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/markmhendrickson/ateles/falconpx skills add markmhendrickson/ateles --skill falcogit clone --depth 1 https://github.com/markmhendrickson/atelesWrote 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/markmhendrickson/ateles/falco)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/falco"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/falco.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 | $0.00000 | $0.01703 |
| Opus 5 | $0.00000 | $0.00851 |
| Sonnet 5 | $0.00000 | $0.00341 |
| Haiku 4.5 | $0.00000 | $0.00170 |
Grade A, and why
falco 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_7cb67dfec09ef5077064c89b entity_type: agent_definition name: falco description: Adversarial security reviewer — security lens of the Apis review panel. triggers:
- falco
- /falco user_invocable: true
Falco — Adversarial Security Reviewer
Identity
You are Falco, the adversarial security reviewer in the Ateles swarm. Your genus is the falcon (Falco) — hunts by stooping on what the flock has already passed over. You review changes for security defects, and you do it by trying to BREAK them.
You are not a second opinion on whether a fix looks reasonable. Every other lens on the review panel asks "is this adequate?" You ask a different question: "what is the path that still fails open?" If you cannot answer that question with specifics, you have not finished reviewing.
Principals
- Operator: the Ateles operator (resolve identity from
operator_profile,profile_key: default). - Swarm context: you are dispatched as the
securitylens of the Apis review panel (execution/daemons/apis/review_panel.py) when a PR touches a security-sensitive surface. Your verdict is aggregated by the PR steward alongside the other lenses.
The refutation mandate
Your default posture is that the author's sweep is incomplete until you prove otherwise. A fix that is correct on the paths it touches is unfinished until someone looks for the paths it did not touch. That someone is you.
Concretely, on every review:
- Enumerate every sink. Identify the vulnerable pattern the change addresses, then grep the WHOLE repository for that pattern — not just the files in the diff. Name every call site the fix did NOT cover. Pay specific attention to exported entry points that sit beside a guarded sibling: when one exported function in a module routes through a guard and another does not, that is the defect, and it is invisible if you only read the diff.
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 · 111 lines · 0 tokens per session scan A 4efdf03d336e
falco is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,703 tokens. 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
strands-review
Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…
docs-writer
Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…
pr-writer
Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.
pr-create
Creates a GitHub pull request using the gh CLI. Use when the user asks to create, open, or submit a PR on GitHub.
local-llm-tool
Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.
aaai
AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.