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/lee-w/maigo/github-reply-draftnpx skills add Lee-W/maigo --skill github-reply-draftgit clone --depth 1 https://github.com/Lee-W/maigoWhat 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 | $0.00047 | $0.01320 |
| Opus 5 | $0.00023 | $0.00660 |
| Sonnet 5 | $0.00009 | $0.00264 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
github-reply-draft 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Reply Draft
Owner: — (orchestrator/agent drafting GitHub replies)
Consumers: /maigo:address-comments (per-thread replies at Finale), /maigo:review (reply drafts at criti gate)
Overview
Drafting GitHub PR replies badly is a recurring source of reviewer friction. Common failure modes: long preambles, referencing mid-iteration helpers that were deleted before merge, merging all threads into one PR-level comment, or overclaiming that a thread is "done ✅" when the reviewer has not yet confirmed acceptance.
This skill captures the six conventions that prevent those failures.
Convention 1 — Default terse
The opening sentence names what changed. If there is a deliberate trade-off, one more sentence names it and signals the user can ask for more detail. Cut: preamble, restating the reviewer's comment, hedging phrases ("hopefully this addresses...", "I believe this should..."), verification narrative ("I re-ran the comparison and got the same result"), the process of what was done, and anything the reviewer can already see from the diff.
The user will ask for more, not less — default short.
Word-level conventions:
- Prefer an em-dash over
, sofor casual flow (reports should stay in sync from now on, not, so reports should stay in sync). - No comma after a sentence-starting
Alsobefore a verb (Also updated the file, notAlso, updated the file). - Avoid vague abstract nouns ("window", "a while", "soon", "some buffer") — swap each for the concrete, quantifiable mechanism behind it (a number of seconds, a count, an explicit configurable flag). A vague noun reads as hand-waving; a measurable mechanism is something a reviewer can actually evaluate and implement.
Good:
validate_emailnow raisesValueErroron empty input instead of propagatingIndexError.
Bad:
Thank you for catching this. I've reviewed your comment about the empty-input case on
validate_emailand I believe I've addressed the concern by adding...
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.
- 2d ago First seen · 146 lines · 47 tokens per session scan A 27a5b7181334
github-reply-draft is a skill published in the GitHub repository Lee-W/maigo (14 stars, last pushed 8d ago), licensed MIT. It adds 47 tokens to every session and 1,320 once invoked, about $0.0002 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 2026-08-30.
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…