oss-fuzz

oss-fuzz is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 43 tokens per session (1,764 once invoked), scanned A, original, Apache-2.0.

A guide for adding an open-source project to OSS-Fuzz, Google's service for finding bugs in open-source software by repeatedly testing it with generated inputs. It also covers running that workflow locally and reproducing a reported issue.

In plain words
What is it for?
Use it to prepare OSS-Fuzz project files, build the Docker image, compile fuzzers, run local fuzzing, or reproduce an OSS-Fuzz report.
Why use it?
It provides a defined local process for building the project's test image, compiling fuzzers with memory-error checks, and running a named test harness.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run --no-project python infra/helper.py build_image --pull "$project_name".

Part of the odin-fuzzing plugin — 12 skills shipped together

Good fit Use it to prepare OSS-Fuzz project files, build the Docker image, compile fuzzers, run local fuzzing, or reproduce an OSS-Fuzz report.

Compare 6 skills from other repositories ↓
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/OutlineDriven/odin-claude-plugin
agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/oss-fuzz

Made for: Claude Code, Codex.

Or install odin-fuzzing, the plugin that ships this one along with the rest of its 12 skills.

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 oss-fuzz

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/oss-fuzz/github.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/oss-fuzz)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/oss-fuzz"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/oss-fuzz/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 oss-fuzz

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/oss-fuzz"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/oss-fuzz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,764 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
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00043 $0.01764
Opus 5 $0.00022 $0.00882
Sonnet 5 $0.00009 $0.00353
Haiku 4.5 $0.00004 $0.00176

Measured 3d ago against content hash bce426b1065f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

oss-fuzz 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 3d 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.

plugins/odin-fuzzing/skills/oss-fuzz/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OSS-Fuzz

Contract

Field Bound contract
Trigger User needs to enroll an open-source project in OSS-Fuzz, run its helper workflow locally, or reproduce an OSS-Fuzz report.
Authority Reversible local: writes only named local artifacts (oss-fuzz clone, Docker images, project enrollment files); rollback is docker rmi for images and filesystem deletion for the clone. No remote mutation.
Side effect OSS-Fuzz project integration files, Docker image builds, and local fuzzing campaign artifacts written to the oss-fuzz working directory.
Done Task A: the project Docker image builds, fuzzers compile with AddressSanitizer, and the named harness executes. Task B: projects/<project_name>/project.yaml, Dockerfile, and build.sh are present and structurally valid.

Inputs

Input Required Description
project_name Required OSS-Fuzz project identifier (slug used in infra/helper.py commands and the projects/ subdirectory).
harness_name Required for local run Fuzzer executable name inside the project's build output directory.
language Required for enrollment Project language (e.g. c++, python, rust, go).
main_repo Required for enrollment URL of the project's primary source repository.
sanitizer Optional Sanitizer for build_fuzzers: address (default), undefined, coverage.
fuzzer_args Optional Extra arguments passed through to the fuzzer binary.
oss_fuzz_dir Optional Local path of the cloned oss-fuzz repository; defaults to ./oss-fuzz.
primary_contact Required for enrollment Maintainer email for project.yaml.

Procedure

Task A: run an enrolled project locally

  1. Verify docker is available and the user has permission to run containers (docker info exits 0). Done when: docker info exits 0.
  2. Clone oss-fuzz if oss_fuzz_dir does not exist or is not a git repository:
    oss_fuzz_dir="${oss_fuzz_dir:-./oss-fuzz}"
    git clone https://github.com/google/oss-fuzz "$oss_fuzz_dir"
    
    Done when: the oss-fuzz repository is cloned and present at oss_fuzz_dir.
  3. Change to the oss-fuzz directory:
    oss_fuzz_dir="${oss_fuzz_dir:-./oss-fuzz}"
    cd "$oss_fuzz_dir"
    
    Done when: the working directory is the oss-fuzz directory.
  4. Build the project Docker image:
    project_name="${project_name:?project_name is required}"
    uv run --no-project python infra/helper.py build_image --pull "$project_name"
    
    If build_image reports the project directory does not exist under projects/, stop and return enrollment-missing. Done when: the project Docker image builds successfully or enrollment-missing is returned.
  5. Build the fuzzers with AddressSanitizer:
    project_name="${project_name:?project_name is required}"
    sanitizer="${sanitizer:-address}"
    uv run --no-project python infra/helper.py build_fuzzers --sanitizer="$sanitizer" "$project_name"
    
    Capture stdout/stderr. If the build exits non-zero, return build-failed with the captured output. Done when: fuzzers compile with the configured sanitizer and stdout/stderr are captured.
  6. Run the named harness:
    project_name="${project_name:?project_name is required}"
    harness_name="${harness_name:?harness_name is required}"
    fuzzer_args="${fuzzer_args:-}"
    uv run --no-project python infra/helper.py run_fuzzer "$project_name" "$harness_name" ${fuzzer_args:+"$fuzzer_args"}
    
    Observe for at least 10 seconds. If the harness exits with a sanitizer report, return crash-detected with the report path. Otherwise return harness-ran. Done when: the harness runs for at least 10 seconds and returns harness-ran or crash-detected.

Read the full file on GitHub · 113 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 113 lines · 43 tokens per session scan A bce426b1065f

Subscribe to this mod's changes

oss-fuzz is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,764 once invoked, about $0.0002 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 2026-09-06.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens