Borrowing it
Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/skills/po-council/SKILL.mdgit clone --depth 1 https://github.com/wlsdks/ontology-atlasWrote 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/wlsdks/ontology-atlas/po-council)<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/po-council"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/po-council/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/wlsdks/ontology-atlas/po-council"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/po-council.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.01380 |
| Opus 5 | $0.00015 | $0.00690 |
| Sonnet 5 | $0.00006 | $0.00276 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
po-council 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 6d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atlas PO review — two critics, one accountable owner
The active pilot does not summon a standing committee. pnpm po:route derives
the primary risk from change facts and all four boundary assessments, then selects Evidence plus
exactly one specialist. The human owner decides.
Reviewer map
| Derived risk | Required reviewers | Independent question |
|---|---|---|
meaning |
po-evidence + po-steward |
Is the lost human ability observed, and do meaning, evidence truth, local-first behavior, agent authority, and correction stay trustworthy? |
positioning |
po-evidence + po-wedge |
Is the lost ability observed, and is the first-contact claim distinctive and earned? |
scope |
po-evidence + po-leverage |
Is the lost ability observed, and is this the smallest worthwhile commitment with a credible rollback? |
po-craft is owner-requested recovery-proof review only. It consumes evidence
from the design, responsive, motion, and walkthrough gates; it does not repeat
them.
Seat briefs live at ../../agents/po-*.md. Open only the selected files. From
either mirrored skill tree, the relative path resolves to the matching agent
tree. Never create a third copy.
Run the selected pair in separate contexts and give neither the other's output before first positions are sealed. Use parallel scheduling when available; serial scheduling alone does not weaken independent contexts. If separate contexts are unavailable, disclose the missing independence and report a perspective check, never a completed independent review.
Required use
Use this review only when pnpm po:route returns review, or when the owner
explicitly requests independent review. Mechanical and ordinary reversible work
do not receive a council. Unknown evidence does not gain certainty from more
seats; reviewers prescribe the cheapest learning path.
Round 0 — prior decision and before-state
Read only the relevant record in docs/DECISIONS.md, located with
pnpm decisions:find <surface terms>. Cite it or explicitly overturn it, check
its falsifier, and read the later records the finder lists as citing it.
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.
- 6d ago Changed · +4 lines cbcd123156d3
- 8d ago Changed · -10 lines · -6 tokens per session 7d14cf153879
- 13d ago First seen · 156 lines · 36 tokens per session scan A 2fed1b64e0de
po-council is a skill published in the GitHub repository wlsdks/ontology-atlas (104 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,380 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
open-ontologies
AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
accurate-code
Use when implementing or modifying code with Kontext Brain so each behavior-bearing logic unit is grounded in current provenance-backed decisions, domain terms, invariants, and Evidence.
container-manager-kg-ingestion
Snapshot a host's Docker/Podman/Swarm inventory into the epistemic-graph knowledge graph as typed OWL nodes via the container-manager-mcp MCP server — containers, images, volumes, networks, swarm services and nodes, with their :usesImage / :runsOn / :builtFrom links. Use when the agent must record live container state…
action-contract-execution-feedback-loop
A specification method for making a business action into a tool an AI agent can call safely. It defines the action’s inputs, outputs, permissions, preconditions, expected effects, error handling, and audit information.