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 skills add ChrisMckerracher/claude-dream-team --skill review-queuegit clone --depth 1 https://github.com/ChrisMckerracher/claude-dream-teamWrote 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/skills/chrismckerracher/claude-dream-team/review-queue)<a href="https://agentmods.dev/skills/chrismckerracher/claude-dream-team/review-queue"><img src="https://agentmods.dev/badge/skills/chrismckerracher/claude-dream-team/review-queue/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/skills/chrismckerracher/claude-dream-team/review-queue"><img src="https://agentmods.dev/badge/skills/chrismckerracher/claude-dream-team/review-queue.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 | $0.01669 |
| Opus 5 | $0.00025 | $0.00834 |
| Sonnet 5 | $0.00010 | $0.00334 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade A, and why
Review Queue Management 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 10d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Queue Management
The review queue orchestrates the handoff pipeline between Coding agents, Code Review agent, and QA agent using the dtq CLI tool.
dtq CLI Reference
dtq submit <task-id> --branch <branch> --worktree <path> --agent <name> # Submit for review
dtq claim <stage> --agent <name> # Claim next item (review|qa)
dtq approve <task-id> --agent <name> # Advance to next stage
dtq reject <task-id> --reason <text> --agent <name> # Send back for revision
dtq status [task-id] # Show queue or item detail
Agent identity is passed via the --agent flag. The queue directory is auto-detected from the git root (no DTQ_QUEUE_DIR env var needed).
Queue Flow (Distributed Peer-to-Peer)
Each task flows independently through the pipeline as soon as it's submitted. Tasks don't wait for batch processing — they progress coding → review → qa → merge-ready in parallel.
Coding Agent completes work
→ dtq submit <task-id> --branch <branch> --worktree <path> --agent coder-1
→ Sends ping via SendMessage to Code Review Agent
Code Review Agent (ping-reactive)
→ Receives ping from Coding Agent
→ dtq claim review --agent code-review (claims the submitted item)
→ Reviews code
→ On APPROVED:
dtq approve <task-id> --agent code-review (advances to qa)
Sends ping via SendMessage to QA Agent
→ On NEEDS_WORK:
dtq reject <task-id> --reason "..." --agent code-review (back to coding)
Sends feedback via SendMessage to Coding Agent
QA Agent (ping-reactive)
→ Receives ping from Code Review Agent
→ dtq claim qa --agent qa (claims the approved item)
→ Validates against specs or auto-approves if trivial
→ On PASSED:
dtq approve <task-id> --agent qa (advances to merge-ready)
Sends merge-ready ping via SendMessage to Team Lead
→ On FAILED:
dtq reject <task-id> --reason "..." --agent qa (back to coding)
Sends failure report via SendMessage to Coding Agent
Team Lead (merge coordinator)
→ Receives merge-ready pings from QA
→ Merges branch into epic branch
→ Confirms merge via SendMessage to Coding Agent
→ Coding Agent marks TaskList task as completed
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.
- 10d ago First seen · 181 lines · 50 tokens per session scan A 6b91b3429ed4
Review Queue Management is a skill published in the GitHub repository ChrisMckerracher/claude-dream-team (5 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 1,669 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.