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.
npx skills add OutlineDriven/outline-driven-development --skill aflppgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/aflpp)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/aflpp"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/aflpp/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/outlinedriven/outline-driven-development/aflpp"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/aflpp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 MCP Rug Pull · line 34 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 43 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- low Tool Misuse · line 43 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00076 | $0.02733 |
| Opus 5.5 | $0.00030 | $0.01093 |
| Sonnet 5.5 | $0.00015 | $0.00547 |
| Haiku 4.5 | $0.00008 | $0.00273 |
Grade A, and why
aflpp 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AFL++
Contract
| Field | Bound contract |
|---|---|
| Trigger | User needs AFL++ setup, multi-core campaign operation, corpus handling, or AFL++ crash triage for a C/C++ target. |
| Authority | Reversible local execution of AFL++ binaries and writes to build artifacts, corpora, logs, and output directories under the working directory. The skill must request explicit user approval before any system-level change: package installation, Docker image pull, kernel tuning, GRUB mutation, or reboot. Roll back by killing campaign processes and removing the output and state directories. |
| Side effect | Local writes to compiled artifacts, seed and output corpora, log files, and short-lived Docker containers. No mutation of source under test beyond compilation. |
| Done | AFL++ target runs against a seed corpus with the intended instrumentation and produces interpretable campaign output. |
Inputs
- Target source tree (C/C++) with a fuzz harness or a program that reads stdin, files, or argv. Required.
- Seed corpus directory with at least one non-empty file. Required; created if absent.
- Run location: host or Docker. Required; default Docker.
- Compilation mode preference (LTO, LLVM, or GCC). Optional; default tries LTO, falls back to LLVM.
- Core count for multi-core campaigns. Optional; default is a single instance.
- Dictionary file for format-aware fuzzing. Optional.
- Sanitizer selection (ASan, UBSan, none). Optional; default none.
Procedure
1. Select run location and verify AFL++
Choose host or Docker. For Docker, pull the image with explicit user approval:
docker pull aflplusplus/aflplusplus:stable
For host installation, request approval before running:
apt install afl++ lld-<clang-version>
Verify the binary: afl-fuzz --version (host) or docker run --rm aflplusplus/aflplusplus:stable afl-fuzz --version (Docker).
Kernel tuning (afl-system-config) gives up to 15% more executions per second but disables OS security features. Request explicit approval before running it, and only on a dedicated VM. For maximum performance, afl-persistent-config plus update-grub and reboot are required — these are irreversible system changes that need approval. Do not run kernel tuning on production or development systems.
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.
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 · 185 lines · 76 tokens per session scan A 503d7f49deca
aflpp is a skill published in the GitHub repository OutlineDriven/outline-driven-development (53 stars, last pushed 22d ago), licensed Apache-2.0. It adds 76 tokens to every session and 2,733 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
bounded-model-checking-c
Use when C or C++ code needs memory-safety or undefined-behavior guarantees proved with CBMC, or ACSL contracts checked with Frama-C Eva or WP. Not for choosing the proof policy: use proof-driven.
blink-gc-plugin
Develop, build, test, and roll changes to the Blink GC Clang plugin (//tools/clang/blinkgcplugin). Use when modifying or adding Oilpan/Blink GC Clang plugin checks, running plugin unit tests, checking Chromium/Blink targets for new plugin violations, suppressing violations with GCPLUGINIGNORE, or force-rolling Clang…
loom-c
C language expertise (C11/C17/C23) for memory-safe, portable, production-quality systems code.
tlaplus-spec-generator
Automatically generate TLA+ specifications from source code (C/C++, Python) for formal verification of distributed systems. Use when users need to: (1) Generate TLA+ specs from program implementations, (2) Model distributed systems, consensus protocols, or concurrent algorithms, (3) Extract state variables, actions…
acsl-annotation-assistant
Create ACSL (ANSI/ISO C Specification Language) formal annotations for C/C++ programs. Use this skill when working with formal verification, adding function contracts (requires/ensures), loop invariants, assertions, memory safety annotations, or any ACSL specifications. Supports Frama-C verification and generates…
hashiiiii-zig
Use when writing, editing, or reviewing Zig implementation, tests, build files, or CI.