage-bug (upstream commit 90ea8eec03d4ae8f43427aaf6fe4722653561a42, MIT-licensed). The upstream skill assumes a user describes the bug, the agent asks clarifying questions, and the user confirms reproduction steps. EVOKORE-MCP is agent-driven, so all of those steps are replaced with artifact reads.

EVOKORE-Specific Adaptations

Upstream behavior EVOKORE behavior
"Ask the user to describe the bug" Read most recent ~/.evokore/sessions/*-evidence.jsonl for tool_error / test_failure rows
"Ask the user for reproduction steps" Read corresponding ~/.evokore/sessions/*-replay.jsonl for the call sequence leading up to the failure (timestamp window before the error row)
"Ask the user about environment" Run npm run repo:audit for branch/worktree drift; optionally call get_telemetry native tool for runtime context
"Iterate with user on root cause hypothesis" Invoke panel-of-experts skill with persona set [debugger, architect, qa-lead] if the root cause crosses bounded contexts (ADR-0005)
"User confirms the fix plan" The fix plan is a TDD plan (failing test path + expected assertion + fix surface) written to docs/bugs/<slug>.md; the actual confirmation is the failing test commit produced by the downstream tdd skill

Read the full file on GitHub · 166 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. 7d ago First seen · 166 lines · 60 tokens per session scan A 04a98f902bf3

Subscribe to this mod's changes

triage-bug is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,832 once invoked, about $0.0003 per session on Opus 5. 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 2026-09-03.