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 larsboes/Axon --skill councilgit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/council)<a href="https://agentmods.dev/skills/larsboes/axon/council"><img src="https://agentmods.dev/badge/skills/larsboes/axon/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/larsboes/axon/council"><img src="https://agentmods.dev/badge/skills/larsboes/axon/council.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00140 | $0.01448 |
| Opus 5 | $0.00070 | $0.00724 |
| Sonnet 5 | $0.00028 | $0.00290 |
| Haiku 4.5 | $0.00014 | $0.00145 |
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 9d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
council
A council is four to five subagents that hold different positions on one decision. Each round runs them in parallel and feeds every member the rounds before it. The run ends with one recommendation and the position that lost.
Council weighs options against each other. To attack a single proposal, use red-team.
Adapted from the Council skill in LifeOS by Daniel Miessler (https://github.com/danielmiessler/LifeOS), MIT.
Procedure
Copy this checklist and track progress:
- [ ] 1. State the decision in one sentence
- [ ] 2. Pick DEBATE or QUICK
- [ ] 3. Pick a preset, or compose a council
- [ ] 4. Collect the evidence the members need
- [ ] 5. Run the rounds
- [ ] 6. Check every round with the clerk
- [ ] 7. Write the synthesis
1 — State the decision. Write the question the council answers and the options on the table. A question with one factual answer is not a council topic. Answer it directly and stop.
2 — Pick the mode.
| Mode | Rounds | Use when |
|---|---|---|
| QUICK | 1 | The decision is cheap to reverse, or the caller wants a sanity check |
| DEBATE | 3 | The decision is expensive to reverse, or the options are close |
Default to QUICK. Escalate to DEBATE when the members disagree about facts, not about taste.
3 — Pick a preset. Read the one file that matches the topic. Do not read the others.
| Preset | Decides | File |
|---|---|---|
| architecture | Placement, boundaries, adopt against build | references/presets/architecture.md |
| investment | A change to a personal portfolio | references/presets/investment.md |
| travel | One trip option against another | references/presets/travel.md |
| security | Threat model, data classes, blast radius | references/presets/security.md |
| product | What to build next, and how much of it | references/presets/product.md |
If no preset fits, read references/compose.md and write the briefs there. If the caller names
the members, use those names and skip this step.
Never launch the same brief twice. Identical members agree, and agreement carries no information.
What ships with it
8 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.
- 9d ago First seen · 107 lines · 140 tokens per session scan A ac9545f7dd4e
council is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 1,448 once invoked, about $0.0007 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 2026-09-07.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.