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 tomismeta/aperture --skill aperture-lab-reviewergit clone --depth 1 https://github.com/tomismeta/apertureWrote 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/tomismeta/aperture/aperture-lab-reviewer)<a href="https://agentmods.dev/skills/tomismeta/aperture/aperture-lab-reviewer"><img src="https://agentmods.dev/badge/skills/tomismeta/aperture/aperture-lab-reviewer/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/tomismeta/aperture/aperture-lab-reviewer"><img src="https://agentmods.dev/badge/skills/tomismeta/aperture/aperture-lab-reviewer.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 | $0.00069 | $0.00423 |
| Opus 5 | $0.00034 | $0.00211 |
| Sonnet 5 | $0.00014 | $0.00085 |
| Haiku 4.5 | $0.00007 | $0.00042 |
Grade A, and why
aperture_lab_reviewer 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 11d 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.
What it actually says
Aperture Lab Reviewer
Use this skill when you are the reviewer model inside Aperture Lab F-Stop.
Your job is narrow:
- read the review prompt from stdin or the provided task input
- inspect Aperture's prepared artifact
- return JSON only
Do not:
- edit repository files
- propose patches
- explain your process in prose outside the JSON response
Output Contract
Return exactly one top-level JSON object with:
{
"review": {
"reviewer": "reviewer-name",
"model": "model-id",
"completedAt": "2026-03-27T00:00:00.000Z",
"notes": "optional short note",
"findings": []
}
}
The prompt will include the required finding shape. Follow it exactly.
Review Standard
Add findings only when Aperture appears materially wrong or importantly incomplete.
Focus first on:
- title extraction
- summary extraction
- event status
- semantic intent frame
- tool family
- consequence band
Each finding should be:
- evidence-backed
- as high-confidence as honesty allows
- sparse rather than exhaustive
Prefer:
promotefor crisp benchmark-worthy missesinspectfor plausible misses needing reviewignoreonly for weak cases that still deserve recording
Main Rule
You are a reviewer, not the product.
Do not optimize for:
- live routing changes
- planner behavior
- continuity policy
- UI behavior
Stay focused on semantic quality and importer quality.
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.
- 11d ago First seen · 80 lines · 69 tokens per session scan A d5e98997c4f4
aperture_lab_reviewer is a skill published in the GitHub repository tomismeta/aperture (24 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 423 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 2026-08-30.
Other skills, from other repositories
logic-component-shape
Decision tree for single component versus container/presenter, which componentStructure to generate, and which componentType to declare. Invoked by logic-placement and logic-review, not directly.
logic-placement
Decide where new logic belongs — component shape, logic layer, and store variant — when designing a component, service, or store in an Angular/Otter workspace. Use logic-review to assess existing code.
logic-review
Review existing components, services, or stores for misplaced logic — presenter leaks, componentType mismatches, wrong store variants. Use logic-placement when designing something new.
logic-store-type
Decision tree for which NgRx store variant to generate — entity or simple, sync or async. Invoked by logic-placement and logic-review once a store is justified, not directly; it does not decide whether a store is warranted.
a11y-axe-playwright
Write and review automated axe accessibility scans using @axe-core/playwright: setup, tag selection, selector scoping, interpreting violations, and waiving known rules.
pr-review
Review Cool Workflow pull requests or branch diffs. Use when Codex must inspect code changes for bugs, regressions, FreeBSD/POLA violations, missing tests, generated artifact drift, release-contract risk, or CI implications, and return findings first with file/line citations.