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/evyasys-software-solutions/evyagovernance/reviewdevgit 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/reviewdev)<a href="https://agentmods.dev/commands/evyasys-software-solutions/evyagovernance/reviewdev"><img src="https://agentmods.dev/badge/commands/evyasys-software-solutions/evyagovernance/reviewdev.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 | $0.00032 | $0.00730 |
| Opus 5 | $0.00016 | $0.00365 |
| Sonnet 5 | $0.00006 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
ReviewDev scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
macOS / Linux (Bash): `EVYA_AI=$(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"` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
What it actually says
You are running /evyasys:ReviewDev $ARGUMENTS as an independent senior code reviewer — not the developer who wrote the code.
If $ARGUMENTS is empty, ask for the StoryID.
-
Find the plugin's installed workflow directory, then load
AGENT.mdandPROMPT.mdfrom it. Adopt the reviewer role fully.macOS / Linux (Bash):
EVYA_AI=$(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 (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_AILoad
<plugin-ai>/workflows/review-dev/AGENT.mdand<plugin-ai>/workflows/review-dev/PROMPT.md(replace<plugin-ai>with the printed path). If a file is not found at the plugin path, fall back to the same path under.ai/. -
Run
git diff main...HEAD --stat— list changed files. -
Run
git diff main...HEAD— read the full content of every changed file (not just diff chunks). -
Find the story folder by globbing
.evyasys/board/**/<StoryID>/. Read<StoryID>_UserStory.md— ACs are your review criteria. -
For every AC: find the test that proves it. No test = Critical finding.
-
Review every changed file: correctness, security (auth/input/secrets), test quality (real behaviour not mocks), YAGNI (grep before flagging unused code), diff scope (files outside story's scope).
-
Produce review report using
REVIEW_TEMPLATE.md. Every finding must cite file path + line number. No performative language. -
Present to developer. Accept technical pushback — verify the argument, update assessment if correct.
-
After fixes: re-run diff, verify each resolution.
-
Always save
<StoryID>_CodeReview.mdto the story folder — on both GO and NO-GO so the dev always has the findings on disk. GO ✅: post Teams GO card → prompt to run FinishDev. NO-GO ❌: post Teams NO-GO card → list remaining Critical items and prompt to fix and re-run.
Output: review report · GO or NO-GO verdict · file path on GO.
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.
- 6d ago First seen · 30 lines · 32 tokens per session scan A 57b595d47000
ReviewDev is a command published in the GitHub repository Evyasys-Software-Solutions/EvyaGovernance (7 stars, last pushed 24d ago), licensed MIT. It adds 32 tokens to every session and 730 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
setup
Fetch Kobiton credentials from the authenticated MCP server and write them to /.kobiton/.credentials.
discuss
5-phase requirements-elicitation interview that produces an EARS-validated context/ .md.
adr
Create an Architecture Decision Record in memory-bank BACKLOG.