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-criticWrote 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-critic)<a href="https://agentmods.dev/skills/google/mantis/mantis-critic"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-critic/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-critic"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-critic.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 | $0.00055 | $0.04416 |
| Opus 5.5 | $0.00022 | $0.01766 |
| Sonnet 5.5 | $0.00011 | $0.00883 |
| Haiku 4.5 | $0.00006 | $0.00442 |
Grade A, and why
mantis-critic 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critic (/mantis-critic)
System Goal
Production Viability Expert. Filters validated security findings to confirm if they remain triggerable in standard release and production configurations.
Command Definition
- Command:
/mantis-critic [--target_root=<path>] [--snapshot_root=<path>] [--snapshot_id=<id>] [--state_root=<path>] - Description: Assesses the production viability of findings, filtering out debug-only features and assertion traps.
- Parameters:
--target_root: AUTHORITATIVE path to the target codebase root. Overrides all other locator sources and is sentinel-exempt (Block A path 1a). Defaults to unset.--snapshot_root: Path to the pinned, immutable snapshot copy for this pass (a.k.a.SNAPSHOT_ROOT). Used as CODE_ROOT when--target_rootis unset (Block A path 1b).--snapshot_id: TheSNAPSHOT_IDthe orchestrator computed for this pass. Used for the Block A sentinel check and for the per-finding Block B drift comparison in Step 3. If omitted, fall back toactive_snapshot.snapshot_idfrom state.--state_root: Path to the root of the Mantis state directory containingworkspace/(defaults to.). Everyworkspace/...path in this file is resolved relative to--state_root; with the default.this is identical to today'sworkspace/.
Input/Output Contract
- Reads:
workspace/findings/(loads all findings regardless of status; also reads each finding's optionaldiscovery_commitfor the per-finding snapshot match check).workspace/kb/THREAT_MODEL.md(if exists, to check deployment intent and the KB's recordedkb_snapshot_id).workspace/.mantis_state.json(to track current loop pass and to readactive_snapshot.{root,snapshot_id,snapshot_pinned}for locator resolution and provenance).- Target source code files under the resolved CODE_ROOT (the pinned snapshot
root when
snapshot_pinned), at paths/lines incode_pathswith contextual offset.
- Writes:
- Updates findings in-place (sets
"production_viability","critic_reasoning", and appends history). - Appends to
workspace/learnings.jsonl.
- Updates findings in-place (sets
- Preconditions:
- Findings must exist in
workspace/findings/.
- Findings must exist in
- Idempotency Guarantee:
- Overwrites viability fields in place. It must check if a critic entry for
the current pass is already recorded in the history array, and check
workspace/learnings.jsonlto ensure it does not write duplicate records if run again on the same input.
- Overwrites viability fields in place. It must check if a critic entry for
the current pass is already recorded in the history array, and check
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 · 326 lines · 55 tokens per session scan A 7ac57e4e1bb7
mantis-critic is a skill published in the GitHub repository google/mantis (2,459 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 4,416 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
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
resolve-handoff
Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.
resolve-publish
Commit the validated fix and follow local-only, workflow-owned, or direct PR publication.
code-task
PREFERRED way to change code in a REAL repository: fix a GitHub issue, fix a bug, add/implement a function or feature, or make any edit to a project the user names by a filesystem path (e.g. /tmp/foo, /code/bar) or a git URL. Clones the repo, runs an OpenSquilla agent on the host to make the change on a task branch…
resolve-inputs
Select the Resolve mode, recover its input, check the workspace, and discover existing fixes.
implementer
Delegate a coding task to Google's Antigravity CLI (agy staffer, fast Gemini), which edits the working tree directly and can perform explicitly requested Git delivery. Use when the user says /agy:implementer, "have agy fix/build X", or wants to hand a well-scoped coding task to the agy staffer instead of doing it in…