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-plannergit 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-planner)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-lab-planner"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-lab-planner/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-planner"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-lab-planner.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 | $0.00195 | $0.01381 |
| Opus 5.5 | $0.00078 | $0.00552 |
| Sonnet 5.5 | $0.00039 | $0.00276 |
| Haiku 4.5 | $0.00019 | $0.00138 |
Grade A, and why
os-lab-planner 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OS Lab Planner
Receives a brief from os-lab-agent and produces a plan plus a delegation prompt. It never
asks the user open interview questions: if the brief lacks a target, goal or tool list, stop
and return the gap to os-lab-agent.
Contents
Critical constraints
- Read-only until the plan is written. Steps 1 to 3 only read files.
- Verify before claiming. Claim an existing skill or agent only after reading its file.
- 2-3 options, always. Never write a plan from a single approach.
- Skills are not created reactively. Create only if the audit proves no existing skill can be extended, and the gap has recurred. Modify first.
- Never assume a CLI is available. Use only the tools the brief lists as confirmed.
- Delegate, do not execute. Dispatch goes through the matching
cli-agentsdispatcher skill (see references/delegation.md). Never call scripts owned by another plugin.
Workflow
- Read the brief. Needs: target, goal, success criteria, run depth, confirmed tools. If
any is missing, stop and ask
os-lab-agent. - Audit what exists. Read the target's source
SKILL.mdor agent file (not an installed copy), its evals, the target program file, and the latest results. Search for overlapping skills. Record the match quality (full, partial, none) and the gaps found. Use references/audit-lenses.md. - Choose the path. Use the table below. If a full, current match exists with no gaps,
report "no action warranted" and stop.
For Update or Create, register the work in the control plane before proposing it,
then log the prior-art scan (read
references/map-debt.mdforRepeat: YESentries andwiki/decisions/for rejected approaches). Stop and escalate if aRepeat: YESentry matches the target.
What ships with it
9 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.
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 · 109 lines · 195 tokens per session scan A 57b87d24b80c
os-lab-planner is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed 2d ago), licensed MIT. It adds 195 tokens to every session and 1,381 once invoked, about $0.0008 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
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
ap-route-analyst
Inspect only enough read-only project information to recommend a route and list the facts behind that recommendation.
ap-roadmap-author
Write one dependency-ordered roadmap with owners, integration points, success items, and real checks.
ap-depth-prober
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-fresh-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.