google/mantis is a modular set of security-review skills that coding agents use to find, reproduce, and patch software vulnerabilities. It is for adapting automated security testing to application, infrastructure, machine-learning, hardware, and firmware projects, with expert review required for results. The catalogue skills and instruction provide the workflow for using Mantis with coding agents.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/google/mantisnpx agentmods add skills/google/mantis/mantis-threat-modelWrote 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/google/mantis/mantis-threat-model)<a href="https://agentmods.dev/skills/google/mantis/mantis-threat-model"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-threat-model/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/google/mantis/mantis-threat-model"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-threat-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00059 | $0.03281 |
| Opus 5.5 | $0.00024 | $0.01312 |
| Sonnet 5.5 | $0.00012 | $0.00656 |
| Haiku 4.5 | $0.00006 | $0.00328 |
Grade A, and why
mantis-threat-model 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 1mo 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Modeler (/mantis-threat-model)
System Goal
Security Architect. Synthesizes trust boundaries, attack surfaces, and attacker
profiles into THREAT_MODEL.md based exclusively on the entities and
architecture defined in the Knowledge Base (KB).
Command Definition
- Command:
/mantis-threat-model - Description: Evaluates architectural perimeters, entry points, and trust boundaries to construct the threat model.
- Arguments (all optional; absent → today's behavior):
--state_root <dir>: parent ofworkspace/. If absent, use./workspace/...relative to the current directory. Locates.mantis_state.json, the KB, and the archive directory.--snapshot_id <id>: theSNAPSHOT_IDthis pass is pinned to. Used ONLY as the provenance value stamped intoTHREAT_MODEL.md(theKB_SNAPSHOT:line). If absent, fall back toactive_snapshot.snapshot_idfrom state; if that is also absent orsnapshot_pinnedis false, the stamp is the literalUNPINNED.--snapshot_root <dir>: accepted for interface uniformity but NOT used — this stage never reads target source (Block A step 0, findings-only role).
Input/Output Contract
- Reads:
workspace/.mantis_state.json—pass_number(to archive per pass) and, for provenance only,active_snapshot({root, snapshot_id, snapshot_pinned}). Both optional; absent → degraded (see Backward-compat).workspace/kb/architecture.md.workspace/kb/entities/*.md.- The EXISTING
workspace/kb/THREAT_MODEL.mdfrom the previous pass, if present — only its firstKB_SNAPSHOT:line, for the freshness check in step 0.
- Writes:
workspace/kb/THREAT_MODEL.md(first line is aKB_SNAPSHOT:provenance header).- Archives the previous
workspace/kb/THREAT_MODEL.md(if any) toworkspace/archive/kb/THREAT_MODEL_pass_${N}.mdBEFORE overwriting.
- Preconditions:
- Knowledge Base files must exist and be populated.
- Idempotency Guarantee:
- Copies the prior
THREAT_MODEL.md(if any) to the pass archive, then deterministically overwritesworkspace/kb/THREAT_MODEL.mdin-place. Re-running a pass with an unchanged snapshot reproduces an equivalent model plus aSTALEbanner (see step 0 and the final save step).
- Copies the prior
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.
- 1mo ago First seen · 252 lines · 59 tokens per session scan A ced15d440489
mantis-threat-model is a skill published in the GitHub repository google/mantis (2,459 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 3,281 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
pinecone-research
Agent RAG and long-term memory with Pinecone.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
stripe-directory
Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill for ANY request…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.