aperture_lab_agent

aperture_lab_agent is a skill for Claude Code, Codex from tomismeta/aperture. It costs 50 tokens per session (457 once invoked), scanned A, original, MIT.

A provider-neutral runtime loop for Aperture Lab F-Stop, a self-hosted system that reviews and improves AI-agent runs. It can work with OpenClaw, Hermes, or another compatible runtime.

In plain words
What is it for?
Operating the F-Stop reviewer and optimizer, running experiments, and applying its defined edit, artifact, and promotion rules.
Why use it?
It provides a standard command surface for running, reviewing, proposing changes, and optimizing the harness while keeping AI out of the main application path.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Operating the F-Stop reviewer and optimizer, running experiments, and applying its defined edit, artifact, and promotion rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomismeta/aperture/aperture-lab-agent
Install

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.

Any agent
npx skills add tomismeta/aperture --skill aperture-lab-agent
Clone the repo
git clone --depth 1 https://github.com/tomismeta/aperture

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for aperture_lab_agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomismeta/aperture/aperture-lab-agent/github.svg)](https://agentmods.dev/skills/tomismeta/aperture/aperture-lab-agent)
Your own site
<a href="https://agentmods.dev/skills/tomismeta/aperture/aperture-lab-agent"><img src="https://agentmods.dev/badge/skills/tomismeta/aperture/aperture-lab-agent/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.

agentmods 80×15 button for aperture_lab_agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomismeta/aperture/aperture-lab-agent"><img src="https://agentmods.dev/badge/skills/tomismeta/aperture/aperture-lab-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.00457
Opus 5 $0.00025 $0.00229
Sonnet 5 $0.00010 $0.00091
Haiku 4.5 $0.00005 $0.00046

Measured 9d ago against content hash 733b25b3cdb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aperture_lab_agent 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 9d 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.

skills/aperture-lab-agent/SKILL.md · 67 lines

What it actually says

Aperture Lab F-Stop Runtime

Use this skill when the goal is to run Aperture Lab F-Stop as a self-hosted runtime harness, not when working on the live product path.

The canonical command surface is provider-neutral:

  • pnpm lab:fstop:run --provider <provider> --reviewer-provider <provider> --optimizer-provider <provider> ...
  • pnpm lab:fstop:review --reviewer-provider <provider> ...
  • pnpm lab:fstop:propose --reviewer-provider <provider> --optimizer-provider <provider> ...
  • pnpm lab:fstop:optimize --provider <provider> ...
  • pnpm lab:fstop:reviewer --provider <provider>
  • pnpm lab:fstop:optimizer --provider <provider>

Supported providers today:

  • openclaw
  • hermes
  • generic

Provider-specific shortcuts such as lab:fstop:openclaw are conveniences, not the core product surface.

Load First

Read:

  • packages/lab/research/autoresearch-program.md
  • packages/lab/research/autoresearch-config.json

These define:

  • allowed edit paths
  • forbidden edit paths
  • artifact flow
  • promotion rules
  • optimizer output contract

Main Rule

Keep AI out of the hot path.

This harness may:

  • run the top-level agent-managed loop
  • import public trajectories
  • run offline review and disagreement capture
  • promote repeated high-confidence disagreements
  • optimize against the frozen calibration corpus
  • return a reviewable proposal artifact

It must not:

  • change live runtime behavior to depend on AI
  • edit outside the allowed semantic/importer surface
  • auto-merge code

Product Surface

Treat lab:fstop:* as the only supported CLI namespace.

Changes

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.

  1. 9d ago First seen · 67 lines · 50 tokens per session scan A 733b25b3cdb6

Subscribe to this mod's changes

aperture_lab_agent is a skill published in the GitHub repository tomismeta/aperture (24 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 457 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.

Related

Other skills, from other repositories

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.

coo1white/cool-workflow · 58 tokens

triage-contributor-pr

Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…

prisma/orm · 131 tokens

no-bare-casts

Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.

prisma/orm · 52 tokens

update-pr

Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.

microsoft/vscode · 26 tokens

remember

Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…

langchain-ai/deepagents · 71 tokens

code-review

Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.

langchain-ai/deepagents · 23 tokens