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 PackmindHub/packmind --skill michel-packmind-engineer-reviewgit clone --depth 1 https://github.com/PackmindHub/packmindWrote 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/packmindhub/packmind/michel-packmind-engineer-review)<a href="https://agentmods.dev/skills/packmindhub/packmind/michel-packmind-engineer-review"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/michel-packmind-engineer-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00181 | $0.02432 |
| Opus 5 | $0.00090 | $0.01216 |
| Sonnet 5 | $0.00036 | $0.00486 |
| Haiku 4.5 | $0.00018 | $0.00243 |
Grade A, and why
michel-packmind-engineer-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 4d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Packmind Engineer Review
Review an implemented issue against the checks that human Packmind engineers actually raise in
review — the judgment calls that pass CI but still get flagged by a reviewer. The full catalogue lives
in references/engineer-checklist.md; this file is the workflow that applies it.
This skill only detects issues — it does not fix them. Findings are evidence-grounded and humble: a static reviewer can be wrong, so findings that need runtime confirmation say so, and uncertain calls are posed as questions, exactly as the team does ("Should not we…? WDYT?").
Why this exists
Linters check style, the compiler checks types, e2e tests check the happy path. None of them notice that
a PinSpaceUseCase extends AbstractMemberUseCase instead of AbstractSpaceMemberUseCase, that a
SpacePinnedEvent is emitted but no Amplitude subscriber listens to it, that a non-admin can reach an
admin page by URL, that a list doesn't refresh after a delete, or that an error toast leaks a raw UUID.
Those are the things reviewers spend their attention on. This skill encodes that attention so it runs
every time, consistently, instead of depending on who happens to review.
1. Resolve the two inputs
The review needs the intent (what the issue asked for) and the implementation (what changed).
Intent — the issue
If given an issue number or URL, fetch it:
gh issue view <number> --json number,title,body,comments
Read the title, body, and existing comments. Extract: the user-facing goal, any explicit rules/scenarios, mentioned edge cases, and named code references (backtick terms, event names, file paths). If the issue references an Example Mapping spec or links a PRD, note it. If no issue is available, ask the user for one; do not invent intent — without it you can only judge code quality, not whether the right thing was built.
Ignore CodeRabbit / bot noise. Auto-generated @coderabbitai plan and "Issue enrichment" blocks are
not human intent — skip them.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 188 lines · 181 tokens per session scan A 7d37bcb5193d
michel-packmind-engineer-review is a skill published in the GitHub repository PackmindHub/packmind (309 stars, last pushed today), licensed Apache-2.0. It adds 181 tokens to every session and 2,432 once invoked, about $0.0009 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
clean-code-reviewer
Reviews code against Robert C. Martin's Clean Code principles. Use when users share code for review, ask for refactoring suggestions, or want to improve code quality. Produces actionable feedback organized by Clean Code principles with concrete before/after examples.
effective-java
Generate and review Java code using patterns and best practices from Joshua Bloch's "Effective Java" (3rd Edition). Use this skill whenever the user asks about Java best practices, API design, object creation patterns, generics, enums, lambdas, streams, concurrency, serialization, method design, exception handling, or…
effective-kotlin
Apply Effective Kotlin best practices (Marcin Moskała, 2nd Ed). Covers Safety (Items 1-10: mutability, scope, nulls, types, expectations, errors, resources, tests), Readability (Items 11-18: operators, receivers, properties, naming), Reusability (Items 19-25: DRY, generics, delegation, variance), Abstraction (Items…
effective-typescript
Review existing TypeScript code and write new TypeScript following the 62 items from "Effective TypeScript" by Dan Vanderkam. Use when writing TypeScript, reviewing TypeScript code, working with type design, avoiding any, managing type declarations, or migrating JavaScript to TypeScript. Trigger on: "TypeScript best…
verification
Verify agent code against organizational policies and best practices. Trigger this skill when the user says something like "verify my agent", "review agent code", "check compliance", "audit my agent", "check my agent against rules", or "validate agent implementation".
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.