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 Tasachii/Tasachii-Tools --skill craft-qagit clone --depth 1 https://github.com/Tasachii/Tasachii-ToolsWrote 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/tasachii/tasachii-tools/craft-qa)<a href="https://agentmods.dev/skills/tasachii/tasachii-tools/craft-qa"><img src="https://agentmods.dev/badge/skills/tasachii/tasachii-tools/craft-qa/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/tasachii/tasachii-tools/craft-qa"><img src="https://agentmods.dev/badge/skills/tasachii/tasachii-tools/craft-qa.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 | $0.00190 | $0.01689 |
| Opus 5 | $0.00095 | $0.00844 |
| Sonnet 5 | $0.00038 | $0.00338 |
| Haiku 4.5 | $0.00019 | $0.00169 |
Grade A, and why
craft-qa 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 12d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
craft-qa — smoke-test, QA, and score a project from four angles
Run a project through its own checks, judge it as four different experts would, and hand back one scorecard plus a precise, fixable list of what's wrong. The deliverable is a verdict and a to-do list — not a wall of logs. It never fixes anything on its own; it scores, then asks.
Inputs
- Target — a project directory (default: the current repo) and/or a URL / local dev server
(
localhost:5173) for a web app. If it's unclear which project, ask before starting. - Focus (optional) — a specific area ("the checkout flow", "the build"). If omitted, cover the whole project at a sensible depth.
Procedure
1. Identify the project
Read the README and manifests (package.json, pyproject.toml, Cargo.toml, go.mod,
.claude-plugin/, Makefile) to learn the stack, the type (web app · library · service · CLI ·
plugin/marketplace), and the commands it actually defines. Never assume a command exists — detect it.
2. Smoke test — run only what the project actually has
Run the checks that exist, capture pass/fail and the real output. Map by stack:
| Stack / type | Run what is present |
|---|---|
| Node / web | npm run build, lint, typecheck, test — only scripts that exist in package.json |
| Python | pytest, ruff / flake8, mypy, or a documented --dry-run entrypoint |
| Rust / Go | cargo build / test / clippy, go build / vet / test |
| Claude plugin / marketplace | claude plugin validate <each plugin>, manifest + version consistency |
| Anything | Does it start? Do referenced files and links resolve? Is committed junk present (git ls-files)? |
Don't fabricate a test suite that isn't there — record "no tests defined" as a finding, not a fake pass.
3. Web apps — drive a real browser (local, free)
Browser QA has one optional prerequisite — the chrome-devtools MCP must be configured in
Claude Code (it is the plugin's only external dependency). It degrades gracefully: without it, the
codebase checks still run and you score the rest, noting the gap rather than blocking.
If the target is a web app and a dev server is reachable (or you can start it), exercise the happy
path through mcp__chrome-devtools__* — local Chrome, no cloud, data stays on the machine:
navigate_page → take_snapshot / take_screenshot → click / fill through the flow →
list_console_messages + list_network_requests for JS errors and 4xx/5xx. Judge the
screenshots yourself. If chrome-devtools isn't connected, say so and score the rest — don't block.
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.
- 12d ago First seen · 99 lines · 190 tokens per session scan A 832ee7cefdfa
craft-qa is a skill published in the GitHub repository Tasachii/Tasachii-Tools (2 stars, last pushed 1mo ago), licensed MIT. It adds 190 tokens to every session and 1,689 once invoked, about $0.0010 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
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…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.