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 OutlineDriven/outline-driven-development --skill councilgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/council)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/council"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/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/outlinedriven/outline-driven-development/council"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/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 | $0.00035 | $0.00726 |
| Opus 5 | $0.00017 | $0.00363 |
| Sonnet 5 | $0.00007 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00073 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- council — 91% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks for a council, second opinions, or parallel investigation. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Subagents inherit the same read-only posture unless the user explicitly scopes a narrower mutation. |
| Side effect | Spawns parallel subagents in chat output. No repo mutation unless the user explicitly scopes it. Deliverable is the council's decision memo. |
| Done | Decision memo with recommendation, consensus, risks, and evidence. |
Inputs
The question or decision to investigate (required). Number of council members or specific investigative stances to represent (optional; default three distinct stances). Scope constraints and admissible evidence sources (optional). The user-stated criteria bound the investigation; do not widen scope beyond them.
Procedure
- Restate the question and confirm scope against the user-stated criteria. Bound the investigation before spawning; do not widen scope. Done when: the question is restated and scope is confirmed against user criteria.
- Define council members as distinct investigative stances appropriate to the question (for example optimist, skeptic, risk-auditor, domain expert). Use the user-specified stances when supplied; otherwise default to three. Done when: each council member is assigned a distinct investigative stance.
- Spawn one subagent per stance. Each subagent investigates the question independently from its assigned stance, gathers evidence, and returns a position with supporting evidence and identified risks. Done when: one subagent is spawned per stance and each returns a position with evidence and risks.
- Collect all subagent positions without merging prematurely. Done when: every subagent position is collected unmerged.
- Compare positions across stances: mark consensus points, disagreements, and unresolved risks. Done when: consensus points, disagreements, and unresolved risks are marked across all positions.
- Synthesize a decision memo stating the recommendation, the consensus reached, dissenting views, residual risks, and the evidence supporting each. Done when: the memo states recommendation, consensus, dissent, residual risks, and per-point evidence.
- Present the memo. Do not select or execute a decision unless the user explicitly authorizes further action. Done when: the memo is presented and no decision is executed without explicit user authorization.
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.
- 2d ago Changed · -15 tokens per session f56037c444bb
- 5d ago First seen · 40 lines · 50 tokens per session scan A fb36a8861861
council is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 35 tokens to every session and 726 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.