Borrowing it
Nothing to install: this file belongs to frostney/GocciaScript. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frostney/GocciaScript/main/.agents/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/frostney/GocciaScriptWrote 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/frostney/gocciascript/code-review)<a href="https://agentmods.dev/skills/frostney/gocciascript/code-review"><img src="https://agentmods.dev/badge/skills/frostney/gocciascript/code-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/frostney/gocciascript/code-review"><img src="https://agentmods.dev/badge/skills/frostney/gocciascript/code-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.03360 |
| Opus 5.5 | $0.00021 | $0.01344 |
| Sonnet 5.5 | $0.00010 | $0.00672 |
| Haiku 4.5 | $0.00005 | $0.00336 |
Grade A, and why
code-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 yesterday.
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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review
Establish whether the requested review scope is correct, necessary, clear, and ready for its claimed use. Without an explicit file or prior-findings input, review the complete change. Review first; remediate only in an authorized fix mode.
Operations, remediation, and boundaries
Choose one operation before gathering evidence:
- Fresh review: judge the bounded change and issue a review verdict.
- Targeted revalidation: recheck selected prior findings without judging the change as a whole.
- Combined: perform both only when the user explicitly requests a fresh review and supplies prior findings; keep their outputs and conclusions separate.
Remediation is independent of the operation:
- Default remediation is none. Inspect and run safe local probes, but do not edit source, tests, configuration, or documentation.
fix <finding IDs>fixes only the selected findings;fix-allfixes every validated in-scope finding in one bounded pass. With prior findings, either mode may edit only for selected findings classifiedstill_presentorchanged, never forresolved,not_retestable, orskippedOutOfScopefindings.- Fix modes authorize local edits and validation, not commits, pushes, PR comments, review-thread changes, deployments, publication, or shared-state mutation. Stop remediation for a material product, architecture, security, compatibility, or scope decision.
- A request to save JSON authorizes only the named findings artifact; it does not authorize remediation.
- Exact file lists and prior-findings JSON are additive inputs. They do not change unscoped review behavior unless the user supplies them.
- A reporting profile or threshold changes presentation only. Gather and validate the complete candidate set across the mapped scope, retain every supported severity in the canonical result, and let the caller decide which severities become visible.
- Search the complete mapped scope; do not stop after the first or highest-severity issue.
- Delegate review lanes by default when the host supports subagents and the
scope is not trivial. A small change, such as a few lines in one file, stays
local.
no-subagentsor an equivalent user instruction keeps the whole review local. When the review delegates lanes, read references/subagent-lanes.md before publishing the lane map. While lanes run, the coordinator continues its own lane-independent work, such as running the project gate.
What ships with it
9 files 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.
- references/adversarial-review.md 1.2 KB
- references/discoverability.md 799 B
- references/engineering-smells.md 1.2 KB
- references/file-scope.md 929 B
- references/findings-json.md 2.3 KB
- references/fix-mode.md 963 B
- references/prior-findings.md 3.5 KB
- references/revalidation-json.md 3.5 KB
- references/subagent-lanes.md 2.9 KB
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.
- yesterday Changed · +10 lines ee3c8141c956
- 22d ago Changed · +10 lines 1f34f52c913b
- 26d ago Changed · -5 lines · +23 tokens per session 22a6a8cba311
- 29d ago First seen · 279 lines · 29 tokens per session scan A a490ff351652
code-review is a skill published in the GitHub repository frostney/GocciaScript (20 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 3,360 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
git-step-commit
Analyze Git changes, split them into coherent commits, infer message language and format, optionally close supplied GitHub issues, and execute safely. Manage persistent global or repository preferences for review versus direct submission and automatic or specified commit-message language through native Git config.…
file-line-audit
Audit oversized source files in a repository. Apply repository .gitignore rules plus extra exclude patterns, filter candidate files with include glob patterns, count physical lines, and output only files at or above the threshold. Use this skill when the user asks to find long files, review file-length distribution…
triage-contributor-pr
Triage open pull requests from external contributors to prisma/orm and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
review-triage-phase
Produces canonical review actions from fetched review state and renders action markdown. Use when the user wants only triage/action-planning for the review-framework workflow.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.