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-evolution-verifiernpx skills add richfrem/agent-plugins-skills --skill os-evolution-verifiergit 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-evolution-verifier)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-evolution-verifier"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-evolution-verifier.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 | $0.00091 | $0.03603 |
| Opus 5 | $0.00046 | $0.01801 |
| Sonnet 5 | $0.00018 | $0.00721 |
| Haiku 4.5 | $0.00009 | $0.00360 |
Grade A, and why
os-evolution-verifier 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 2d 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
After evolving os-architect or its downstream agents, you need proof that the changes actually work. This skill dispatches os-architect in single-shot simulation mode for each test scenario and verifies artifact presence — not by reading the transcript, but by checking that expected files exist or expected content appears in output.
Evolution is verified by artifact presence, not by transcript review.
Artifact Verification Table
| Evolution Type | What to Check |
|---|---|
| Path C (Gap Fill) | SKILL.md present at expected path |
| Path B (Update) | tasks/todo/<slug>-plan.md AND tasks/todo/copilot_prompt_<slug>.md written |
| Path A+ (No-op) | No new files written; HANDOFF_BLOCK contains STATUS: complete |
| Category 3 (Lab Setup) | improvement/run-config.json written AND HANDOFF_BLOCK emitted |
| HANDOFF_BLOCK integrity | All 7 fields present: INTENT, TARGET, PATH, DISPATCH, STATUS, OUTPUTS, NEXT_ACTION |
| Confidence model | Low confidence prompt → clarifying question appears before Phase 2 audit |
| Evolution Integrity Gate | When logic in plugins/ changes, references/map-debt.md or evolution-log.md is updated, or Evolution-Check: none is present |
Phase 1 — Resolve Test Inputs
If invoked with all, find test scenarios:
ls temp/os-evolution-verifier/scenarios/*.json 2>/dev/null | sort
If invoked with a specific file, verify it exists and is valid JSON with required fields:
python3 -c "
import json, sys
d = json.load(open('$SCENARIO_FILE'))
required = ['id', 'name', 'path', 'prompt', 'expected_artifact', 'artifact_check']
missing = [f for f in required if f not in d]
if missing:
print(f'SCHEMA ERROR: missing fields: {missing}'); sys.exit(1)
print(f'Scenario: {d[\"id\"]} — {d[\"name\"]}')
"
If no scenarios found and no file given, report:
"No test scenarios found. Create scenario JSON files in
temp/os-evolution-verifier/scenarios/or run context-bundler (red-team mode) to generate them fromos-architect-agent.md."
What ships with it
5 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.
- 2d ago Changed · +2 lines 89bb2da724be
- 5d ago First seen · 350 lines · 91 tokens per session scan A e5f7818bbd80
os-evolution-verifier is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 3,603 once invoked, about $0.0005 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
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.