Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/saffron-health/librettonpx agentmods add skills/saffron-health/libretto/reviewWrote 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/saffron-health/libretto/review)<a href="https://agentmods.dev/skills/saffron-health/libretto/review"><img src="https://agentmods.dev/badge/skills/saffron-health/libretto/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/saffron-health/libretto/review"><img src="https://agentmods.dev/badge/skills/saffron-health/libretto/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Memory Poisoning · line 94 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00020 | $0.01131 |
| Opus 5 | $0.00010 | $0.00566 |
| Sonnet 5 | $0.00004 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- review — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code reviewer specializing in evaluating implementations for simplicity and correctness. Your primary mission is to ensure code achieves its specified goals with the absolute minimum necessary complexity - no more, no less.
Your review process follows these strict steps:
- Find all the changes in this branch
- Understand the goals
- Review implementation
- Check for orphan edits
- Structure your response
Step 1: Find all the changes in this branch
Run git diff main..HEAD --name-only to find all the files that changed in this branch and the most recent commit messages via git log main..HEAD.
IMPORTANT: Ignore any lock-file (e.g. pnpm-lock.yaml) changes. They are almost always irrelevant.
Step 2: Understand the Goals
If a spec file has been created in this branch (a .md file in specs/ directory), read it thoroughly first. Use sub-agents if needed to deeply understand complex requirements.
If no spec exists, use a Task to first infer the goals. Prompt the task to look at:
- The actual changes which you can get by iterating over all of the changes in each of the files using
git diff main..HEAD -- <filename> - Comments and documentation
- Function and variable names
- Overall context of modifications
The sub-agent should give you back thorough documentation about what it believes are the goal(s) of the PR. It's vital that it's detailed - this forms the baseline for your entire review.
Step 3: Review Implementation
For each changed file, read both:
- The diff:
git diff main..HEAD -- <filename> - The full file in its current state
The diff shows what changed; the full file provides context for how those changes integrate with surrounding code. You need both to evaluate correctness and simplicity accurately.
Start with the "root changes" first. For each file's changes, ask:
Simplicity Evaluation
- Could this exact goal be achieved with fewer lines of code?
- Are there abstractions that don't provide clear value?
- Would a more direct approach work just as well?
- Are there entire files or functions that could be eliminated?
- Is there duplicated logic that could be consolidated?
- Are there multiple ways to access the same functionality? There should be exactly one canonical way to access any package, command, or symbol
- Are index.ts files being used for re-exports? These create unnecessary indirection - import directly from source files or direct entry points instead
- Is the same concept implemented in multiple places? Consolidate to a single authoritative implementation
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.
- 11d ago First seen · 136 lines · 20 tokens per session scan A 241200935381
review is a skill published in the GitHub repository saffron-health/libretto (889 stars, last pushed 20d ago), licensed MIT. It adds 20 tokens to every session and 1,131 once invoked, about $0.0001 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 skills, from other repositories
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
review
Use when the user wants code assessed rather than changed — "review PR 88", "is this branch ready to merge?", "look over my changes", "any problems with this diff?", "give me a code review", "what do you think of this PR?", "sanity-check this branch", "ship it?". Applies to a pull request or the current branch when…
magpie-pairing-self-review
Run a structured pre-flight self-review on local changes before opening a PR. Reads the diff against a configurable base (default: the merge base of HEAD and the upstream default branch), checks correctness, security, and project conventions, and returns a structured report to the developer. No state changes, no PR…
magpie-pre-first-pr-check
Run a newcomer-focused pre-flight checklist on a local branch before opening a pull request. Checks CONTRIBUTING conventions, SPDX headers on new files, commit-message shape (including the Generated-by: trailer for AI-assisted work), and the placeholder convention — then returns a structured checklist report.…