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/create-ol-github-issuenpx skills add mitodl/agent-kit --skill create-ol-github-issuegit 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 | $0.00061 | $0.01709 |
| Opus 5 | $0.00030 | $0.00855 |
| Sonnet 5 | $0.00012 | $0.00342 |
| Haiku 4.5 | $0.00006 | $0.00171 |
Grade A, and why
create-ol-github-issue 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a GitHub Issue (/olissue)
When the user runs /olissue, guide them through creating a GitHub issue in a
mitodl repository using the org's standard issue templates.
Default organization
Always default to mitodl unless the user explicitly names a different org.
Step 1 — Gather required inputs
Ask the user for:
| Field | Notes |
|---|---|
| Repository | e.g. ol-django — org is implied as mitodl |
| Issue type | See template menu below |
| Title | Short, imperative sentence |
| Body details | Their text for each section of the chosen template |
Ask in a single batched question covering everything missing — one round trip, not a sequence of one-field prompts.
Ask for the body text; don't invent it. The user knows what the issue is about and you don't. Ask for their words per template section and use them mostly as given — tighten wording and fix formatting, but do not expand a one-line answer into three paragraphs. Only draft a section yourself when the user asks you to or points you at source material (an error, a code path, a thread) — and then show the draft before creating the issue.
Blank sections: the templates below mark optional sections with
<!--- optional — delete if empty --> (Possible Solution, Additional Details).
Delete those when empty rather than padding them. Every other section is
required — if one comes back blank, ask again for it instead of deleting it or
filling it in yourself. An issue with no Steps to Reproduce is the thing this
skill exists to prevent.
Step 2 — Choose a template
Present these four options and apply the matching template body:
| # | Name | Labels | Template file |
|---|---|---|---|
| 1 | Bug Report | bug |
bug.md |
| 2 | Technical Issue | (none) | default.md |
| 3 | Product Issue | (none) | product.md |
| 4 | Design QA | design QA |
designQA.md |
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 · 218 lines · 61 tokens per session scan A 67a280752cb3
create-ol-github-issue is a skill published in the GitHub repository mitodl/agent-kit (2 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 61 tokens to every session and 1,709 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…