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/simota/agent-skills/breachnpx skills add simota/agent-skills --skill breachgit clone --depth 1 https://github.com/simota/agent-skillsWrote 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/simota/agent-skills/breach)<a href="https://agentmods.dev/skills/simota/agent-skills/breach"><img src="https://agentmods.dev/badge/skills/simota/agent-skills/breach.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 | $0.00044 | $0.05174 |
| Opus 5 | $0.00022 | $0.02587 |
| Sonnet 5 | $0.00009 | $0.01035 |
| Haiku 4.5 | $0.00004 | $0.00517 |
Grade C, and why
breach scanned grade C with 1 finding 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- CAPABILITIES_SUMMARY: - threat_modeling: Design threat models using STRIDE, PASTA, Attack Trees, and MITRE ATT&CK mapping - attack_scenario_design: Create structured attack scenarios with kill chains and exploitatio Copies of this mod
1 near-identical copy found in the catalogue:
- breach — 97% identical, 13 lines differ
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breach
Red team engineering agent that thinks like an attacker. Designs attack scenarios, builds threat models, and validates security controls through adversarial simulation. Covers traditional application security, infrastructure, and AI/LLM-specific attack vectors.
"Defenders think in lists. Attackers think in graphs. Breach maps the graph."
What ships with it
11 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.
- _common 10 B
- reference/_common 13 B
- reference/ai-red-teaming.md 14 KB
- reference/attack-playbooks.md 6.0 KB
- reference/autorun-schema.md 1.1 KB
- reference/handoffs.md 3.5 KB
- reference/phishing-campaign-design.md 7.8 KB
- reference/recipes-index.md 2.1 KB
- reference/social-engineering-design.md 9.4 KB
- reference/supply-chain-attack-design.md 11 KB
- reference/threat-modeling.md 9.6 KB
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.
- 5d ago First seen · 310 lines · 44 tokens per session scan C 79de6966ce8f
breach is a skill published in the GitHub repository simota/agent-skills (75 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 5,174 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
beevibe-team-mesh-negotiation
Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…
project-init
Scaffold an unconfigured directory into a configured pi project. Interactive, profile-driven: previews the planned writes, then writes AGENTS.md, .pi/settings.json and prompt files — optionally also a knowledge base, an openspec/ scaffold, and user-global /.pi/agent/settings.json. Use on a bare directory, or when the…
suede-aso
Suede-owned app-store optimization discipline for keyword fields, titles, subtitles, descriptions, screenshots, ratings context, and competitor listing audits. Use when improving App Store or Google Play visibility or listing conversion from a live app URL and current console evidence. NOT FOR: building or releasing…
suede-copy
Suede Labs conversion-copy writer: landing sections, email, microcopy, buttons, headlines, CTAs, variants, and anti-slop edits. Use when asked to write or rewrite conversion copy for one surface in one pass — a hero, a button set, an email subject, a README section, a product blurb — or when copy on a single surface…
copywriting
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value…