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.
git clone --depth 1 https://github.com/Evyasys-Software-Solutions/EvyaGovernanceWrote 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/evyasys-software-solutions/evyagovernance/qa)<a href="https://agentmods.dev/commands/evyasys-software-solutions/evyagovernance/qa"><img src="https://agentmods.dev/badge/commands/evyasys-software-solutions/evyagovernance/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/commands/evyasys-software-solutions/evyagovernance/qa"><img src="https://agentmods.dev/badge/commands/evyasys-software-solutions/evyagovernance/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 | $0.00143 | $0.00812 |
| Opus 5.5 | $0.00057 | $0.00325 |
| Sonnet 5.5 | $0.00029 | $0.00162 |
| Haiku 4.5 | $0.00014 | $0.00081 |
Grade B, and why
Qa scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
EVYA_AI=$(find "$HOME/.claude/plugins" -maxdepth 6 -type d -name ".ai" 2>/dev/null | grep -i "EvyaGovernance" | head -1); [ -z "$EVYA_AI" ] && EVYA_AI=".ai"; echo "$EVYA_AI" What it actually says
You are running /evyasys:Qa $ARGUMENTS.
Step 0 — Load workflow
First — find the plugin's installed workflow directory (do this before any file read):
macOS / Linux — run via Bash:
EVYA_AI=$(find "$HOME/.claude/plugins" -maxdepth 6 -type d -name ".ai" 2>/dev/null | grep -i "EvyaGovernance" | head -1); [ -z "$EVYA_AI" ] && EVYA_AI=".ai"; echo "$EVYA_AI"
Windows — run via PowerShell:
$EVYA_AI = (Get-ChildItem "$env:USERPROFILE\.claude\plugins" -Recurse -Directory -Filter ".ai" -ErrorAction SilentlyContinue | Where-Object { $_.FullName -like '*EvyaGovernance*' } | Select-Object -First 1 -ExpandProperty FullName); if (-not $EVYA_AI) { $EVYA_AI = ".ai" }; Write-Output $EVYA_AI
Use the printed path in place of .ai for every workflow file read below, and as $EVYA_AI in the script commands the
prompt gives you ($EVYA_AI/../scripts/lib/…). If a file is not found at the plugin path (older install), fall back to the
same path under .ai/. Project files under .evyasys/workflows/qa/ override same-named plugin files.
Load these from <plugin-ai>/workflows/qa/:
AGENT.md— your role, mandate and what you never doPROMPT.md— the nine steps, the HARD-GATE and the output contractPLAN_SCHEMA.md— the exact manifest and block formats the hook acceptsCHECKLIST.md— the self-review gateQUESTIONING.md— when and how to ask (mode, scope, source, environment, token variable name, Playwright)
The templates (TEST_PLAN_TEMPLATE.md, RELEASE_NOTES_TEMPLATE.md) are used in story mode.
release mode only — also load RELEASE_AGENT.md, RELEASE_PROMPT.md, RELEASE_CHECKLIST.md and RELEASE_DOC_TEMPLATE.md, and follow RELEASE_PROMPT.md instead of PROMPT.md (its output is one <!-- EVYARELEASE {…} --> block).
Then follow PROMPT.md exactly. Never write to production. Never call an application API except through qa-http.js.
Plan from the code before touching any environment. Never file bugs yourself — the hook groups failures and the user approves each one.
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.
- 10d ago First seen · 41 lines · 143 tokens per session scan B 8ed29f5f114a
Qa is a command published in the GitHub repository Evyasys-Software-Solutions/EvyaGovernance (7 stars, last pushed 7d ago), licensed MIT. It adds 143 tokens to every session and 812 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other commands, from other repositories
tdd
Test-driven development with tests that actually catch breaks: red before green, name the break each test catches, and the mutation check before done.
ci
CI/CD hygiene and run health: pinned actions, timeouts, concurrency, tests — plus the latest runs via gh.
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.
add-entry
Command "add-entry" from gosha70/code-copilot-team, covering /add-entry, procedure and refuse to merge if.
debate
Run adversarial debate to stress-test and improve a document.
CLAUDE_CODE_107_FEATURE_AUDIT
A command that reads the code for 107 features and judges whether each is ready for production. It records the results in an Excel file.