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-pull-requestnpx skills add mitodl/agent-kit --skill create-ol-pull-requestgit 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 | $0.00075 | $0.02443 |
| Opus 5 | $0.00037 | $0.01222 |
| Sonnet 5 | $0.00015 | $0.00489 |
| Haiku 4.5 | $0.00007 | $0.00244 |
Grade C, and why
create-ol-pull-request scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- testing instructions --> How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Pull Request (/olpr)
When the user runs /olpr, or asks to open a pull request in a repo with a
mitodl remote, guide them through creating a PR using the org's standard
pull request template.
Auto-detection
This skill should activate automatically (without /olpr) when:
- The user says "create a PR", "open a pull request", "submit a PR", etc., and
- The current repo has a remote URL containing
github.com/mitodl/(verify withgit remote -v).
Step 1 — Inspect the branch and diff
Before prompting the user, gather context automatically:
# Confirm current branch and its upstream
git --no-pager branch --show-current
git --no-pager log --oneline origin/HEAD..HEAD
# Check for an existing open PR on this branch
gh pr view --json url,title,state 2>/dev/null
- If an open PR already exists for the branch, share its URL and stop — do not create a duplicate.
- If there are no commits ahead of the base, warn the user before proceeding.
Step 2 — Determine the base branch
Default to the repo's default branch (usually main). Override if the user
specifies a different target.
gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'
Step 3 — Gather PR metadata
Ask the user for each field in a single batched question, rather than inferring the body and asking them to correct it:
| Field | How to obtain |
|---|---|
| Title | Ask the user; offer one derived from the branch name / commits as a default they can overwrite |
| Linked tickets | Ask for issue numbers (Closes #, Fixes #, or N/A) |
| Description | Ask what the PR does; summarise from commits only if the user says "summarise"; summary should be short and high level; put detailed technical explanation of the PR in the <details> block |
| Screenshots | Ask if UI changes are present; skip section if not applicable |
| Testing notes | Ask how the changes were tested and how a reviewer can validate |
| Additional context | Ask for reviewer notes, caveats, or checklist items |
| Draft? | Ask if this should be a draft PR (default: no) |
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 · 258 lines · 75 tokens per session scan C 6251ceba8609
create-ol-pull-request is a skill published in the GitHub repository mitodl/agent-kit (2 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 75 tokens to every session and 2,443 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). 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…