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 red-teamgit 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/red-team)<a href="https://agentmods.dev/skills/larsboes/axon/red-team"><img src="https://agentmods.dev/badge/skills/larsboes/axon/red-team/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/red-team"><img src="https://agentmods.dev/badge/skills/larsboes/axon/red-team.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 | $0.00128 | $0.01021 |
| Opus 5 | $0.00064 | $0.00511 |
| Sonnet 5 | $0.00026 | $0.00204 |
| Haiku 4.5 | $0.00013 | $0.00102 |
Grade A, and why
red-team 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
red-team
One proposal goes in. The strongest honest case for it and the strongest surviving case against it come out, with each objection ranked and testable.
Red-team attacks a single proposal. To weigh options against each other, use council.
Adapted from the RedTeam skill in LifeOS by Daniel Miessler (https://github.com/danielmiessler/LifeOS), MIT.
Procedure
Copy this checklist and track progress:
- [ ] 1. Restate the proposal as atomic claims
- [ ] 2. Write the steelman
- [ ] 3. Attack every claim through the lenses
- [ ] 4. Rank the findings by severity
- [ ] 5. Name the one core issue
- [ ] 6. Report, and hand off if the answer is a choice
1 — Atomic claims. Read references/method.md and split the proposal into claims that are
each independently true or false. A claim that cannot be false is a preference. Move it out of
the list and say so.
2 — Steelman. Write the version of the proposal its author would sign. Fix its weak wording, supply the argument it left implicit, and use its best evidence. Attacking a proposal you first made weaker proves nothing.
3 — Attack. Read references/lenses.md and run each lens against every claim. Run the lenses
as parallel red-team-lens subagents, one lens per agent, when the proposal is longer than a page
or the claims need files read. Run them inline otherwise. A lens reads files; it never runs a
command and never edits one, so any measurement it is allowed to cite has to be in its prompt.
4 — Rank. Sort every surviving finding into fatal, structural, cost or cosmetic.
Discard anything that only restates a claim in a hostile tone. Volume is not signal.
5 — The core issue. Name the single assumption that, if false, collapses the rest. Most proposals have exactly one. Say so if this one has none.
6 — Report. Follow references/output-format.md. Every finding carries a remediation and a
test that would settle it.
What counts as a finding
- A stated claim that is false, and the evidence that it is false.
- An unstated assumption the proposal needs and never argues.
- A step that does not follow from the step before it.
- A category error: the proposal treats one thing as another and inherits the wrong rules.
- A precedent that already went the other way, cited.
What ships with it
3 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 · 87 lines · 128 tokens per session scan A ba1dabed519f
red-team is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 128 tokens to every session and 1,021 once invoked, about $0.0006 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.