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/kaeawc/auto-mobile/github-clinpx skills add kaeawc/auto-mobile --skill github-cligit clone --depth 1 https://github.com/kaeawc/auto-mobileWhat 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 | $0.00048 | $0.02360 |
| Opus 5 | $0.00024 | $0.01180 |
| Sonnet 5 | $0.00010 | $0.00472 |
| Haiku 4.5 | $0.00005 | $0.00236 |
Grade A, and why
github-cli 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub CLI Usage
Shared dependency for check-ci, github-pr-feedback, auto-mobile-code-review,
pr-analysis, push-pr, and push-my-prs.
- Prefer
gh pr view|list|create|editandgh issue list|view. - Reach for
gh api/GraphQL only where the subcommands fall short — review-thread resolution state and live job logs are the two cases that matter here. - Write long output to
scratch/and summarize. Job logs run 100KB+; never let one into the conversation whole.
PR feedback: four separate surfaces
No single endpoint returns all PR feedback. Collect all four, paginated, or miss whole categories:
gh api --paginate "repos/kaeawc/auto-mobile/issues/<PR>/comments?per_page=100" # conversation
gh api --paginate "repos/kaeawc/auto-mobile/pulls/<PR>/reviews?per_page=100" # review verdicts
gh api --paginate "repos/kaeawc/auto-mobile/pulls/<PR>/comments?per_page=100" # inline (no resolution state)
# review threads — the only source of resolution state — below
These three return top-level JSON arrays, and --paginate merges the pages into one flat
array, so redirecting to a file and parsing it with jq is safe. Verified on gh 2.96 against
PR #4117 with per_page=2: five GET requests, one top-level document, element count matching
the unpaginated result. (The gh api manual describes pages as separate documents — true for
GraphQL and for object-shaped responses, but not for these array endpoints on this version. If
you are on an older gh, re-check before relying on it.) Do not add --slurp
here: on an array endpoint it produces an array of pages ([[…],[…]]), and it is rejected
outright when combined with --jq (the --slurp option is not supported with --jq or --template). GraphQL is the opposite case — see below.
Scope everything to the PR's headRefOid; after any push, re-collect from the new head. For
the triage workflow — ledger, dispositions, resolution conditions — use github-pr-feedback.
This is just the mechanics.
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 · 189 lines · 48 tokens per session scan A 57d07943780d
github-cli is a skill published in the GitHub repository kaeawc/auto-mobile (45 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 2,360 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…