mantis-reproduce

mantis-reproduce is a skill for Claude Code, Codex from google/mantis. It costs 47 tokens per session (11,419 once invoked), scanned A, original, Apache-2.0.

A step that creates and runs a small test program or input to check whether a suspected software crash or security flaw can actually be triggered.

In plain words
What is it for?
Use it to generate crash reproducers, run them in sandboxes, verify findings, and re-test specific findings after a patch.
Why use it?
It replaces an unverified report with evidence from an isolated test environment.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is --state_root if passed, else ./workspace/... relative to the current dir).

Good fit Use it to generate crash reproducers, run them in sandboxes, verify findings, and re-test specific findings after a patch.

Compare 6 skills from other repositories ↓
About the project

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.

google/mantis · 2,525 stars · on GitHub · cloud.google.com

Install

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.

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

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-reproduce

README.md
[![agentmods](https://agentmods.dev/badge/skills/google/mantis/mantis-reproduce/github.svg)](https://agentmods.dev/skills/google/mantis/mantis-reproduce)
Your own site
<a href="https://agentmods.dev/skills/google/mantis/mantis-reproduce"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-reproduce/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.

agentmods 80×15 button for mantis-reproduce

Your own site · 80×15
<a href="https://agentmods.dev/skills/google/mantis/mantis-reproduce"><img src="https://agentmods.dev/badge/skills/google/mantis/mantis-reproduce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,419 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket warn 23 Oct 2026
  • Snyk pass 23 Oct 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 581
    Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.
    Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
How audits are shown
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 5.1 $0.00047 $0.11419
Opus 5.5 $0.00019 $0.04568
Sonnet 5.5 $0.00009 $0.02284
Haiku 4.5 $0.00005 $0.01142

Measured yesterday against content hash 995383801295, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mantis-reproduce 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.

skills/mantis-reproduce/SKILL.md · 829 lines

How it starts

The opening of the file, as written. The whole thing — 829 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reproducer (/mantis-reproduce)

System Goal

Integration Test Engineer. Designs crash reproducers or inputs and executes them inside isolated sandbox environments to empirically verify bugs.

Command Definition

  • Command: /mantis-reproduce [--reattack] [--finding_id=<uuid>] [--force] [--target_root=<path>] [--state_root=<path>] [--snapshot_root=<path>] [--snapshot_id=<SNAPSHOT_ID>] [--snapshot_pinned=<true|false>]
  • Description: Generates and runs crash reproducers to verify security flaws.
  • Parameters:
    • --reattack: When executing as part of patch verification to isolate re-attack outcomes.
    • --finding_id: The specific finding UUID to reproduce. Must be provided and is required when --reattack is specified.
    • --force: Override/bypass eligibility checks for targeted normal runs.
    • --target_root: Path to the root of the target codebase under test (defaults to .). AUTHORITATIVE when supplied — overrides --snapshot_root (Block A step 1a); the sentinel check is skipped for this tree (e.g. a patched shadow during re-attack verification).
    • --state_root: Path to the root of the Mantis state directory containing workspace/ (defaults to .).
    • --snapshot_root: Root of the pinned immutable code snapshot for this pass. Consumed by Block A (Step 0) when --target_root is not supplied.
    • --snapshot_id: The SNAPSHOT_ID string of the pinned snapshot, consumed by Block A (sentinel) and Block B (snapshot match check) in Step 0.
    • --snapshot_pinned: When false (set by mantis-patch during re-attack on a patched shadow), the reproduce sub-agent MUST skip the snapshot sentinel/match check for this invocation — the --target_root tree is authoritative and sentinel-exempt (Block A step 1a).

Input/Output Contract

  • Reads:
    • state_root/workspace/findings/ (viable/conditional findings).
    • target_root/ (Repository source files to analyze trigger paths).
    • state_root/workspace/archive/.repro_attempts.json.
    • state_root/workspace/.mantis_state.json (to track current loop pass).
  • Writes:
    • PoC reproduction files (e.g. poc_[uuid].py or crash_[uuid].payload inside state_root/workspace/reproducers/).
    • If run normally: updates findings in-place under state_root/workspace/findings/ (sets "repro_status", "repro_file_path", "run_command", "repro_output", and appends history). Updates status to "VALID" if provisionally valid.
    • If run with --reattack: updates findings in-place under state_root/workspace/findings/ (sets "reattack_status", "reattack_file_path", "reattack_run_command", "reattack_output", "reattack_variants", and appends history with stage "reattack"). Does not modify "repro_*" fields or "status". Exception: may atomically downgrade patch_status per INV-1 in Step 6 (never persist VERIFIED_SECURE alongside a non-failed_to_bypass reattack_status).
    • Updates state_root/workspace/archive/.repro_attempts.json atomically.
    • Stamps "repro_snapshot_id" / "reattack_snapshot_id" on updated findings and stores .repro_attempts.json values as {count,last_snapshot} objects (bare integers still read correctly).
  • Preconditions:
    • Findings must exist in state_root/workspace/findings/.
    • Sandbox/container runtime environment must be available.
  • Idempotency Guarantee:
    • Updates findings in place. Uses state_root/workspace/archive/.repro_attempts.lock file locking and atomic temporary file swaps (os.replace on state_root/workspace/archive/.repro_attempts.json.tmp) to guarantee concurrency safety and retry stability.
    • Snapshot-aware: regenerates the PoC when the finding's snapshot no longer matches; refuses to emit a negative verdict without reached-sink evidence. Re-attack verdicts on a snapshot mismatch are governed by the C5 unpatched-baseline re-run (Step 6), which supersedes the legacy blanket refusal — a failed_to_bypass verdict is only written after C5 has confirmed the unpatched baseline still triggers on the current snapshot.

Read the full file on GitHub · 829 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. yesterday Changed · +21 lines 995383801295
  2. 1mo ago First seen · 808 lines · 47 tokens per session scan A b5b704b9cbc8

Subscribe to this mod's changes

mantis-reproduce is a skill published in the GitHub repository google/mantis (2,525 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 11,419 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.

Related

Other skills, from other repositories

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.

sickn33/agentic-awesome-skills · 37 tokens

agentic-coding-workflow-expert

Expert guide for AI-assisted coding workflows — agentic code generation, multi-agent code swarms, self-healing CI/CD, automated PR review, spec-to-code pipelines, codebase knowledge graphs, and human-in-the-loop approval gates / Panduan ahli untuk workflow pengkodean berbasis AI — generasi kode agentic, code swarm…

roedyrustam/vibes-plug · 110 tokens

property-mutation-testing-expert

Expert guide for property-based testing (fast-check, Hypothesis) and mutation testing (Stryker, mutmut) — AI-generated test properties, invariant discovery, mutation score optimization, and test suite quality verification / Panduan ahli property-based testing (fast-check, Hypothesis) dan mutation testing (Stryker…

roedyrustam/vibes-plug · 103 tokens

spec-driven-development-expert

Expert guide for Spec-Driven Development (SDD) & Contract-First Architecture — TypeSpec, OpenAPI 3.1, Gherkin BDD, Pact consumer-driven contracts, Spectral linting, and automated spec-to-code pipelines / Panduan ahli pengembangan berbasis spesifikasi (SDD) dan arsitektur contract-first.

roedyrustam/vibes-plug · 76 tokens

accessibility-testing-expert

Expert guide for automated and manual Web Accessibility (a11y) testing — axe-core, Pa11y, Playwright a11y, screen reader testing, and WCAG 2.2 Level AA/AAA compliance / Panduan ahli pengujian aksesibilitas web.

roedyrustam/vibes-plug · 62 tokens

autonomous-tdd-debugger

Empowers the agent to autonomously run tests, read terminal stack traces, and self-heal code until tests pass. Transforms the agent from a passive coder to an active CI pipeline debugger.

roedyrustam/vibes-plug · 46 tokens