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/stoa-platform/stoa/councilnpx skills add stoa-platform/stoa --skill councilgit clone --depth 1 https://github.com/stoa-platform/stoaWrote 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/stoa-platform/stoa/council)<a href="https://agentmods.dev/skills/stoa-platform/stoa/council"><img src="https://agentmods.dev/badge/skills/stoa-platform/stoa/council.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 | $0.00031 | $0.04707 |
| Opus 5 | $0.00015 | $0.02354 |
| Sonnet 5 | $0.00006 | $0.00941 |
| Haiku 4.5 | $0.00003 | $0.00471 |
Grade A, and why
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 4d 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council Validation — $ARGUMENTS
Three-Stage Council
This skill drives Stage 1 (ticket pertinence) and Stage 2 (plan validation) — both prose-based, 8-persona scoring per the canonical Team Coca jury (HEG-PAT-003).
Stage 3 (code review) runs after implementation on the actual diff, via scripts/council-review.sh (4-axis: conformance, debt, attack_surface, contract_impact). It is not invoked by this skill — it is wired to the pre-push hook (CAB-2048) and council-gate.yml CI workflow (CAB-2049). See .claude/docs/council-s3.md for full docs.
S1 (this skill, prose) → S2 (this skill, plan) → implementation → S3 (council-review.sh, diff) → merge
Step 1: Gather Context
Read and understand the feature/ADR/change description. Gather context from:
memory.md— current sprint, related workplan.md— where this fits in priorities- Relevant code files if technical
Step 1b: Context Compiler — Impact Score
Run the Context Compiler to get the blast radius before scoring:
- Determine the primary component from $ARGUMENTS (or from the ticket description if CAB-XXXX is provided)
- Run:
docs/scripts/build-context.sh --component <component> --intent "$ARGUMENTS"- If a ticket ID is available: add
--ticket "CAB-XXXX"
- If a ticket ID is available: add
- Read the generated context pack in
docs/context-packs/ - Extract the Impact Score and level (LOW/MEDIUM/HIGH/CRITICAL)
- Include the Impact Score in each persona's evaluation context
- If CRITICAL (>= 31): flag it explicitly in the Council report header
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.
- 4d ago First seen · 403 lines · 31 tokens per session scan A 5a89ee0ea42e
council is a skill published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 4,707 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 2026-08-31.
Other skills, from other repositories
lyrik
Security assessment of a codebase — minimal mode for runner validation.
librarian
Read-only retrieval over the daily-digest kept set. Slash-invoke with /librarian ; returns items verbatim with citations.
notes
Create and manage text notes in the workspace.
tdx-assets
Look up staff devices, assets, and locations in TeamDynamix (TDX). Given a list of names, emails, or partial identifiers, resolve each person and return the assets assigned to them with location, model, ownership type, and status. Read-only.
aggregator
Daily fetch from a fixed public allowlist; score against the user's interests file; cluster into themes; push the digest to the configured channel.
file-search
Find files and search content across directories.