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 dinhanhthi/coding-friend --skill cf-review-customgit clone --depth 1 https://github.com/dinhanhthi/coding-friendWrote 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/dinhanhthi/coding-friend/cf-review-custom)<a href="https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-review-custom"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-review-custom/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/dinhanhthi/coding-friend/cf-review-custom"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-review-custom.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 | $0.00000 | $0.00538 |
| Opus 5.5 | $0.00000 | $0.00215 |
| Sonnet 5.5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
cf-review-custom 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
After
After the standard review completes, check if any changed files require documentation updates.
Step A1: Identify implementation changes that need doc sync
From the files already reviewed in this session, filter for changes in these source directories:
| Source path pattern | Documentation target |
|---|---|
plugin/skills/{name}/SKILL.md |
website/src/content/docs/skills/{name}.mdx |
plugin/agents/{name}.md |
website/src/content/docs/reference/agents.mdx |
cli/src/commands/{name}.ts |
website/src/content/docs/cli/cf-{name}.mdx |
Only consider files that were actually changed in this conversation's diff — do NOT scan the entire codebase.
If no implementation files match the patterns above, skip the remaining steps and end with: "No doc-sync needed."
Step A2: Compare changes against documentation
For each matched implementation file:
- Read the implementation file to understand what changed (use the diff from the review, not the entire file)
- Read the corresponding documentation file
- Check whether the documentation already reflects the changes — look for:
- New or renamed workflow steps, flags, arguments
- Changed behavior, conditions, or modes
- Added or removed features, options, or commands
- Updated agent metadata (model, tools, description)
Step A3: Report doc-sync findings
Append a Doc Sync section to the review report:
### 📄 Doc Sync
| Source | Doc | Status |
|---|---|---|
| `plugin/skills/cf-ask/SKILL.md` | `website/.../skills/cf-ask.mdx` | Out of date — missing new `--verbose` flag |
| `plugin/agents/cf-explorer.md` | `website/.../reference/agents.mdx` | Up to date |
**Action needed:** <list specific updates required, or "None — all docs are in sync">
If updates are needed, ask the user whether to apply them now or leave as a reminder.
Rules
- Only check documentation for files that were changed in the current conversation — never do a full-repo audit.
- Do not rewrite entire doc files. Only update the specific sections that drifted from the implementation.
- Preserve the existing documentation style, frontmatter, and structure when making updates.
- If a documentation file does not exist for a new implementation file, flag it as "Missing doc" rather than creating one automatically.
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.
- 2mo ago First seen · 54 lines · 0 tokens per session scan A e407bc11876e
cf-review-custom is a skill published in the GitHub repository dinhanhthi/coding-friend (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 538 tokens. 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 2026-08-31.
cf-review-custom compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cf-review-customdinhanhthi/coding-friend | Skill | 4 | today | MIT | A | 0 | Claude Code, Codex |
| doris-repo-reviewapache/doris-skills | Skill | 49 | 2d ago | Apache-2.0 | A | 180 | Claude Code, Codex |
| develop-with-evidenceapache/doris-skills | Skill | 49 | 2d ago | Apache-2.0 | A | 147 | Codex |
| doris-pr-descriptionapache/doris-skills | Skill | 49 | 2d ago | Apache-2.0 | A | 196 | Claude Code, Codex |
| oxlintdelexw/claude-code-misc | Skill | 2 | 7mo ago | MIT | A | 111 | Claude Code, Codex |
| cn-checkcontinuedev/continue | Skill | 36k | yesterday | Apache-2.0 | A | 49 | Claude Code, Codex |
| officecli-pitch-deckiOfficeAI/OfficeCLI | Skill | 33k | 7d ago | Apache-2.0 | A | 163 | Claude Code, Codex |