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/robisson/build-like-amazon-agent-skillsWrote 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/robisson/build-like-amazon-agent-skills/review)<a href="https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/review"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/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 | $0.00586 |
| Opus 5 | $0.00000 | $0.00293 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00059 |
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review — Code Review Bar Raising
Path resolution: All
skills/,agents/, andpatterns/paths in this command are relative to the plugin root directory. If not found in the working directory, resolve from the plugin installation path.
You are activating the review skill chain: code-review-bar-raising → operational-readiness-review.
What to do
- Read skills at
skills/code-review-bar-raising/andskills/operational-readiness-review/. - Perform a comprehensive review of the code or system under examination.
Step 1: Code Review (Bar Raising)
Review code against these dimensions:
- Correctness: Does it do what it claims? Edge cases handled?
- Simplicity: Is there a simpler way? Remove unnecessary abstractions.
- Naming: Are names precise and self-documenting?
- Testing: Are tests sufficient, meaningful, and maintainable?
- Security: Input validation, authz checks, secret handling?
- Performance: Obvious inefficiencies? Unbounded operations?
- Operational readiness: Logging, metrics, error handling, retries?
- Documentation: Would a new team member understand this in 6 months?
Provide feedback as:
- 🚫 Must fix — blocks merge (correctness, security, data loss risks)
- ⚠️ Should fix — strongly recommended (clarity, maintainability)
- 💡 Consider — optional improvements (style, alternative approaches)
Step 2: Operational Readiness Review
Before production deployment, verify:
- Runbook exists for common failure scenarios
- Alarms fire before customers notice
- Rollback plan is documented and tested
- Load testing validates capacity assumptions
- Dependencies are understood and failure modes documented
- On-call team knows about the change
Implementation Memory Capture
After the review is complete and findings are resolved, check whether any findings represent a recurring pattern (same finding across 2+ PRs, or the reviewer explicitly flags "this keeps happening"). If so:
- Read
skills/implementation-memory/SKILL.md. - Generate a self-reflection: "What recurring implementation mistake does this finding reveal? What rule would prevent it in future builds?"
- Extract up to 2 candidate learnings.
- Present candidates to the user for Accept / Reject / Edit (same format as
/buildsemi-automatic trigger). - Apply admission checks and rejection rules before writing to
docs/implementation-memory.md.
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 · 53 lines · 0 tokens per session scan A 300290a0c7f6
review is a command published in the GitHub repository robisson/build-like-amazon-agent-skills (14 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 586 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 2026-08-30.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
critique
Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation.
fix-comments
Address PR review comments by implementing requested changes automatically.
review
Perform a thorough code review of the current uncommitted changes or a specified file/directory.
review-open-prs
Command "review-open-prs" from The-Artificer-of-Ciphers-LLC/skills-from-the-artificer, covering batch pr review directive — all open prs i did not author, phase a — enumerate target prs & build the queue, phase b — per-pr directive (runs once per queued $pr), 0. context anchoring and 1. preconditions.
advisor
Get a second opinion from Codex (GPT-5) on your current plan, diff, or a specific question.