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/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/review)<a href="https://agentmods.dev/commands/d-padmanabhan/agent-engineering-handbook/review"><img src="https://agentmods.dev/badge/commands/d-padmanabhan/agent-engineering-handbook/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 | $0.00009 | $0.00547 |
| Opus 5 | $0.00005 | $0.00273 |
| Sonnet 5 | $0.00002 | $0.00109 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
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 7d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REVIEW MODE ACTIVATED
You are now in REVIEW phase.
Your Tasks
-
Verify Implementation
- Check that changes match the approved plan
- Ensure all planned items are complete
- Confirm no unrelated changes were made
-
Check for Issues
- Security vulnerabilities
- Bugs or edge cases
- Performance concerns
- Error handling gaps
-
Review Against Standards
- Code follows 100-core.mdc guidelines
- Language-specific rules applied
- Tests added/updated
- Documentation updated
-
Suggest Improvements
- Note potential improvements but DON'T implement them
- These are for future work, not this PR
- Prioritize by impact
-
Update Context Files
- Document findings in
reflect-*.mdortasks.md - Note lessons learned
- Document findings in
Review Checklist
Correctness
- Changes match the agreed plan
- All edge cases handled
- Error handling appropriate
- No regressions introduced
Security
- No hardcoded secrets
- Input validation present
- No injection vulnerabilities
- Principle of least privilege followed
Quality
- Code follows existing patterns
- Naming is clear and consistent
- No unnecessary complexity
- DRY principle followed
Testing
- Tests added/updated
- Edge cases covered
- Tests pass locally
Documentation
- Code comments where needed
- README updated if applicable
- API docs updated if applicable
Output Format
## Review Summary
### What Was Implemented
- [Summary of changes]
### Verification
- [x] Matches approved plan
- [x] All items complete
- [ ] Issue found: [description]
### Issues Found
1. **[Critical/Recommended/Optional]**: [Issue description]
- Location: `file.py:123`
- Suggestion: [How to fix]
### Suggested Improvements (Future Work)
- [Improvement 1]
- [Improvement 2]
### Ready to Commit?
[Yes/No - with reasoning]
After Review
If ready to commit, use the Git workflow skill (${HANDBOOK_ROOT}/skills/git-workflow/SKILL.md) for message format and the Git rule (${HANDBOOK_ROOT}/rules/130-git.mdc) for mandatory approval and signing gates.
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.
- 7d ago First seen · 101 lines · 9 tokens per session scan A 6bcb1eecdb58
review is a command published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 8d ago), licensed MIT. It adds 9 tokens to every session and 547 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.