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 skills add Kevin-Liu-01/Agent-Machines --skill plan-mode-reviewgit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/skills/kevin-liu-01/agent-machines/plan-mode-review)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/plan-mode-review"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/plan-mode-review/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/skills/kevin-liu-01/agent-machines/plan-mode-review"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/plan-mode-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 63 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00042 | $0.00791 |
| Opus 5 | $0.00021 | $0.00396 |
| Sonnet 5 | $0.00008 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
plan-mode-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 9d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan-Mode Review Checklist
A structured review pass that catches issues before they ship. Walk through each section in order. A finding in section 1 invalidates everything in sections 2-4 -- don't review code that isn't the right code.
1. Architecture
- Is the right system absorbing this change? If a frontend bug is being fixed in the backend, stop.
- Are existing patterns being matched, or is a new pattern being introduced? New patterns require justification.
- Is this a one-way door (hard to reverse) or a two-way door? One-way decisions get more scrutiny.
- Does the public API change? If yes, what's the migration story?
- Does the change cross trust boundaries? (See
security-audit.)
2. Code quality
- Functions ≤ 70 lines, files ≤ 500 lines, args ≤ 5, nesting ≤ 3 levels.
- Function name doesn't contain "and"; if it does, split.
- No
any(TypeScript) orAny(Python) without explicit, documented justification. - No fallback chains (
a or b or c). Explicit branches. - No ternaries used for control flow. Early returns instead.
- Comments explain intent, not what. Remove narrative comments.
- Match the surrounding style. If the file uses factories, use factories.
3. Tests
- New behavior has a new test. Bug fixes have a regression test that fails before the fix.
- Tests describe invariants ("a paid user cannot see the trial banner"), not specific bugs ("regression test for issue #1234").
- No tests that mock the system under test (mock-echo). Tests must exercise real behavior.
- Tests pass under the real CI command, not a local subset.
4. Performance
- Hot paths: any new allocation in a per-request path? Any new DB round-trip? Any N+1?
- New dependencies pulled in transitively? Bundle size delta if frontend.
- Any new feature flag, cache, or polling? Justify TTLs.
5. Errors and observability
- Failure modes have specific error types, not generic
Exception/Error. - User-facing errors don't leak internal state (host names, IPs, stack traces, schema).
- Operator-facing logs are structured (logger.error with kv pairs), not f-string blobs.
- Correct HTTP status code: 422 for malformed fields, 409 for state conflicts, 400 for syntax, 500 for our bugs.
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.
- 9d ago First seen · 72 lines · 42 tokens per session scan A 952b848b7a82
plan-mode-review is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 791 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
dx-roaster
Brutally honest developer-experience audit for a GitHub repo. Scores 10 DX dimensions (time-to-first-success, README clarity, visual proof, install, quick-start, docs, examples, community, trust, marketing), writes a shareable roast in the requested tone (brutal/honest/kind), produces a prioritized action plan ranked…
mcp-review
Review MCP server specifications and updates for compliance, security, and quality. Use when evaluating server.json files, PRs adding/updating servers, or assessing MCP server changes. NOT for creating new entries (use add-mcp-server instead).
code-review
When the user wants a thorough code review of changes, a PR, a file, or a feature branch. Use when the user says "review this," "code review," "check my code," "what's wrong with this," "review my PR," "look over this," "critique this," "review before merge," or when submitting code for quality assessment. Performs…
holix-cron
Schedule recurring agent tasks via Holix built-in gateway cron (not crontab or custom scripts).
review-guidelines
Additional code review guidelines specific to this codebase. Auto-loaded by the review agent during PR reviews to enforce project conventions.
quick-review
Review a code diff or file for correctness bugs, security issues, and clear simplifications. One finding per line, severity-tagged. Use when user wants fast, focused code review.