Borrowing it
Nothing to install: this file belongs to archfill/tsumugi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/archfill/tsumugi/main/.agents/skills/tsumugi-verify/SKILL.mdgit clone --depth 1 https://github.com/archfill/tsumugiWrote 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/archfill/tsumugi/tsumugi-verify)<a href="https://agentmods.dev/skills/archfill/tsumugi/tsumugi-verify"><img src="https://agentmods.dev/badge/skills/archfill/tsumugi/tsumugi-verify/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/archfill/tsumugi/tsumugi-verify"><img src="https://agentmods.dev/badge/skills/archfill/tsumugi/tsumugi-verify.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 | $0.00078 | $0.00761 |
| Opus 5 | $0.00039 | $0.00380 |
| Sonnet 5 | $0.00016 | $0.00152 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
tsumugi-verify 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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify tsumugi changes
Choose checks from the actual diff. Do not equate command success with complete coverage.
Establish the change scope
- Read
AGENTS.mdanddocs/ROADMAP.mdwhen the change affects product behavior or architecture. - Inspect
git status --short, changed filenames, and the relevant diff. - Preserve unrelated user changes and exclude generated or private files from conclusions unless they are part of the requested scope.
- Classify the change with references/verification-matrix.md.
Run checks progressively
- Start with the narrowest targeted test or static check.
- Run package-level typecheck/test/build for affected packages.
- Run workspace CI-equivalent checks when the change crosses packages or is being prepared for commit/push/deploy.
- Add database, browser, smoke, or eval validation only when the change requires it.
- Use context-preserving output processing for large test, build, diff, or log output. Surface exact failures and summaries instead of raw output.
The primary CI parity commands are:
pnpm typecheck
pnpm -r build
pnpm -r test
Always run git diff --check before declaring a code change ready. This command does not inspect untracked files: validate those files directly, or run git diff --cached --check only after staging has been explicitly authorized.
Interpret coverage honestly
- Server
testruns Vitest. - UI, shared, and CLI
testscripts currently report that no tests exist; their success is not automated behavioral coverage. - Repository
lintscripts are placeholders and are not a meaningful quality gate. - Server eval files are outside the ordinary production TypeScript build path. Validate relevant benches at runtime when behavior in search, promotion, or dreaming changes.
- Separate public synthetic fixtures from private fixtures. Never imply private-quality validation if only synthetic fixtures ran.
- A successful mocked repository test does not replace a real PostgreSQL integration check for new SQL.
- Static skill validation does not prove Codex discovery or implicit invocation in the current task. Confirm skill availability in a new task when that behavior is part of the acceptance criteria.
What ships with it
2 files 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.
- 8d ago First seen · 71 lines · 78 tokens per session scan A c2cb9fc1424e
tsumugi-verify is a skill published in the GitHub repository archfill/tsumugi (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 78 tokens to every session and 761 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 2026-08-31.
Other skills, from other repositories
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
project-knowledge
Accumulated project memory: verified gotchas and prior findings for oh-my-posh work. Consult BEFORE touching shell integration scripts (zsh, pwsh, fish, bash, cmd/Clink), terminal or pty behavior, WSL-based shell testing, or internals (cache, segments, streaming, serve daemon). Read only the topic files relevant to…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
performing-fuzzing-with-aflplusplus
Perform coverage-guided fuzzing of compiled binaries using AFL++ (American Fuzzy Lop Plus Plus) to discover memory corruption, crashes, and security vulnerabilities. The tester instruments target binaries with afl-cc/afl-clang-fast, manages input corpora with afl-cmin and afl-tmin, runs parallel fuzzing campaigns with…
codspeed-optimize
Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster'…