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 skills add mushroomTW/MushroomTW-Skills --skill library-firstgit clone --depth 1 https://github.com/mushroomTW/MushroomTW-SkillsWrote 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/mushroomtw/mushroomtw-skills/library-first)<a href="https://agentmods.dev/skills/mushroomtw/mushroomtw-skills/library-first"><img src="https://agentmods.dev/badge/skills/mushroomtw/mushroomtw-skills/library-first/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mushroomtw/mushroomtw-skills/library-first"><img src="https://agentmods.dev/badge/skills/mushroomtw/mushroomtw-skills/library-first.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00065 | $0.01860 |
| Opus 5 | $0.00032 | $0.00930 |
| Sonnet 5 | $0.00013 | $0.00372 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
library-first 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 7d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library-First
Search before hand-writing a general mechanism; every line of custom code is a liability.
Invariants
- Emit exactly one terminal decision:
used,wrote manually, ordeferred. Usedeferredonly when a missing project fact makes a gate undecidable, and state both that nothing is to be implemented yet and the evidence that would unblock it. - A third-party package that fails the Quality Gate does not exist; judge a standard library by fitness and version support instead.
- Verify what you are unsure of; never guess.
Workflow
| Step | Action | Input | Output | Format |
|---|---|---|---|---|
| 1 | Name and route | requirement, variable names | domain term + search/manual |
e.g. exponential backoff retry, not callApiAgain; domain logic or a genuine three-line helper routes to manual |
| 2 | Search the ecosystem | search domain term + language |
1-3 candidates | cover the standard library + npm/PyPI/NuGet/pkg.go.dev/crates.io; manual skips to Step 4 |
| 3 | Evaluate candidates | candidates | Pass/Fail/Unknown/N/A |
apply the Quality Gate to third-party packages; confirm fitness and version support for a standard library |
| 4 | Terminal decision | evaluation results | used/wrote manually/deferred |
exactly one; see the templates |
🔴 CHECKPOINT 1 · 🛑 STOP — pause after Step 2 on the search path: confirm the standard library was covered, mainstream packages were covered, and the query used a domain term rather than a variable name. The manual path never fakes a search; it goes straight to Step 4.
Quality Gate (a third-party package is adopted only when all six pass)
Record each gate as Pass, Fail, Unknown, or N/A. Unknown is not a pass; N/A must state why the gate does not apply to this project. All Pass/N/A allows used; any Fail moves to the next candidate, and only after every candidate fails do you wrote manually; when Unknown is all that remains you must deferred, never a conditional sentence pretending the package was adopted.
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.
- 7d ago Changed · +2 lines ed67392bbd75
- 10d ago First seen · 102 lines · 65 tokens per session scan A 2279c8526a61
library-first is a skill published in the GitHub repository mushroomTW/MushroomTW-Skills (0 stars, last pushed 10d ago), licensed MIT. It adds 65 tokens to every session and 1,860 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
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
dorodango
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…