Borrowing it
Nothing to install: this file belongs to uber/submitqueue. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/uber/submitqueue/main/.agents/skills/autoreview/SKILL.mdgit clone --depth 1 https://github.com/uber/submitqueueWrote 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/uber/submitqueue/autoreview)<a href="https://agentmods.dev/skills/uber/submitqueue/autoreview"><img src="https://agentmods.dev/badge/skills/uber/submitqueue/autoreview/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/uber/submitqueue/autoreview"><img src="https://agentmods.dev/badge/skills/uber/submitqueue/autoreview.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 | $0.00047 | $0.00517 |
| Opus 5.5 | $0.00019 | $0.00207 |
| Sonnet 5.5 | $0.00009 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
autoreview 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 21d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoreview dispatcher
The review runs in subagents. Subagents cannot start subagents of their own, so this parent context coordinates three phases and relays their outputs verbatim. It never reads the diff, runs checks, opens changed files, or writes findings itself.
Every subagent is a general-purpose subagent on the inherited model, run in the foreground. Give each one only what its prompt below names: nothing from the conversation that wrote the change.
1. Plan
Launch one planner:
You are the autoreview planner.
Repository: <absolute repository path>
Target: <the target exactly as the user named it, or `current branch changes including uncommitted work`>
Request: <user's review instruction>
Read `<repository>/.agents/skills/autoreview/review.md` and execute its "Plan" section only. Return only the plan block it specifies.
2. Lenses
For every assignment in the plan, launch one lens reviewer. Launch them all in one message so they run in parallel:
You are an autoreview lens reviewer.
Plan header:
<the plan's header lines, verbatim>
Assignment:
<one assignment block, verbatim>
Read `<repository>/.agents/skills/autoreview/review.md` and execute its "Lens" section for this assignment only. Return only the lens result it specifies.
3. Consolidate
Launch one consolidator:
You are the autoreview consolidator.
Plan:
<the whole plan, verbatim>
Lens results:
<every lens result, verbatim, each under its assignment id>
Read `<repository>/.agents/skills/autoreview/review.md` and execute its "Consolidate" and "Report" sections. Return only the final report.
Return the consolidator's report unchanged. Do not weaken, expand, or reinterpret its findings.
If a subagent cannot be launched or fails, do not review in the parent context and do not drop its part silently. Pass the failure to the consolidator as that assignment's result, so it lands under Not reviewed. If the planner or consolidator fails, report the review as incomplete and name the phase.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 21d ago Changed · +28 lines 3fe4cc1c949b
- 29d ago Changed · -97 lines c35ab55b1738
- 1mo ago First seen · 133 lines · 47 tokens per session scan A 9fb1fe066e55
autoreview is a skill published in the GitHub repository uber/submitqueue (242 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 517 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 2026-09-29.
Other skills, from other repositories
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
code-review
You are a senior code reviewer. You receive diffs via stdin.
ring:verifying-code
Verifying a Go project: runs every quality check (lint, vet, imports, format, docs, unit, integration, E2E) and returns a single MERGEREADY or NEEDSFIX verdict. Report-only: never fixes anything. Use for a quick pre-merge or pre-PR check outside a full dev-cycle. Skip when not a Go project, when you want a single…
pixiv-cli-pr
Prepare, update, or verify a pixiv-cli pull request using its current template, trusted verification policy, reviewed diff, and head-specific check results. Use for contributor handoff or PR readiness; merging, live /test execution, and releases are separate actions.
ci-orchestrator
Run a CI-like pipeline locally (format, lint, vet, static-analysis, tests) and summarize per-step results with remediation guidance.
go-concurrency-safety
L1 supplement - audits Go-specific concurrency hazards in node client code: map iteration non-determinism, goroutine leaks, mutex ordering, panic boundaries, context cancellation.