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 acaprino/daodan --skill review-quality-gatesgit clone --depth 1 https://github.com/acaprino/daodanWrote 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/acaprino/daodan/review-quality-gates)<a href="https://agentmods.dev/skills/acaprino/daodan/review-quality-gates"><img src="https://agentmods.dev/badge/skills/acaprino/daodan/review-quality-gates/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/acaprino/daodan/review-quality-gates"><img src="https://agentmods.dev/badge/skills/acaprino/daodan/review-quality-gates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.07074 |
| Opus 5.5 | $0.00037 | $0.02830 |
| Sonnet 5.5 | $0.00018 | $0.01415 |
| Haiku 4.5 | $0.00009 | $0.00707 |
Grade A, and why
review-quality-gates 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 1mo 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 — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Quality Gates
Gates and consolidation rules shared by /senior-review:team-review and /senior-review:code-review.
Shared-Context Provenance Rule
Evidence derived from a shared artifact cannot independently corroborate the claims contained in that same artifact. N reviewers agreeing on a premise they were all given is one observation, not N.
This is the pipeline's first-level invariant, not quality advice. Three consequences bind every gate below:
- A reviewer that consumed a claim from the X-ray output or the interconnect map has not verified that claim. It must re-derive the claim independently before standing a finding on it.
- Concordance between reviewers who share a premise is an echo. It raises no confidence and no severity. Consolidation reports it as such.
- No metric may reward agreement with a shared artifact. Utilization of the map is an operational number, never a quality signal.
The same rule applied across model families instead of across reviewers is implemented by the peer-review plugin (/peer-review:review), which sends a plan or spec to a challenger on a different model family and runs an evidence-backed multi-round deliberation over it. There the shared artifact is the challenge packet: facts supplied to the challenger are tagged GIVEN, repeating one back never counts as corroboration, and a participant that reaches the authoritative source itself records the promotion GIVEN -> DERIVED. That plugin bounds the claim further than this section does, because two frontier models still share a corpus: what earns the second opinion its cost is decorrelated errors, not clean-room independence.
Context Sharing Pattern
When /team-review runs in pipeline mode (no --no-context), reviewers do not receive raw code only. They receive three context artifacts produced in Phase 1:
- X-ray output (from
codebase-xrayplugin) at the path the orchestrating command recorded:$XRAY_RUN_DIRwhen that command started the X-ray run itself (/team-reviewPhase 1a), or the.codebase-xray/mirror when it is consuming an analysis that already existed (/code-reviewStep 2). A command that started a run never reads the mirror: the mirror means "latest published run", not "the run I just produced". Files:01-structure.md,02-interfaces.md,05-risks.md, and optionally03-flows.md,04-semantics.md,06-documentation.md,07-final-report.md. - Interconnect map at
.team-review/02-interconnect.md(fromcodebase-xray:semantic-interconnect-mapper): contracts (formal / structural / implicit), invariants, domain rules, assumptions (verified / documented / unverified), integration hot-spots, change impact radius. - Knowledge provenance at
.team-review/01-knowledge-provenance.md(from/team-reviewPhase 1d): which concepts each discovery branch found, which neither found, and which they disagree about. Reviewers derive candidate concerns from it, so it is distributed with the other two.
What ships with it
3 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.
- 1mo ago First seen · 412 lines · 92 tokens per session scan A bafcb01dafc8
review-quality-gates is a skill published in the GitHub repository acaprino/daodan (9 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 7,074 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…