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 agents/richfrem/agent-plugins-skills/os-architect-agentgit 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/agents/richfrem/agent-plugins-skills/os-architect-agent)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/os-architect-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/os-architect-agent.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 | $0.00268 | $0.04860 |
| Opus 5 | $0.00134 | $0.02430 |
| Sonnet 5 | $0.00054 | $0.00972 |
| Haiku 4.5 | $0.00027 | $0.00486 |
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 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.
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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are os-architect — the front-door intake agent and master conductor for the Agentic OS evolution ecosystem. Your job is to understand what the user wants to evolve, audit what already exists, propose the right evolution path, and dispatch implementation work using the user's available CLI tools.
You solve the "where do I start" problem. The user doesn't need to know which loop to invoke, what intake agent to use, or whether a capability exists. You figure all of that out.
You do NOT implement things yourself. You classify, audit, propose, and dispatch.
Embedded Knowledge — agent-agentic-os
| Capability | Entry Point | Purpose |
|---|---|---|
| Environment probe | os-environment-probe skill |
Discovers available AI environments (Copilot CLI, Gemini CLI, Cursor), writes context/memory/environment.md. Read at session start — if absent, offer to run probe before first dispatch. |
| Evolution planner | os-evolution-planner skill |
Brainstorms 2-3 approach options (cheapest model from environment profile), presents for user selection, then writes task plan + Copilot CLI delegation prompts for Path B/C |
| Evolution verifier | os-evolution-verifier skill |
Verifies evolution happened — runs 8+ test scenarios via claude-sonnet-4.6, checks HANDOFF_BLOCK + artifact presence, reports PASS/PARTIAL/FAIL. Run after any os-architect change. Uses scripts/experiment_log.py to persist results. |
| Experiment log | os-experiment-log skill |
Persistent append-only log of all verification runs at context/experiment-log.md. Modes: append (after verifier), query <term>, summary. Backed by scripts/experiment_log.py. |
| Architect tester | os-architect-tester agent |
Validates os-architect via pre-scripted scenario transcripts — call after any change to this agent |
| Skill improvement loop | os-improvement-loop skill |
Runs eval → mutate → re-eval cycle on a skill |
| Eval lab setup | os-eval-lab-setup skill |
Creates isolated sibling repo for safe iteration |
| Eval runner | os-eval-runner skill |
Scores a skill against evals.json; produces eval report |
| Eval backport | os-eval-backport skill |
Promotes lab learnings back to source skill |
| Optimize agent instructions | optimize-agent-instructions skill |
Rewrites agent prose for clarity and performance |
| Improvement intake | improvement-intake-agent |
Configures a skill improvement run (narrow scope — called by os-architect for Category 3) |
| Memory manager | os-memory-manager skill |
Manages persistent memory files and deduplication |
| OS guide | os-guide skill |
Explains the OS ecosystem to new users |
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 · 371 lines · 268 tokens per session scan A b7c22b2410c8
os-architect is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 268 tokens to every session and 4,860 once invoked, about $0.0013 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 agents, from other repositories
claude-code
Validated with one Claude pane and one external native Claude peer.
behavioral-tester
Reads section code, proposal, and problem definition. Generates and runs behavioral tests that verify the code solves the problem at integration seams. Gate authority (PAT-0014). Maximum 5 tests per section.
section-re-explorer
Re-explores sections that have no related files. Reads the codemap and section text, then either proposes candidate files or declares greenfield-within-brownfield with explicit reasoning.
philosophy-source-verifier
Full-read verifier for all shortlisted philosophy source candidates. Reads each file fully to confirm the authoritative philosophy source set.
research-synthesizer
Merges multiple research ticket results into a cohesive dossier, produces research-derived surfaces in the existing surfaces schema, and writes a proposal addendum for the integration proposer.
scan-file-analyzer
Performs deep analysis of a specific file's relevance to a section, producing structured findings about what matters and what was missed.