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-fstopgit 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-fstop)<a href="https://agentmods.dev/skills/tomismeta/aperture/aperture-lab-fstop"><img src="https://agentmods.dev/badge/skills/tomismeta/aperture/aperture-lab-fstop/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-fstop"><img src="https://agentmods.dev/badge/skills/tomismeta/aperture/aperture-lab-fstop.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 | $0.00052 | $0.00351 |
| Opus 5.5 | $0.00021 | $0.00140 |
| Sonnet 5.5 | $0.00010 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
aperture_lab_fstop 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 2mo 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 F-Stop
Use this skill when the goal is to operate F-Stop, the discovery and proposal subsystem inside Aperture Lab.
The canonical command surface is:
pnpm lab:fstop:campaign --provider <provider> --reviewer-provider <provider> --optimizer-provider <provider> ...pnpm lab:fstop:run --provider <provider> --reviewer-provider <provider> --optimizer-provider <provider> ...pnpm lab:fstop:review --reviewer-provider <provider> ...pnpm lab:fstop:reviewer --provider <provider>pnpm lab:fstop:propose --reviewer-provider <provider> --optimizer-provider <provider> ...pnpm lab:fstop:optimize --provider <provider> ...pnpm lab:fstop:optimizer --provider <provider>
Load first:
packages/lab/research/autoresearch-program.mdpackages/lab/research/autoresearch-config.json
Main rule:
- keep AI out of the live Aperture hot path
- use F-Stop to discover, review, calibrate, and propose
- let Aperture Lab own the scoring and gates
- prefer
lab:fstop:campaignfor unattended VPS work
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.
- 2mo ago First seen · 33 lines · 52 tokens per session scan A 48d570e5ab25
aperture_lab_fstop is a skill published in the GitHub repository tomismeta/aperture (25 stars, last pushed 11d ago), licensed MIT. It adds 52 tokens to every session and 351 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 2026-08-30.
Other skills, from other repositories
cool-workflow
Use when the user asks for Cool Workflow, CW, agent workflow control-plane, TypeScript workflow orchestration, phased multi-agent work, background workflow tasks, reusable workflow apps, or auditable agent run state.
ci-triage
Diagnose failing CI, build, release-gate, or test runs for Cool Workflow. Use when a GitHub Actions check, local npm test, npm run build, release gate, smoke test, or generated-manifest check fails and Codex must identify the first actionable failure with logs and verifier commands.
deploy-check
Verify Cool Workflow release, publish, deploy, or package readiness. Use when Codex must check build/test gates, generated manifests, project index sync, dist/source contract, changelog/release notes, npm package contents, or pre-tag risk before shipping.
design-qa
Evaluate Cool Workflow architecture, product design, operator UX, context-pack, workflow-app, MCP/CLI, or release-process proposals. Use when Codex must decide whether a design respects FreeBSD/POLA, mechanism-not-policy, stable JSON surfaces, evidence, and verifier boundaries before implementation.
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.
resonate-lovable-usage-prompt-typescript
Specialized guidance for building Resonate applications within Lovable.dev, which is Node.js/React/TypeScript. Use when working with Lovable's AI-assisted development environment to scaffold, iterate, and deploy Resonate workflows in the TypeScript SDK.