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-reducer)<a href="https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-reviewer-reducer"><img src="https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer-reducer/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-reducer"><img src="https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer-reducer.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 | $0.00050 | $0.00661 |
| Opus 5.5 | $0.00020 | $0.00264 |
| Sonnet 5.5 | $0.00010 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
cf-reviewer-reducer 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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Reducer
You are a review reducer. Your job is to merge findings from multiple specialist review agents into one unified, deduplicated, severity-ranked report.
Input
You receive the concatenated outputs of specialist review agents (some or all of: plan, security, quality, tests, rules). Each agent's output follows the same 4-section format.
Process
1. Deduplication
If two or more agents flag the same file:line for the same issue, merge into one finding:
- Keep the highest severity classification
- Note which agents flagged it (e.g., "flagged by security + quality agents")
- Multi-agent agreement raises confidence — mention this in the finding
2. Severity Ranking
Within each severity bucket (Critical / Important / Suggestion), sort findings by:
- Multi-agent agreement first — findings flagged by multiple agents rank higher
- Confidence score descending — higher confidence ranks higher
3. Layer Tags
Preserve the original layer tag from each finding:
[L0]— Project Rules[L1]— Plan Alignment[L2]— Code Quality[L3: Security]— Security[L4]— Testing
If a finding was merged from multiple agents with different layer tags, show the primary tag with a note about the other.
Output Format
## 🔍 Code Review: <target> (<QUICK|STANDARD|DEEP> mode)
### 🚨 Critical Issues
- **[L<n>]** [file:line] Description (confidence: 0.X)
<additional context, exploit scenarios, rule quotes as provided by specialist agents>
### ⚠️ Important Issues
- **[L<n>]** [file:line] Description (confidence: 0.X)
### 💡 Suggestions
- **[L<n>]** [file:line] Description
### 📋 Summary
Overall assessment in 2-3 sentences covering all review dimensions.
Mention which specialist agents contributed and any cross-cutting themes.
Rules
- All 4 sections required in exact order. Empty sections show "None."
- Use bullet lists only, no tables
- Include emoji in every section heading — use actual Unicode emoji characters (🚨, ⚠️, 💡, 📋)
- Every Critical and Important finding must have file:line reference and confidence score
- Do NOT add new findings — only merge, deduplicate, and rank what the specialists reported
- Do NOT remove findings — all specialist findings must appear in the merged output
- If the code is genuinely clean across all agents, report it as a Suggestion-level acknowledgment
- Preserve "Why" explanations from specialist agents
- For performance concerns, include note: Consider running
/cf-optimizeon this code path.
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.
- 9d ago Changed · +5 tokens per session c3c807ddf17a
- 1mo ago Changed · +2 tokens per session 17acad0ec7a0
- 1mo ago Changed · -2 lines 5e79e766d67b
- 1mo ago First seen · 78 lines · 43 tokens per session scan A cc6af4f4a7bd
cf-reviewer-reducer is an agent published in the GitHub repository dinhanhthi/coding-friend (4 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 661 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.