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/theafh/ai-modules/format_rustnpx skills add theafh/ai-modules --skill format_rustgit clone --depth 1 https://github.com/theafh/ai-modulesWhat 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 | $0.00087 | $0.01328 |
| Opus 5 | $0.00044 | $0.00664 |
| Sonnet 5 | $0.00017 | $0.00266 |
| Haiku 4.5 | $0.00009 | $0.00133 |
Grade A, and why
format_rust 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
format_rust
Preferred style
Use clear, procedural flow with small, single‑purpose functions and explicit data flow; keep names concrete so intent is obvious at a glance.
Clippy‑driven improvements
Write code that naturally satisfies clippy by choosing the simplest correct form, and treat clippy warnings as signals to improve clarity, safety, and maintainability.
Imports
Use only necessary imports and prefer direct module paths; remove unused imports promptly to keep warnings clean.
Errors versus broken invariants
Treat a failure the world causes — a missing file, malformed input, a value that does not parse, a timeout — as a Result the caller handles with ?. Treat a failure that means one of the program's own guarantees is false as a panic, because continuing would compute on state already known to be void. Reach for unwrap only in that second category: it is an assertion, not a fallback. At each fallible call, decide whether failure there means the world is wrong or the code is wrong, and route accordingly — using unwrap because writing the error type is tedious claims a broken invariant while actually sitting in an unhandled error.
Fallible builders
Route fallible builder APIs through Result and the error idiom the consumer of that API selects under Error idiom follows the consumer, returning that error type from the builder rather than panicking.
Panic discipline across a trust boundary
On any path reachable from input the process does not control, return a typed error the caller handles. Treat the constructs that panic on failure — unwrap, expect, direct indexing and slicing, and arithmetic that can overflow — as defects on that path, because an input that reaches one is a remotely triggerable denial of service.
An expect message names the invariant
Where a panic is the correct outcome, write an expect whose message names the invariant the site rests on rather than the symptom, and leave bare unwrap behind. That message makes the claim reviewable: a reader can check the stated invariant, while a bare unwrap cannot distinguish a proven claim from a skipped error path.
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 · 82 lines · 87 tokens per session scan A 56afb5e18b04
format_rust is a skill published in the GitHub repository theafh/ai-modules (38 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 1,328 once invoked, about $0.0004 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
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…