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-architectgit 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-architect)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-architect"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-architect.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.01007 |
| Opus 5 | $0.00042 | $0.00504 |
| Sonnet 5 | $0.00017 | $0.00201 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
os-architect 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
os-architect is the single entry point to the Agentic OS evolution ecosystem. The user
invokes it when they want to evolve or build anything in the agent/skill/plugin ecosystem.
It interviews, audits, and routes — never implements directly. The full behavior spec lives
in agents/os-architect-agent.md.
How to Invoke
/os-architect
No arguments needed. Start with a plain-language description of what you want to evolve.
What It Does
- Phase 1 — Intent Interview: classifies the request into one of 5 evolution categories
- Phase 2 — Ecosystem Audit: verifies what capabilities exist vs what's missing
- Phase 3 — Proposal + Dispatch: proposes Path A/B/C and dispatches via the user's CLI tools
Native Plan Mode required for Phases 1-2: per graph-planning-superpowers-policy.md §2.1,
enter host-native Plan Mode (Claude Code /plan, or the host's equivalent) before Phase 1 begins.
Phases 1-2 are audit-only — Read/Grep/Bash(read-only) commands to classify intent and inspect
existing capabilities. Do NOT write, edit, or scaffold any file before the Path (A/B/C) is
proposed in Phase 3 and the user confirms it. Write is only exercised once a path is confirmed,
Plan Mode is exited, and control passes to os-evolution-planner or create-sub-agent.
Dispatch Paths
| Path | When | Mechanism |
|---|---|---|
| A+ — No Action | audit shows full match + all patterns present | tell user, no dispatch |
| A — Orchestrate | capability exists, current | route to existing agent/skill + run_agent.py |
| B — Update | capability exists, outdated/incomplete | os-evolution-planner writes plan + prompt → dispatch + optional improvement loop |
| C — Create | gap confirmed | create-sub-agent scaffold → os-evolution-planner plan + prompt → eval lab → evals HARD-GATE → os-architect-tester validates |
Related Capabilities
| Skill / Agent | Purpose |
|---|---|
os-evolution-planner skill |
Called for Path B/C: writes structured task plan + Copilot CLI delegation prompt |
os-architect-tester agent |
Validates os-architect correctness via scenario simulation — run after any changes |
improvement-intake-agent |
Called for Category 3 (Lab Setup): configures the skill improvement run |
create-sub-agent |
Called for Path C (Gap Fill): scaffolds the new agent/skill file |
What ships with it
1 file 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.
- 7d ago First seen · 73 lines · 83 tokens per session scan A 6aea1b3d9463
os-architect is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,007 once invoked, about $0.0004 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 2026-08-31.
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
A read-only tool for collecting all comments from a Bilibili video, including replies and pinned comments. Bilibili is a Chinese video-sharing platform.
feature-implementation
Implement software features, fix bugs, and write production-quality code. Use this for hands-on development work including writing new code, modifying existing code, and debugging issues.