mantis-researcher

mantis-researcher is a skill for Claude Code, Codex from google/mantis. It costs 57 tokens per session (6,057 once invoked), scanned A, original, Apache-2.0.

A security code auditor that reviews selected production files according to an existing review plan. It looks for missing boundary checks, required conditions, unsafe input handling, and broken interface expectations.

In plain words
What is it for?
Use it after a review plan and source snapshot exist to perform triage and detailed analysis of selected files. It is for discovering and documenting issues, not planning the review or applying patches.
Why use it?
It focuses a code review on planned targets and specific failure patterns, helping uncover problems that a general reading may miss. It records the review against the pinned code snapshot.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/google/mantis/mantis-researcher
Any agent
npx skills add google/mantis --skill mantis-researcher
Clone the repo
git clone --depth 1 https://github.com/google/mantis

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mantis-researcher

README.md
[![agentmods](https://agentmods.dev/badge/skills/google/mantis/mantis-researcher.svg)](https://agentmods.dev/skills/google/mantis/mantis-researcher)
Your own site
<a href="https://agentmods.dev/skills/google/mantis/mantis-researcher"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,057 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.06057
Opus 5 $0.00028 $0.03028
Sonnet 5 $0.00011 $0.01211
Haiku 4.5 $0.00006 $0.00606

Measured 4d ago against content hash 3f8203e26347, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mantis-researcher 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 4d 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.

mantis-researcher/SKILL.md · 430 lines

How it starts

The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mantis Researcher (/mantis-researcher)

System Goal

Resilience Code Auditor. Performs rapid triage and deep-dive reviews of source files to identify boundary checks, preconditions, missing sanitization, and interface violations.

Command Definition

  • Command: /mantis-researcher
  • Description: Audits production source code files based on the strategy in workspace/plan.json.
  • Arguments (optional; supplied by the orchestrator, consumed by Block A):
    • --snapshot_root / SNAPSHOT_ROOT: absolute path to the pinned, read-only code snapshot for this pass. This is the CODE_ROOT that all snapshot-relative path fields resolve against (Block A step 1b).
    • --snapshot_id / SNAPSHOT_ID: the pass snapshot identifier. Used for the sentinel check (Block A step 2) and stamped verbatim into every finding's discovery_commit.
    • --state_root: absolute path to the workspace/ state directory (plan.json, .mantis_state.json, findings/, kb/). State paths are STATE-RELATIVE and are NEVER prefixed with CODE_ROOT (Block A step 3).
    • --target_root (authoritative override, Block A step 1a) is also honored if supplied.
    • All flags absent -> DEGRADED/legacy mode: CODE_ROOT falls back to the current directory, snapshot_pinned is treated as false, and behavior matches today's exactly (no discovery_commit is written).

Input/Output Contract

  • Reads:
    • workspace/plan.json (falls back to codebase sweep if missing/empty).
    • workspace/.mantis_state.json (to track current loop pass).
    • referenced Markdown files in "kb_references" (e.g. workspace/kb/entities/*.md).
    • Target source code files.
    • workspace/kb/structural_index/manifest.json (to check structural index availability/status).
    • workspace/helpers/query_structural_index.py (to invoke bounded structural-index queries).
  • Writes:
    • Raw finding files to workspace/findings/<uuid>.json (creates workspace/findings/ if missing).
  • Preconditions:
    • Target files must be accessible.
  • Idempotency Guarantee:
    • Writes new findings as separate files with unique UUIDs. Rely on mantis-dedupe to cluster and merge duplicate findings on subsequent steps.

Read the full file on GitHub · 430 lines

Changes

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.

  1. 4d ago First seen · 430 lines · 57 tokens per session scan A 3f8203e26347

Subscribe to this mod's changes

mantis-researcher is a skill published in the GitHub repository google/mantis (905 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 6,057 once invoked, about $0.0003 per session on Opus 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.