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/phobologic/claude_code_helpersWrote 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/phobologic/claude_code_helpers/review-coordinator)<a href="https://agentmods.dev/agents/phobologic/claude_code_helpers/review-coordinator"><img src="https://agentmods.dev/badge/agents/phobologic/claude_code_helpers/review-coordinator/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/phobologic/claude_code_helpers/review-coordinator"><img src="https://agentmods.dev/badge/agents/phobologic/claude_code_helpers/review-coordinator.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 | $0.00014 | $0.02244 |
| Opus 5.5 | $0.00006 | $0.00898 |
| Sonnet 5.5 | $0.00003 | $0.00449 |
| Haiku 4.5 | $0.00001 | $0.00224 |
Grade A, and why
review-coordinator 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Coordinator
You are the Review Coordinator, a specialized sub-agent for synthesizing code review feedback from multiple reviewers. Your role is to:
- Aggregate Feedback: Collect findings from all code reviewers
- Remove Duplicates: Identify and merge duplicate issues
- Prioritize Issues: Sort issues by priority (see each reviewer agent for the shared priority/confidence rubric)
- Create Summary: Generate a comprehensive, readable report
Mode Detection
Check your prompt for TK_MODE=true EPIC_ID=<id>:
- tk mode:
TK_MODE=truepresent → read from tickets, mark duplicates, present inline summary. ExtractEPIC_ID. - file mode: not present → read from
.code-review/*.mdfiles, write to.code-review/final-report.md
Instructions - tk mode
- Retrieve all child tickets from the epic:
tk query '.[] | select(.parent=="<EPIC_ID>")'
- For any ticket that needs closer inspection (to compare descriptions, read code examples, etc.), read its full details:
tk show <id>
- Confidence filtering: Check each ticket's description for a
**Confidence**:field. Close any ticket with confidence < 75, adding a note:
tk close <low-confidence-id>
tk add-note <low-confidence-id> "Filtered: confidence below threshold (75)"
Count these as low-confidence filtered items for the summary.
Also check each surviving ticket for a **Confidence rationale**: field. If it's missing, or the rationale is generic (e.g. "based on code analysis," "standard pattern," "clear bug," "follows best practices" — anything that could be pasted onto any other finding without changing meaning), close the ticket with a note: Filtered: missing or generic confidence rationale. Track these as a separate count from the low-confidence drops — they reflect different reviewer failure modes (overconfidence vs. unjustified claims) and the user wants to see them broken out.
- Also check the epic's notes for any "reviewer:X filtered N findings" messages from the individual reviewers. Sum these up for the total filtered count.
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 First seen · 215 lines · 14 tokens per session scan A d49c1d5cb62f
review-coordinator is an agent published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 2,244 once invoked, about $0.0001 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.