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 sdewell/code-quorum --skill q-reviewgit clone --depth 1 https://github.com/sdewell/code-quorumWrote 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/sdewell/code-quorum/q-review)<a href="https://agentmods.dev/skills/sdewell/code-quorum/q-review"><img src="https://agentmods.dev/badge/skills/sdewell/code-quorum/q-review/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/sdewell/code-quorum/q-review"><img src="https://agentmods.dev/badge/skills/sdewell/code-quorum/q-review.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 | $0.00084 | $0.03355 |
| Opus 5.5 | $0.00034 | $0.01342 |
| Sonnet 5.5 | $0.00017 | $0.00671 |
| Haiku 4.5 | $0.00008 | $0.00335 |
Grade A, and why
q-review 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 8d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Q-Review — multi-round code review
Completion gate
For every council start, q_await is the blocking completion notification. After completing the host's independent work, call it in the same turn as the start. Do not end the turn, tell the user you will check later, or leave a live job_id pending. If the council is still running, remain in the blocking call until it returns a result or error.
Arguments
$ARGUMENTS is the target spec — what to review — optionally with flags. If
empty, it defaults to all work on this branch versus main (committed and
uncommitted). Recognized target forms:
- (empty) — the whole branch vs
main: merge-base → working tree, including uncommitted tracked changes. working— uncommitted tracked changes only.pr:123or a PR URL — an open PR; its title/body/labels orient the review extent.A..B/A...B— an explicit commit range (two-dot literal / three-dot merge-base, PR-like).all— the whole codebase; agents read the repo atcwd. Pair this with--scope.
For pr:N and range targets, run from a checkout that has the reviewed head
checked out (a worktree on the PR branch) so file reads and the diff agree.
When cwd's HEAD is not the reviewed head, the diff is prefixed with a
working-tree notice telling seats to judge additions from the diff, not the
tree; without it, seats reading a main checkout report the PR's own
additions as missing.
If the user supplied a --scope <path>, capture it for Step 1. When reviewing all with no scope doc, tell the user a scope doc is strongly recommended and point them at skills/q-review/references/scope-template.md (copy it into the repo as code-quorum-review-scope.md and pass --scope code-quorum-review-scope.md).
If the user supplied --verbose or --gemini-model <id>, capture them for
Step 1. Strip --scope <path>, --verbose, and --gemini-model <id> from the
target before passing target; otherwise the tool will try to resolve the flag
text as part of the review target.
What ships with it
1 file 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.
- 8d ago Changed · +1 lines 2390333619d4
- 1mo ago Changed · +3 lines 57b3291db16e
- 1mo ago Changed · +7 lines 5d9bb9edfd3e
- 2mo ago First seen · 127 lines · 84 tokens per session scan A 5402954e307d
q-review is a skill published in the GitHub repository sdewell/code-quorum (1 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 3,355 once invoked, about $0.0003 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 skills, from other repositories
review-prs
Triage open PRs — screen from the diff, delegate the admission judgment to audit-the-list, then merge or close on GitHub. Fire when the maintainer asks to review PRs, process the PR queue, or judge whether a specific PR should be merged.
reviewing-personhog-protocol
The full review process for personhog coordination-protocol changes — leases, fencing, handoffs, supervisors, failure budgets, warming, and changelog semantics. Use before pushing or requesting review on any personhog protocol changeset, when asked for an exhaustive or careful review of personhog code, and after any…
deploy-landed
A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…
guardian
Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy; the ship recipe also executes PR delivery (create, CI watch, merge, cleanup) with Ask First on merge. Use when PR preparation, commit strategy, or gated PR delivery is needed.
harness-pr-reviewer
Checks a submitted PR against the environment's baseline assets (CLAUDE.md, memory, naming, asset classification) and attaches a review comment with a merge recommendation. 5 steps — diff read, 8-area consistency check, self-catch, comment, merge recommendation.