mantis-critic

A security-review step that checks whether reported findings still work in normal production builds, where debug assertions are disabled.

In plain words
What is it for?
Use it after findings have been validated to check their production viability before treating them as release-relevant security issues.
Why use it?
It filters out issues that only appear during debugging or depend on assertions that production does not use.

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

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,416 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 $0.00055 $0.04416
Opus 5 $0.00028 $0.02208
Sonnet 5 $0.00011 $0.00883
Haiku 4.5 $0.00006 $0.00442

Measured 2d ago against content hash 7ac57e4e1bb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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-critic/SKILL.md · 326 lines

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_root is unset (Block A path 1b).
    • --snapshot_id: The SNAPSHOT_ID the 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 to active_snapshot.snapshot_id from state.
    • --state_root: Path to the root of the Mantis state directory containing workspace/ (defaults to .). Every workspace/... path in this file is resolved relative to --state_root; with the default . this is identical to today's workspace/.

Input/Output Contract

  • Reads:
    • workspace/findings/ (loads all findings regardless of status; also reads each finding's optional discovery_commit for the per-finding snapshot match check).
    • workspace/kb/THREAT_MODEL.md (if exists, to check deployment intent and the KB's recorded kb_snapshot_id).
    • workspace/.mantis_state.json (to track current loop pass and to read active_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 in code_paths with contextual offset.
  • Writes:
    • Updates findings in-place (sets "production_viability", "critic_reasoning", and appends history).
    • Appends to workspace/learnings.jsonl.
  • Preconditions:
    • Findings must exist in workspace/findings/.
  • 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.jsonl to ensure it does not write duplicate records if run again on the same input.

Read the full file on GitHub · 326 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. 2d ago First seen · 326 lines · 55 tokens per session scan A 7ac57e4e1bb7

Subscribe to this mod's changes

mantis-critic is a skill published in the GitHub repository google/mantis (853 stars, last pushed 5d ago), licensed Apache-2.0. It adds 55 tokens to every session and 4,416 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.