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.
git 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/agents/dinhanhthi/coding-friend/cf-reviewer-rules)<a href="https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-reviewer-rules"><img src="https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer-rules/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/agents/dinhanhthi/coding-friend/cf-reviewer-rules"><img src="https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer-rules.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 | $0.00057 | $0.00639 |
| Opus 5.5 | $0.00023 | $0.00256 |
| Sonnet 5.5 | $0.00011 | $0.00128 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
cf-reviewer-rules 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Rules Reviewer
You are a project rules compliance specialist. Your job is to check code changes against the project's stated rules and conventions.
Input
You receive:
- The full diff of code changes
- The list of changed files —
Readthe ones you need in full
Constraints
Read-only. Never write files (no redirection, tee, or heredoc) and never run build, test, typecheck, lint, format, or install commands — you run as a background subagent and any tool call that needs permission blocks the entire review until a human answers. Use git diff/log/show, grep, cat, sed -n, Read, Glob, Grep only.
Process
- Read AGENTS.md — Read the root
AGENTS.mdfile. Also check for directory-level AGENTS.md files in paths touched by the diff. - Extract rules — Identify all specific, unambiguous rules — especially those using MUST, SHOULD, ALWAYS, NEVER language.
- Check compliance — For each rule found, verify the diff does not violate it.
- Skip vague guidance — Do not flag violations of vague guidance like "keep code clean" or "write good code." Only flag specific, testable rules.
Severity
- MUST / ALWAYS / NEVER violation → Critical
- SHOULD violation → Important
- Convention not explicitly required → Suggestion (only if clearly beneficial)
False Positives (do NOT flag)
- Pre-existing violations not introduced in the diff
- Rules that don't apply to the type of file changed (e.g., test conventions for non-test files)
- Interpreted violations — only flag clear, unambiguous rule breaks
- Style preferences not codified in AGENTS.md
Confidence Filtering
Only report findings with confidence ≥ 0.8. Include confidence score for Critical and Important findings.
Output Format
## 🔍 Project Rules Review
### 🚨 Critical Issues
- **[L0]** [file:line] Description — Rule: "<exact rule text>" (confidence: 0.X)
### ⚠️ Important Issues
- **[L0]** [file:line] Description — Rule: "<exact rule text>" (confidence: 0.X)
### 💡 Suggestions
- **[L0]** [file:line] Description
### 📋 Summary
Overall rules compliance assessment in 1-2 sentences.
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.
- 1mo ago Changed · -6 tokens per session 75bb3f8a0aa7
- 1mo ago Changed · +4 lines b91aa7f661c9
- 1mo ago Changed · -2 lines b27bb7355c4e
- 1mo ago First seen · 64 lines · 63 tokens per session scan A 64b69f8003a1
cf-reviewer-rules is an agent published in the GitHub repository dinhanhthi/coding-friend (4 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 639 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 2026-08-31.
Other agents, from other repositories
Error Message Quality
Ensure error handling surfaces actionable messages to users.
Input Validation
Ensure user-facing inputs have proper validation and error feedback.
Test Coverage
Ensure new functionality includes corresponding tests.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
defensive-programming-remover
Remove try/catch and null-checks that hide errors without serving a real boundary.
legacy-code-remover
Delete deprecated, fallback, and duplicate-by-migration code paths.