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/fatihkan/badiWrote 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/fatihkan/badi/eng-review)<a href="https://agentmods.dev/commands/fatihkan/badi/eng-review"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/eng-review.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 | $0.00000 | $0.00749 |
| Opus 5 | $0.00000 | $0.00375 |
| Sonnet 5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
eng-review 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 today.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering review command. Turns a green-lit goal into a locked architecture and a sequenced, shippable increment plan via the engineering-manager agent.
Required Tools
- Read (context, specs, existing code)
- Grep / Glob (map the affected surface)
- Bash (git status / structure inspection)
- Agent (delegate to engineering-manager; optionally architecture-advisor — both launched by the main thread)
When to Use
After /ceo-review green-lights a bet, before writing code. Run this to lock the approach and break the work into independently mergeable increments. The output feeds implementation and, later, /qa and /ship.
Procedure
Step 1: Frame the Goal
- Read the green-lit scope (from
/ceo-review, a spec, or the user). - Map the affected files, modules, and external dependencies.
- Note constraints from
memory.md/knowledge-base.md.
Step 2: Delegate to Engineering Manager
Launch the engineering-manager agent. Ask it to:
- Lock one architectural approach (and name the rejected alternatives).
- Break the goal into increments that each ship value and merge independently.
- Sequence by dependency and risk; front-load unknowns.
- Name, per increment, an implementer (who writes the code: the main thread by default, or a write-capable agent) separately from the advisory reviewer(s) — the read-only specialists (architecture-advisor, security-scanner, test-strategist, refactoring-advisor, performance-profiler, …) that review the implementer's diff. Review specialists cannot write code, so they are never the implementer.
- State the definition of done per increment.
The engineering-manager has no Agent tool and cannot delegate. If it flags a deep design question it cannot settle, the main thread launches architecture-advisor with that question and passes the answer into the engineering-manager's brief (or its re-brief in Step 3).
Step 3: Validate the Plan
Check the returned plan against all four:
- Is each increment shippable in a single PR?
- Is the riskiest work first?
- Are dependencies explicit and acyclic?
- Does each increment have a clear acceptance bar?
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.
- today First seen · 49 lines · 0 tokens per session scan A b4e0cc49abc7
eng-review is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 749 tokens. 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 2026-09-06.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524) — sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
qa
Systematic QA testing of a web application — diff-aware, tiered, with fix-and-verify loop.
review-pr
Perform a comprehensive code review of a pull request.
security-audit
Comprehensive security audit with scored posture assessment.