github-triage

github-triage is a skill for Claude Code, Codex from mattmre/EVOKORE-MCP-PUBLIC. It costs 62 tokens per session (2,582 once invoked), scanned A, original, MIT.

A guide to moving open GitHub issues through a seven-state triage process by reading their descriptions, labels, linked documents, and captured evidence. It produces a brief for each issue and explains why work may be out of scope.

In plain words
What is it for?
Use it to classify open issues, recommend their next triage state, prepare agent briefs, and document issues that should not be pursued.
Why use it?
It replaces ad hoc issue handling with consistent decisions based on the available record. This makes the next action and its reasoning easier for maintainers to review.

Skill for Claude CodeCodex

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

Good fit Use it to classify open issues, recommend their next triage state, prepare agent briefs, and document issues that should not be pursued.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/github-triage"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/github-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,582 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 $0.00062 $0.02582
Opus 5 $0.00031 $0.01291
Sonnet 5 $0.00012 $0.00516
Haiku 4.5 $0.00006 $0.00258

Measured 5d ago against content hash 4537b53c9571, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

github-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 5d 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/PROJECT MANAGEMENT/github-triage/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

github-triage — Label-Based Issue State Machine

When to use this skill

Use when there is at least one open GitHub issue in this repository that needs to be moved through the triage state machine (see ADR-0006). The skill replaces the upstream "maintainer manually triggers" model with an agent-driven transition: the agent reads the issue body, the labels, linked artifacts under docs/, and the latest evidence/replay JSONL, then decides the next state.

If there are no open issues, stop. If the only open issues are already in terminal states (triage:done, triage:wontfix), stop. If a docs/agent-briefs/<issue-number>.md artifact already exists for the issue but the issue's labels do not match the brief's recommended next state, fix the brief first.

Adapted From Upstream

This skill is adapted from mattpocock/skills/github-triage (upstream commit 90ea8eec03d4ae8f43427aaf6fe4722653561a42, MIT-licensed). The upstream skill uses 7 labels with a documented transition table, an AGENT-BRIEF.md artifact pattern, and an .out-of-scope/ knowledge base. EVOKORE-MCP keeps all three but rewires the transition triggers from "maintainer comments on the issue" to "agent reads evidence and applies the rule".

EVOKORE-Specific Adaptations

Upstream behavior EVOKORE behavior
"Maintainer triggers triage" Agent runs this skill against gh issue list --state open --json number,labels,title and transitions automatically per the rule below
"User describes the bug to triage" Read the issue body + linked docs/bugs/<slug>.md (if present) + most recent evidence JSONL; route ambiguity to triage:human-review
"Human writes the agent brief" Agent writes docs/agent-briefs/<issue-number>.md from the issue body + linked artifacts
"Human applies labels" Agent emits the label transition; actual gh issue edit --add-label calls are gated by EVOKORE_AUTO_LABEL_ISSUES=true (DC-43)
"Maintainer dismisses out-of-scope items" Agent writes .out-of-scope/<slug>.md with rationale and emits the triage:wontfix label transition

Read the full file on GitHub · 226 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. 5d ago First seen · 226 lines · 62 tokens per session scan A 4537b53c9571

Subscribe to this mod's changes

github-triage is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 2,582 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.

Related

Other skills, from other repositories