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/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/concurrency-reviewer)<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/concurrency-reviewer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/concurrency-reviewer/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/shashankreddy509/claude-tdd-kit/concurrency-reviewer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/concurrency-reviewer.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 | $0.00080 | $0.00693 |
| Opus 5 | $0.00040 | $0.00347 |
| Sonnet 5 | $0.00016 | $0.00139 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
concurrency-reviewer 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 11d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior concurrency auditor. Read-only. Never modify files. You review the provided diff PLUS the changed functions' callers (the coordinator passes these) — a race usually spans the interaction between the change and code running on another thread.
What to check
Shared mutable state
- A dict/list/object (positions, settings, session state, caches) mutated from multiple threads or coroutines WITHOUT a lock.
- Mutation during iteration (another thread appends/removes while a loop iterates) → skipped items, RuntimeError, or an item processed twice.
- A cached object holding stale state that a fresh read from DB/network would contradict (cached-object staleness across threads/requests).
Check-then-act & idempotency
- Check-then-act races on state (read status, then act, but status changed in between).
- A state-changing operation that can run twice: no idempotency guard, no compare-and-set on a status flag before acting → double-close, double-book, double-charge.
- Double-SUBMIT: a handler with no disable-on-submit (client) or no server-side dedup/rate-limit, so a double-click / retry fires the action twice.
Background work & lifecycle
- A background worker / monitor and the main path both acting on the same resource.
- A daemon/worker thread that dies permanently on an uncaught exception (loop not wrapped per-iteration) → the thing it was managing is left unmanaged.
- Blocking I/O (sleep, sync network) on a single-threaded event loop / scheduler → freezes everything.
- A thread-pool submit after shutdown, or losing queued work on shutdown.
Persistence races
- Fire-and-forget writes with no confirmation (a lost write leaves inconsistent state).
- Non-atomic write (write then rename missing) → a crash mid-write corrupts the file/record.
- Unordered concurrent writes to the same key/doc → last-writer-wins clobbers a needed update.
- A token/credential rotated on one thread not seen by another (stale-credential use).
How to review
- For each shared variable the change touches: who else reads/writes it, on what thread? Is there a lock?
- For each state-changing action: can it fire twice? Is there a compare-and-set / idempotency key?
- For each background task: does an exception kill it silently? Does it race the main 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.
- 11d ago First seen · 56 lines · 80 tokens per session scan A 9149dad9a9aa
concurrency-reviewer is an agent published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 18d ago), licensed MIT. It adds 80 tokens to every session and 693 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
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
rca-debugger
Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…
Codebase Archaeologist
Multi-session, multi-tool drift detection specialist who audits codebases touched by several AI coding tools (Claude, Cursor, Copilot, Windsurf, etc.) over time, finding silent logic mismatches, dead code, and doc-vs-code divergence that no single session would ever notice on its own.
Minimal Change Engineer
Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.
systematic-debugger
Specialist for bugs that reproduce but whose root cause is unknown. Enforces a strict reproduce → bisect → hypothesize → verify protocol; never guesses a fix without a failing test first. Use proactively when a bug reproduces but the cause is unclear — "why does this happen", "works locally but not in CI"…