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 commands/yashs33244/the_y_coding_standard/y-qagit clone --depth 1 https://github.com/yashs33244/the_y_coding_standardWrote 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/commands/yashs33244/the_y_coding_standard/y-qa)<a href="https://agentmods.dev/commands/yashs33244/the_y_coding_standard/y-qa"><img src="https://agentmods.dev/badge/commands/yashs33244/the_y_coding_standard/y-qa.svg" alt="Measured on agentmods" 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 | $0.00144 | $0.01693 |
| Opus 5 | $0.00072 | $0.00847 |
| Sonnet 5 | $0.00029 | $0.00339 |
| Haiku 4.5 | $0.00014 | $0.00169 |
Grade A, and why
y-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 5d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/y-qa
The "Does it work?" gate. Step 06 of the Sprint Loop. /y-review told us the code looks right on paper. /y-qa tells us the code actually runs. Tests pass. The golden path works. The obvious error paths do not crash. The obvious boundaries do not explode. The output is findings/YYYY-MM-DD-qa.md with a top-line verdict and the evidence behind it.
Pre-flight
Before running QA, confirm:
- We are in a git repo. If not, abort.
- There is an active plan in
plans/. Read it to know what user flows we are validating. - There is a recent
findings/YYYY-MM-DD-review.md. If not, suggest running/y-reviewfirst. If the user insists on skipping, log this as a concern in the QA report. - Today's date is known. Use it to name the findings file.
- The
findings/folder exists. If not, create it.
Ask the user once: "QA on current branch, recent commit, or a specified PR number?" Default to current branch.
Workflow
1. Identify the change scope
Capture:
- Current branch name.
- Recent commit messages:
git log --oneline -10. - Files changed since branching from main:
git diff --name-only main...HEAD.
Read the active plan and extract the user-facing flows we promised. These are the flows we will walk through.
2. Detect test runners
Look for config in this order:
package.jsonscripts and devDependencies. Look forvitest,jest,playwright,cypress,test.pyproject.tomlorpytest.iniortox.ini. Look forpytest.Cargo.toml. Look forcargo test.go.mod. Look forgo test.
If no test runner is configured, write a P1 finding in the QA report: "No test runner detected. Set one up before next sprint." Continue with manual checks only.
Load the right reference for context:
- Python tests:
references/python.md. - React / Next.js tests:
references/react-nextjs.md.
3. Run unit + integration tests
Run the detected test command. Capture full output, including:
- Total tests run.
- Passed / failed / skipped.
- Stack traces for failures.
- Time taken.
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.
- 5d ago First seen · 187 lines · 144 tokens per session scan A 90e2dafe7c4b
y-qa is a command published in the GitHub repository yashs33244/the_y_coding_standard (2 stars, last pushed 3mo ago), licensed MIT. It adds 144 tokens to every session and 1,693 once invoked, about $0.0007 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 commands, from other repositories
paul:verify
Guide manual user acceptance testing of recently built features.
plan-spec
仅在人工明确安排 UI 自动化时，根据任务、产品规则或原型生成独立行为 Spec.
journey-audit
Outside-in product audit as a deep session — 7 read-only roles check what the site promises against what the code does, what a user experiences, what arrives by mail, and what the data says is used. Writes a dossier; needs a per-repo journey-manifest.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.