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
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 google/mantis --skill mantis-configuregit clone --depth 1 https://github.com/google/mantisWrote 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-configure)<a href="https://agentmods.dev/skills/google/mantis/mantis-configure"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-configure/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-configure"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-configure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00077 | $0.01905 |
| Opus 5.5 | $0.00031 | $0.00762 |
| Sonnet 5.5 | $0.00015 | $0.00381 |
| Haiku 4.5 | $0.00008 | $0.00191 |
Grade A, and why
mantis-configure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Configurator (/mantis-configure)
System Goal
Environment and Model Configurator. Configures workflow.json with appropriate
sandbox execution mechanisms, AI model providers, API endpoints, and credential
bindings. Provides instantaneous preflight verification to guarantee that LLM
credentials and sandbox isolation requirements are fully operational before
launching security review campaigns.
Command Definition
- Command:
/mantis-configure - Description: Configures Mantis pipeline settings (sandboxes, models,
credentials, preflight validation) in
workflow.json. - Execution Command:
python3 "${MANTIS_HOME:-/path/to/mantis}/reference/scripts/configure.py" [flags...]
Path Anchoring Requirement (CRITICAL): The configuration script resides
within the Mantis installation directory at reference/scripts/configure.py.
You MUST invoke this script via an absolute path or via $MANTIS_HOME.
NEVER execute python3 reference/scripts/configure.py using a relative path
inside audited target repositories.
- CLI Options:
--sandbox/-s: Sandbox mechanism (static-only,gvisor,microsandbox,gce).--model/-m: Default LLM model (e.g.gemini-3.8-flash,vertex_ai/claude-opus-5,vertex_ai/zai_org/glm-5.2-maas,openai/{MODEL_ID}).--api-base: Custom endpoint URL for OpenAI-compatible LLM servers (e.g.http://localhost:8000/v1).--reasoning-effort: Reasoning effort level (low,medium,high).--timeout: LLM request timeout in seconds.--project/-p: GCP Project ID (for GCE sandbox or Vertex AI routing).--zone/-z: GCP Zone (e.g.us-central1-b).--image/-i: Sandbox image name (e.g.mantis-sandbox-imageormantis-sandbox:latest).--subnet: GCE Subnet name (e.g.mantis-isolated-subnet).--workdir: Sandbox guest workdir (default:/workspace).--workflow/-w: Path toworkflow.json(defaults to auto-discovery).--db/-d: Path to SQLite knowledge database (default:knowledge.db).--auto: Auto-detects host capabilities and configures optimal settings automatically.--save: Explicitly saves configuration changes toworkflow.local.json.--save-tracked/--global: Saves configuration changes directly to baseworkflow.json.--interactive: Interactive step-by-step terminal wizard.--test/--preflight: Executes fast (1-2s) static validation tests verifying LLM configuration format and sandbox readiness.--probe/--probe-llm: Actively probes LLM reachability, provider credentials, and client dependencies with a minimal test prompt (test, max 256 tokens).--show: Displays current configuration and diagnostic status.--dry-run: Simulates configuration changes without modifying files.--update-nodes: Updates all agent nodes inworkflow.jsonto use the specified default model.--json: Outputs configuration status and preflight diagnostics in JSON.
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.
- yesterday Changed 7f00cd90de45
- 1mo ago Changed · +10 lines 8547c0f1485c
- 1mo ago First seen · 175 lines · 77 tokens per session scan A 16e191ace4eb
mantis-configure is a skill published in the GitHub repository google/mantis (2,454 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 1,905 once invoked, about $0.0003 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
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
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.
jobs
Manage agy staffer background jobs - collect results, check status, cancel, follow-up conversation, and setup. Use when an agy job needs collecting, when the user asks "is the agy job done", "show agy's result", "cancel the agy job", "continue the agy conversation", or "set up agy". This is the orchestrator's skill…
output-dev-eval-testing
Create offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators with verify(), creating dataset YAML files, building eval workflows, or running workflow tests via CLI.
output-dev-scenario-file
Create test scenario JSON files for Output SDK workflows. Use when creating test inputs, documenting expected behaviors, or setting up workflow testing.
output-plan-workflow
Use when the user asks to create, build, generate, scaffold, or plan a new workflow. Orchestrates the full planning process including architecture, steps, prompts, evaluators, and testing strategy using specialized subagents.