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-rfc-discussionnpx skills add mitodl/agent-kit --skill create-ol-rfc-discussiongit clone --depth 1 https://github.com/mitodl/agent-kitWrote 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.
[](https://agentmods.dev/skills/mitodl/agent-kit/create-ol-rfc-discussion)<a href="https://agentmods.dev/skills/mitodl/agent-kit/create-ol-rfc-discussion"><img src="https://agentmods.dev/badge/skills/mitodl/agent-kit/create-ol-rfc-discussion.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.02745 |
| Opus 5 | $0.00028 | $0.01373 |
| Sonnet 5 | $0.00011 | $0.00549 |
| Haiku 4.5 | $0.00006 | $0.00275 |
Grade A, and why
create-ol-rfc-discussion 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.
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an RFC Discussion (/olrfc)
When the user runs /olrfc, or asks to post/create an RFC, guide them through
writing a short, high-altitude RFC and posting it to mitodl/hq as a
GitHub Discussion in the RFC category.
What an RFC is for
An RFC exists to get a team of busy people to agree on what problem we're solving, roughly how we intend to solve it, and what that commits us to. It is a decision document, not a design document.
The implementation detail follows later, as a spec opened against the target repositories. Anything a reader does not need in order to say "yes, go do that" belongs in the spec — not here.
| Belongs in the RFC | Belongs in the spec |
|---|---|
| The problem and why now | Schemas, interfaces, function signatures |
| The 2–3 real options and why they lose/win | File and module layout |
| The chosen direction, in shape not steps | Ordered task breakdown, estimates |
| What the decision commits us to, and what it costs | Test plans, migration scripts |
| Questions that could change the decision | Config keys, flag names, env vars |
| Links to prior art / related RFCs | Error handling, edge cases |
If you catch yourself writing code blocks, type definitions, or a numbered build plan, you have crossed into spec territory. Cut it.
Length budget — this is a hard requirement
Target: 800–1,500 words. Ceiling: 2,000. That is a 5–10 minute read. RFCs that run 20–30 minutes do not get read, and unread RFCs do not produce decisions.
Rough per-section budget:
| Section | Budget |
|---|---|
| Problem | 150–300 words |
| Options Considered | 300–500 words total across all options |
| Decision | 150–250 words |
| Approach | 150–300 words |
| Consequences | 100–200 words |
| Open Questions | 75–150 words |
Before posting, check it:
wc -w /tmp/rfc-body.md
If it is over 2,000, cut — do not rationalise. The usual offenders, in order: step-by-step implementation plans, exhaustive option enumeration, restating the problem inside the Decision section, and worked examples.
What ships with it
1 file 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.
- 5d ago First seen · 312 lines · 57 tokens per session scan A 23d4235032b5
create-ol-rfc-discussion is a skill published in the GitHub repository mitodl/agent-kit (2 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 57 tokens to every session and 2,745 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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-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…