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-reviewWrote 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-review)<a href="https://agentmods.dev/skills/google/mantis/mantis-review"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-review/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-review"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00038 | $0.06345 |
| Opus 5.5 | $0.00015 | $0.02538 |
| Sonnet 5.5 | $0.00008 | $0.01269 |
| Haiku 4.5 | $0.00004 | $0.00634 |
Grade A, and why
mantis-review 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer (/mantis-review)
System Goal
Independent Validator. Reviews consolidated findings against active source code to verify validity and filter out noise and false positives.
Command Definition
- Command:
/mantis-review - Description: Independently reviews findings and filters out false positives.
Input/Output Contract
- Reads:
workspace/findings/(finding JSON files, including each finding's optionaldiscovery_commitprovenance stamp).workspace/.mantis_state.json(current looppass_number; and, when present,active_snapshot={root, snapshot_id, snapshot_pinned}for snapshot provenance).- Invocation args when passed by the orchestrator:
--snapshot_root,--snapshot_id,--state_root(and, rarely,--target_root). - Target source code files at the
code_pathspaths/lines, read under the resolvedCODE_ROOT(the pinned snapshot root — see Instructions Step 0 / Block A), never the live tree when a snapshot is pinned.
- Writes:
- Updates findings on disk in-place (sets
"status","reasoning","repro_hints","triage_checklist", and appends history). - Writes helper script
workspace/helpers/append_review.py.
- Updates findings on disk in-place (sets
- Preconditions:
workspace/findings/exists with finding files.- Target source code files exist.
- Idempotency Guarantee:
- Modifies finding files in-place using the helper script
append_review.py, which MUST carry# MANTIS_HELPER_VERSION = 2as its first line; regenerate the helper if that marker is absent or a different integer (see Instructions step 5). - Idempotency key is (pass_number, snapshot). Before (re)writing a
finding, scan its
historyarray:- SNAPSHOT MODE OFF (neither
--snapshot_idwas passed NOR isactive_snapshotreadable in state): SKIP the review update iff a"stage": "reviewer"entry already exists for the currentpass_number(byte-for-byte today's behavior). - SNAPSHOT MODE ON: SKIP the review update iff a
"stage": "reviewer"entry exists whosepass_numberequals the current pass AND whosesnapshotequalsSNAPSHOT_ID. A reviewer entry that lackssnapshot(legacy) or carries a differentsnapshotcounts as UNKNOWN → RE-REVIEW (do NOT skip), so a finding reviewed under the old skill is re-grounded against the current pinned snapshot.
- SNAPSHOT MODE OFF (neither
- Modifies finding files in-place using the helper script
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 · 438 lines · 38 tokens per session scan A 3c0a274abc31
mantis-review is a skill published in the GitHub repository google/mantis (2,474 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 6,345 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
conductor-review
Reviews the completed track work against guidelines and the plan. Acts as a Principal Software Engineer to ensure quality and compliance.
reviewer
Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /agy:reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent verifier…
refactor-safety
A safety checklist for code refactoring, such as extracting components, merging duplicate logic, renaming variables, or reorganizing structure. Refactoring changes code structure without intending to change its behavior.
cc-refactor-safety
A safety checklist for refactoring, such as extracting components, merging repeated logic, renaming variables, or changing structure.
query-performance-safety
A code-review guide for database access and recursive processing. It applies when code makes queries inside loops, fetches many IDs, uses IN clauses, or nests service calls.
storage-url-safety
A code-review guide for file URLs backed by object storage such as MinIO, OSS, or Amazon S3. Object storage keeps files outside the main application server.