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 5.5 | $0.00051 | $0.00408 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 1mo ago), licensed MIT. It adds 128 tokens to every session and 1,021 once invoked, about $0.0005 per session on Opus 5.5. 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.
red-team compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| red-teamlarsboes/Axon | Skill | 1 | 1mo ago | MIT | A | 128 | Claude Code |
| ligandmpnnaipoch/open-science | Skill | 5.5k | today | Apache-2.0 | A | 100 | Claude Code, Codex |
| evo2aipoch/open-science | Skill | 5.5k | today | Apache-2.0 | A | 83 | Claude Code, Codex |
| create-agentPM-Shawn/Abu-Cowork | Skill | 419 | 3d ago | Apache-2.0 | A | 13 | Claude Code |
| content-monitorCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 16 | Claude Code, Codex |
| llm-wikiCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 27 | Claude Code, Codex |
| simplifyCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 24 | Claude Code, Codex |