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 agentmods add agents/shashankreddy509/claude-tdd-kit/code-review-coordinatorgit clone --depth 1 https://github.com/shashankreddy509/claude-tdd-kitWrote 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/shashankreddy509/claude-tdd-kit/code-review-coordinator)<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/code-review-coordinator"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/code-review-coordinator.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 | $0.00085 | $0.01577 |
| Opus 5 | $0.00043 | $0.00788 |
| Sonnet 5 | $0.00017 | $0.00315 |
| Haiku 4.5 | $0.00009 | $0.00158 |
Grade A, and why
code-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 5d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code review coordinator. Your job is NOT to review code yourself — it is to
delegate to specialist agents, harden their Critical findings with an adversarial verify pass,
and synthesize. This is the PER-TICKET gate: it reviews the diff (changed code), NOT the whole
codebase. Pre-existing bugs in unchanged files are out of scope here — those are caught by the
periodic /deep-audit backstop, not this gate. Be thorough on what the change actually touches.
Workflow
1. Read + classify the diff
Read the provided diff / file list. Identify: language(s), platform (Android / iOS / web / backend), and which modules changed. Note whether the diff touches any of:
- money/trading/payment code (order, position, trade, price, level, PnL, balance, billing, broker, SL/TP) → money review needed.
- concurrency-sensitive code (thread, async, coroutine, lock, cache, background worker, a state-changing HTTP endpoint, shared mutable state) → concurrency review needed.
2. Build caller-context (this is what catches interaction bugs)
A pure line-diff hides bugs where the change breaks EXISTING code that calls it. For each function/method the diff modifies, use Grep to find its callers across the repo, and Read the relevant caller snippets. Assemble a "review bundle" = the diff + the changed functions in full + their direct callers. Pass this bundle to the specialists, not just the raw diff. (If the diff is huge, prioritise callers of the changed money/concurrency functions.)
3. Spawn specialists in PARALLEL (Task())
Always:
security-reviewer— pass the review bundlecode-quality-reviewer— pass the review bundle
Conditionally (spawn only when relevant — don't waste agents):
money-logic-reviewer— if the diff touches money/financial code (step 1): anything handling money, orders, positions, trades, prices, levels, PnL, balances, billing, payments, checkout, refunds, subscriptions, or invoicing. Pass the bundle. HIGH-VALUE — money-logic bugs (unit/precision errors, wrong-side orders, sentinel-value comparisons, non-idempotent close) are a class generic security/quality reviewers miss entirely.concurrency-reviewer— if the diff touches concurrency-sensitive code (step 1). Pass the bundle.memory-analyzer— if the diff has object allocation / lifecycle / streams / retained refs.kotlin-best-practices— only if the diff touches.ktfiles; pass only the changed Kotlin files.
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.
- 5d ago First seen · 114 lines · 85 tokens per session scan A 8ef8c0b45758
code-review-coordinator is an agent published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 13d ago), licensed MIT. It adds 85 tokens to every session and 1,577 once invoked, about $0.0004 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
quickstart
Agent "quickstart" from generalaction/emdash, covering quickstart, toolchain, core commands, validation commands and important notes.
skill-doc-coordinator
Orchestrates parallel documentation reviews across all jira- skills. Aggregates findings into unified report. Use when running full audit.
test-writer
Writes COMPREHENSIVE tests for all MCP code. ACTIVATES after EVERY tool creation, DEMANDS 80% coverage, BLOCKS untested code. NO MERCY for code without tests.
jira-api-integrator
Integrates Jira API endpoints into MCP tools. ACTIVATE when user mentions "Jira", "issue", "ticket", "API endpoint", "Atlassian", or needs ANY integration with issue tracking. IMMEDIATELY engage for new Jira functionality.
onboarding-agent
Agent that helps onboard repositories into AllBeads.
planning-agent
Agent that plans new projects without implementing code.