What is fpg-code-review?

A code-review guide that checks changes against the repository's coding standards and other applicable rules, as well as for defects. It can review a pull request, branch, commit, file, or working changes.

Use it to review code and report findings in the conversation. It can also create or update a standards document when explicitly asked, but it does not implement fixes.

It helps find rule violations, bugs, security or performance problems, and missing tests before changes are accepted. It also helps establish review standards when a repository does not have them.

fpg-code-review — Skill for Codex by felipepg22/FPGSkills

Install

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.

Any agent

npx skills add felipepg22/FPGSkills --skill fpg-code-review

Clone the repo

git clone --depth 1 https://github.com/felipepg22/FPGSkills

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/felipepg22/fpgskills/fpg-code-review/github.svg)](https://agentmods.dev/skills/felipepg22/fpgskills/fpg-code-review)

Your own site

<a href="https://agentmods.dev/skills/felipepg22/fpgskills/fpg-code-review"><img src="https://agentmods.dev/badge/skills/felipepg22/fpgskills/fpg-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/felipepg22/fpgskills/fpg-code-review"><img src="https://agentmods.dev/badge/skills/felipepg22/fpgskills/fpg-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,109 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00068	$0.02109
Opus 5.5	$0.00027	$0.00844
Sonnet 5.5	$0.00014	$0.00422
Haiku 4.5	$0.00007	$0.00211

Measured 8d ago against content hash dd395112997a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fpg-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 8d 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.

skills/fpg-code-review/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fpg Code Review

Discover the rules that actually apply before reviewing. Check standards compliance alongside correctness, security, performance, and test coverage. Report in the conversation by default; edit code or post comments externally only when requested. Standards-file creation and explicitly requested updates follow the document workflow below.

1. Establish the review target

Honor the user's target and exclusions. A directory supplied to locate the repository, as in “review my code in this repo,” identifies the workspace; it does not request a repository-wide review. Inspect repository state and applicable agent instructions. Resolve the baseline and record the files or diff being reviewed before creating or updating any standards document, so that document does not accidentally expand the review.

No target supplied: review staged and unstaged changes relative to HEAD, including relevant untracked source and test files. Inspect the index as well when staged and unstaged edits overlap. In an unborn repository, review the staged and working files as new files. If there are no changes, ask for the target rather than choosing a recent commit or the whole repository.
PR or branch: use its actual base and head, comparing the merge-base to the head unless the user specifies another comparison. Obtain the PR's base from available repository or PR tools; ask if it cannot be established. Keep unrelated local changes outside this target.
Commit or range: preserve the requested range; for a single commit, compare with its parent, or the empty tree for a root commit. Clarify an ambiguous merge-parent choice.
Files or repository: review the requested current contents, including relevant surrounding code. In a non-Git directory, file and repository reviews remain supported; ask for a target if none was supplied.

Use available local tools or a connected PR service; the workflow requires no particular connector or other skill. If a target or baseline is inaccessible, report what is missing instead of substituting another target.

Read the full file on GitHub · 87 lines

Files

What ships with it

3 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.

Changes

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.

8d ago First seen · 87 lines · 68 tokens per session scan A dd395112997a

Subscribe to this mod's changes

fpg-code-review is a skill published in the GitHub repository felipepg22/FPGSkills (11 stars, last pushed 8d ago), licensed MIT. It adds 68 tokens to every session and 2,109 once invoked, about $0.0003 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 2026-10-30.

Code review

fpg-code-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fpg-code-reviewfelipepg22/FPGSkills	Skill	11	8d ago	MIT	A	68	Codex
autoreviewopenclaw/clawhub	Skill	9.5k	yesterday	MIT	A	17	Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills	Skill	2.2k	6d ago	MIT	A	115	Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermes	Skill	5.2k	yesterday	MIT	A	48	Claude Code, Codex
revdiff-planumputun/revdiff	Skill	945	yesterday	MIT	A	84	Claude Code
explore-unknownsdzhng/skills	Skill	1.4k	2d ago	MIT	A	162	Claude Code, Codex
re0-mergeLilMGenius/paperthin	Skill	1.4k	4d ago	MIT	A	70	Claude Code