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 skills/mitodl/agent-kit/github-issue-triagenpx skills add mitodl/agent-kit --skill github-issue-triagegit clone --depth 1 https://github.com/mitodl/agent-kitWhat 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 | $0.00082 | $0.03247 |
| Opus 5 | $0.00041 | $0.01623 |
| Sonnet 5 | $0.00016 | $0.00649 |
| Haiku 4.5 | $0.00008 | $0.00325 |
Grade A, and why
github-issue-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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue Triage
Produces a backlog health report: which open issues are done, superseded, or still real — backed by evidence from the live codebase and git history.
Three deterministic scripts are provided in scripts/:
| Script | Purpose |
|---|---|
fetch-issues.sh |
Download all open issues to a JSON file |
explore-issue.sh |
Cross-reference a single issue against the local repo |
close-issues.sh |
Bulk-close or bulk-comment on a list of issue numbers |
Repo modes
The triage process behaves differently depending on how the target GitHub repo is organised:
| Mode | Description | Example |
|---|---|---|
| Direct | Issues live in the same repo as the code they describe | mitodl/ol-infrastructure |
| Tracker | A catch-all repo holds issues; labels route each issue to the actual product repo | mitodl/hq |
Detect the mode before batching. In tracker repos, each issue's product label is the routing key to the codebase that needs to be searched. Skipping this step causes every agent to search the wrong repo (the empty tracker), producing no evidence and unreliable verdicts.
Overview
The core pattern is enumerate → resolve → batch → fan out → synthesize:
- Fetch all open issues with full bodies (
fetch-issues.sh). - (Tracker repos only) Build a label→local-path map and annotate each issue with the correct codebase path to search.
- Group issues into 4–6 thematic batches, keeping same-product issues together so each agent searches one codebase.
- Dispatch one subagent per batch in parallel; each uses
explore-issue.shand targetedrg/git logsearches to gather evidence. - Synthesize per-batch verdicts into a tiered report.
- Optionally act on the report with
close-issues.sh.
Phase 1 — Fetch issues
./skills/process/github-issue-triage/scripts/fetch-issues.sh \
mitodl/ol-infrastructure \
/tmp/issues_full.json
The script writes a JSON array. Extract a compact view for mode detection:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 370 lines · 82 tokens per session scan A c42c0791de0d
github-issue-triage is a skill published in the GitHub repository mitodl/agent-kit (2 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 82 tokens to every session and 3,247 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.