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 me2resh/apexyard --skill approve-architecturegit clone --depth 1 https://github.com/me2resh/apexyardWrote 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/me2resh/apexyard/approve-architecture)<a href="https://agentmods.dev/skills/me2resh/apexyard/approve-architecture"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/approve-architecture/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/me2resh/apexyard/approve-architecture"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/approve-architecture.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 | $0.00035 | $0.02719 |
| Opus 5 | $0.00017 | $0.01359 |
| Sonnet 5 | $0.00007 | $0.00544 |
| Haiku 4.5 | $0.00003 | $0.00272 |
Grade A, and why
approve-architecture 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/approve-architecture — Record Per-PR Design-Review Approval
Writes .claude/session/reviews/<owner>__<repo>__<pr>-architecture.approved (repo-qualified path, see AgDR-0060) with the current HEAD SHA so the require-architecture-review.sh merge-gate hook will let a design-artifact PR through. Without this marker, the hook blocks merges on any PR that touches a technical design, a migration AgDR, or a feature spec / PRD.
This skill is the architecture-review analog of /approve-design (UI gate) and /approve-merge (CEO gate). Same pattern, different gate. The reviewer is Tariq (the Solution Architect).
The one rule you must not break
INVOKE THIS SKILL ONLY ON EXPLICIT, PER-PR, DESIGN-REVIEW APPROVAL.
Normally Tariq writes the marker himself on an APPROVED verdict (see .claude/agents/solution-architect.md). This skill is the operator path to record the same marker — for when a human architect reviewed the design, or when you need to re-record after a rebase.
Valid invocation triggers:
- "design review passed" / "architecture approved" / "the design in #42 is sound" — if and only if the surrounding context clearly names a specific PR and the design has actually been reviewed against the architecture lens.
- "PR #42 architecture approved" — names the PR explicitly.
- A reply to your own "PR #42's design — architecture review approved?" message that consists of any affirmative token.
Invalid triggers (do NOT run this skill):
- "looks good" / "nice design" — when said about a whiteboard sketch, a Figma, or a verbal proposal that is not a specific PR's design artifact. Architecture review means reviewing the committed design doc / AgDR / spec in a PR, not a sketch.
- "the approach is fine" — when said in a planning context ("let's go with this approach") rather than a review context ("I've reviewed the design doc against the lens and it's sound").
- "go" / "continue" / "ship it" — umbrella responses to a multi-step plan. Same rule as
/approve-merge. - Your own inference that "the design is probably fine." NO. Stop and ask.
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 · 190 lines · 35 tokens per session scan A ba4cba461677
approve-architecture is a skill published in the GitHub repository me2resh/apexyard (498 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 2,719 once invoked, about $0.0002 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 2026-08-30.
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.