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 richfrem/agent-plugins-skills --skill os-lab-setupgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/os-lab-setup)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-lab-setup"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-lab-setup/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/richfrem/agent-plugins-skills/os-lab-setup"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-lab-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00161 | $0.00680 |
| Opus 5.5 | $0.00064 | $0.00272 |
| Sonnet 5.5 | $0.00032 | $0.00136 |
| Haiku 4.5 | $0.00016 | $0.00068 |
Grade A, and why
os-lab-setup 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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lab Setup (os-lab-setup)
Bootstrap lab environments for skill improvement runs, copying plugin files as real files (no symlinks) and configuring eval-instructions.md.
Contents
Critical Constraints
- Resolve Symlinks on Copy: Always use
cp -RLso the lab repo contains independent, standalone files. - Clean Slate: Remove
.agent .agents .gemini .claudedirectories in the lab repo before installing. - Workspace Permissions: Confirm directory permissions before creating or mutating lab repositories.
Quick start
Generate evaluation instructions for a target skill in a lab repo:
python3 scripts/generate_eval_instructions.py --skill <skill-name> --lab-repo <path>
Workflow
- Intake: Gather lab repo path, target plugin path, skill name, and GitHub repository URL.
- Bootstrap Lab Repo: Initialize git repository, clean slate, and copy plugin files via
cp -RL. - Generate Instructions: Render
eval-instructions.mdfromassets/templates/eval-instructions.template.md. - Seed Commit: Commit baseline state in lab repo and push to origin.
- Launch Options: Provide the user with manual instructions or an autonomous CLI launcher command (for
agy-based launches, seeagy-cli-agent). Hand the run itself toos-lab-loop.
Verification
Confirm lab repo contains materialized files and valid eval-instructions.md:
test -f "<lab-repo-path>/eval-instructions.md" && echo "Lab setup valid"
References
- detailed-reference.md — Intake questions, option tables, and exact bootstrap commands.
- acceptance-criteria.md — Verification criteria for bootstrapped lab environments.
- fallback-tree.md — Remediation pathways if lab initialization or generation fails.
What ships with it
16 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.
- assets/diagrams/sibling-repo-labs.mmd 49 B
- assets/templates/autoresearch/evals.json.template 64 B
- assets/templates/autoresearch/program.md.template 64 B
- assets/templates/autoresearch/results.tsv.template 65 B
- assets/templates/eval-instructions.template.md 58 B
- evals/.lock.hashes 425 B
- evals/evals.json 1.4 KB
- evals/results.tsv 195 B
- references/acceptance-criteria.md 55 B
- references/cheapest_models.md 38 B
- references/copilot_proposer_prompt.md 46 B
- references/detailed-reference.md 54 B
- references/fallback-tree.md 49 B
- references/operating-protocols.md 42 B
- references/program.md 30 B
- scripts/generate_eval_instructions.py 46 B runs code
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.
- yesterday First seen · 64 lines · 161 tokens per session scan A 2ecd14884217
os-lab-setup is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed 2d ago), licensed MIT. It adds 161 tokens to every session and 680 once invoked, about $0.0006 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 2026-10-16.
Other skills, from other repositories
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
issue-to-pr
Implement one bounded repository issue with normal host tools, prove the tested change through one scafld finalize wall, and optionally publish the exact pull request through scoped provider authority with readback.
cmux-testing
Choose scoped cmux verification, add behavioral tests, and validate Swift test targets and wiring. Use when adding tests or deciding what local/CI evidence a change needs.
development-scheduler
A workflow for coordinating multi-role coding work through Herdr, a task scheduler, and repo-harness sessions. It assigns implementation, review, and handoff tasks while checking permissions and evidence.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.
spinout
Use when extracting a project into its own repo — a venture spinout (e.g. a product leaving its incubator repo) or a sanitized content-snapshot fork. Guided 5-step runbook: target sphere + path, confidentiality/sanitize check, copy + fresh git init, SNAPSHOT-FREEZE marker in the source repo, remotes + registration.…