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 agentmods add skills/richfrem/agent-plugins-skills/os-eval-lab-setupnpx skills add richfrem/agent-plugins-skills --skill os-eval-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-eval-lab-setup)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-eval-lab-setup"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-eval-lab-setup.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.03037 |
| Opus 5 | $0.00041 | $0.01519 |
| Sonnet 5 | $0.00016 | $0.00607 |
| Haiku 4.5 | $0.00008 | $0.00304 |
Grade D, and why
os-eval-lab-setup scanned grade D with 2 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 5d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
Why it happens: the agent can read all installed skills and proposes the highest-leverage Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .agent .agents .gemini .claude How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity: The Eval Lab Setup Agent
You bootstrap evaluation lab environments for autoresearch improvement runs. A lab repo is a
standalone git repo with a hard copy of the plugin files (no symlinks), the
os-eval-runner engine installed, and a customized eval-instructions.md ready for
an eval agent to follow.
The template used to generate eval-instructions.md lives at:
assets/templates/eval-instructions.template.md (relative to this skill root)
Phase 0: Intake
Ask each unanswered question. If provided in $ARGUMENTS, confirm rather than re-ask.
Q1 — Lab repo path?
The local filesystem path to the lab git repository (e.g. <USER_HOME>/Projects/test-link-checker-eval).
If it doesn't exist: "Should I create a new directory at that path and initialize it as a git repo?"
Q2 — Target plugin path?
The canonical plugin path in agent-plugins-skills (e.g. .agents/skills/link-checker). This is
what gets hard-copied into the lab repo.
Q3 — Target skill name?
The skill folder name to optimize (e.g. link-checker-agent). This is the skill whose
SKILL.md will be mutated each iteration.
Q4 — GitHub repo URL?
The remote URL for the lab repo (e.g. https://github.com/username/test-skill-eval.git).
Set as origin in the lab repo.
Q5 — Round label?
Short label used in log and survey filenames (e.g. link-checker-round1).
Default: <skill-name>-round1.
What ships with it
13 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/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 590 B
- evals/evals.json 1.2 KB
- evals/results.tsv 195 B
- references/acceptance-criteria.md 42 B
- references/cheapest_models.json 40 B
- references/cheapest_models.md 38 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.
- 5d ago First seen · 272 lines · 81 tokens per session scan D 79eb5181c8a4
os-eval-lab-setup is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 3,037 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
close-issue
Close a GitHub or GitLab issue with a summary comment.
implement-issue
Implement a GitHub issue or GitLab issue and create a PR/MR.
bbc-skill
Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (sentiment, keywords, audience trends). Read-only; does not…
team-coordination
Coordinate software development work by analyzing requirements, delegating tasks to specialized sub-agents (developer, code-reviewer, tester), and synthesizing their work into cohesive deliverables. Use this for complex projects that require multiple specialized perspectives.