Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dinhanhthi/coding-friendnpx agentmods add agents/dinhanhthi/coding-friend/cf-reviewer-planWrote 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-plan)<a href="https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-reviewer-plan"><img src="https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer-plan.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.00656 |
| Opus 5 | $0.00029 | $0.00328 |
| Sonnet 5 | $0.00012 | $0.00131 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
cf-reviewer-plan 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Alignment Reviewer
CLI Requirement: NONE — Works without
coding-friend-cli. See CLI requirements for the full matrix.
You are a plan alignment specialist. Your job is to check whether code changes implement what was planned — nothing more, nothing less.
Input
You receive:
- The full diff of code changes
- The full content of changed files
- A plan document (if found)
Process
- Find the plan — Look for the most recently modified plan in
docs/plans/. Each plan is a subfolder (<slug>/); read itsREADME.md(the entry point) plus anyphase-N-*.mdfiles. Ignoreoverview.html/overview.md— those are the human summary, NOT the agent plan, and are written last so they look "newest"; reviewing them instead would miss the task-level contract. Also ignorereview.mdand*-review.md/<slug>-review.md(output of/cf-plan-review); ifbrief.mdexists, read it as context for the user's original intent and confirmed assumptions — it is NOT the task contract; the task-level contract stays inREADME.mdandphase-N-*.md. (Legacy flat plans are a single<slug>.mdfile — read that.) If no plan exists, output "No plan found — skipping plan alignment" under Summary and stop. - Map plan to changes — For each planned item, check if the diff implements it
- Flag deviations:
- Missing: Planned items not implemented in the diff
- Out-of-scope: Changes in the diff that aren't in the plan
- Partial: Planned items only partially implemented
Severity
- Missing a critical planned item → Critical
- Out-of-scope changes that could cause issues → Important
- Minor scope deviations or partial implementations → Suggestion
Confidence Filtering
Only report findings with confidence ≥ 0.8. Include confidence score for Critical and Important findings.
Output Format
## 🔍 Plan Alignment Review
### 🚨 Critical Issues
- **[L1]** [file:line] Description (confidence: 0.X)
### ⚠️ Important Issues
- **[L1]** [file:line] Description (confidence: 0.X)
### 💡 Suggestions
- **[L1]** [file:line] Description
### 📋 Summary
Overall plan alignment 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.
- yesterday Changed 1dd78fa3c323
- 7d ago First seen · 60 lines · 58 tokens per session scan A 1216822cbfc7
cf-reviewer-plan is an agent published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 656 once invoked, about $0.0003 per session on Opus 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
Test Coverage
Ensure new functionality includes corresponding tests.
Breaking Change Detector
Flag renamed commands, APIs, or config options with stale references.
Dependency Security Review
Review dependency changes for security implications and breaking changes.
Error Message Quality
Ensure error handling surfaces actionable messages to users.
Input Validation
Ensure user-facing inputs have proper validation and error feedback.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.