agentmods.dev

cf-review

cf-review is a skill for Claude Code from dinhanhthi/coding-friend. It costs 137 tokens per session (6,819 once invoked), scanned C, original, MIT.

A code-review workflow that sends selected changes to a separate agent for inspection.

In plain words
What is it for?
Use it to review uncommitted changes, files, commits, branches, or a described area of code, with quick and deep modes.
Why use it?
It provides a dedicated check for problems before changes are merged.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions Codex.

not rated 4repo changed today C scan 137 tokens original MIT

Good fit Use it to review uncommitted changes, files, commits, branches, or a described area of code, with quick and deep modes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dinhanhthi/coding-friend/cf-review
View source ↗ dinhanhthi/coding-friend cf.dinhanhthi.com
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 dinhanhthi/coding-friend --skill cf-review
Clone the repo
git clone --depth 1 https://github.com/dinhanhthi/coding-friend

Made for: Claude Code.

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.

agentmods badge for cf-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-review/github.svg)](https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-review)
Your own site
<a href="https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-review"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-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.

agentmods 80×15 button for cf-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-review"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,819 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00137 $0.06819
Opus 5.5 $0.00055 $0.02728
Sonnet 5.5 $0.00027 $0.01364
Haiku 4.5 $0.00014 $0.00682

Measured today against content hash 53052a24de0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

cf-review scanned grade C with 1 finding 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 today.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/assess-changes.sh, scripts/gather-diff.sh, scripts/mark-reviewed.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

- Set only by config with a commit range target or `--out` → do not refuse: set `fix=false`, `commit=false`, print `> ℹ️ review.fix/review.commit ignored (commit range or --out).` and continue.
plugin-antigravity/skills/cf-review/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cf-review

✨ CODING FRIEND → /cf-review activated

Review the code changes for: $ARGUMENTS

Auto-Triggered

Invoked by /cf-plan (after all tasks), /cf-fix (after verified fix), and /cf-optimize (after measured + verified).

Workflow

Step 0: Custom Guide

bash "<plugin-root>/lib/load-custom-guide.sh" cf-review

If the block above printed anything, apply only the ## Before, ## Rules, and ## After sections; if it shows the raw command instead of output, re-run that exact load-custom-guide.sh fence now.

Step 1: Identify the target

  • Empty $ARGUMENTS → all uncommitted changes (net HEAD → working tree; staged hunks counted once, not twice)
  • File path → that file
  • Commit range (e.g. HEAD~3..HEAD) → those commits
  • Natural-language description (e.g. "the auth logic changes") → default uncommitted set, focus findings on that area
  • --deep / --quick → force that mode (override auto-detection)

Fix/commit flags:

  • --fix → fix=true; --commit → commit=true, and --commit implies --fix. --no-fix → fix=false, commit=false; --no-commit → commit=false. Strip all four from $ARGUMENTS; a --no-* flag wins over its positive flag and over config.
  • No flag decides a value → read review.fix / review.commit from merged config (~/.coding-friend/config.json + CF_CONFIG_FILE, default .coding-friend/config.json; local field overrides global); review.commit: true implies fix=true unless --no-commit was passed (then fix comes from review.fix alone). Absent or non-boolean → false. /cf-plan and /cf-tdd autopilot pass --no-fix because they own their fix loop; /cf-commit passes --no-fix because it owns the change set.
  • Explicit --fix/--commit with a commit range target → refuse: print > ⚠️ --fix/--commit need working-tree changes; not allowed with a commit range. and stop.
  • Explicit --fix/--commit with --out → refuse (exclusive): print > ⚠️ --fix/--commit are exclusive with --out; not allowed together. and stop.
  • Set only by config with a commit range target or --out → do not refuse: set fix=false, commit=false, print > ℹ️ review.fix/review.commit ignored (commit range or --out). and continue.
  • Set → print > 🔧 --fix — will apply Critical/Important findings after review (no confirmation). (append and commit when clean when commit=true; append (from config) when config set it).

Read the full file on GitHub · 260 lines

Files

What ships with it

7 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.

  1. today Changed · +16 lines 53052a24de0e
  2. 8d ago Changed bce7ce7d82f4
  3. 19d ago Changed · +2 lines · +8 tokens per session scan A → C ac44138303cb
  4. 1mo ago Changed · +9 lines d3fadbb2067e
  5. 1mo ago Changed · +1 lines 97f60fc81554
  6. 1mo ago Changed · +19 lines · +13 tokens per session 8094ab91ac2e
  7. 1mo ago Changed · +82 lines c65eed830d5f
  8. 1mo ago Changed · -1 lines 2dab35290f6b
  9. 1mo ago Changed · -12 lines · +57 tokens per session c32f02cea412
  10. 2mo ago First seen · 144 lines · 59 tokens per session scan A 044333a637d1

Subscribe to this mod's changes

cf-review is a skill published in the GitHub repository dinhanhthi/coding-friend (4 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 6,819 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeCode reviewagentclaudeclimcpskills
Related

cf-review compared with skills from other repositories

cf-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cf-reviewdinhanhthi/coding-friendSkill4todayMITC137Claude Code
doris-repo-reviewapache/doris-skillsSkill492d agoApache-2.0A180Claude Code, Codex
develop-with-evidenceapache/doris-skillsSkill492d agoApache-2.0A147Codex
doris-pr-descriptionapache/doris-skillsSkill492d agoApache-2.0A196Claude Code, Codex
oxlintdelexw/claude-code-miscSkill27mo agoMITA111Claude Code, Codex
cn-checkcontinuedev/continueSkill36kyesterdayApache-2.0A49Claude Code, Codex
officecli-pitch-deckiOfficeAI/OfficeCLISkill33k7d agoApache-2.0A163Claude Code, Codex