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 agentmods add skills/blacktop/alf/skillsnpx skills add blacktop/alf --skill skillsgit clone --depth 1 https://github.com/blacktop/alfWrote 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/blacktop/alf/skills)<a href="https://agentmods.dev/skills/blacktop/alf/skills"><img src="https://agentmods.dev/badge/skills/blacktop/alf/skills.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00177 | $0.03537 |
| Opus 5 | $0.00088 | $0.01768 |
| Sonnet 5 | $0.00035 | $0.00707 |
| Haiku 4.5 | $0.00018 | $0.00354 |
Grade A, and why
alf 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- alf — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
alf — Agentic LLDB Fuzzer
alf lets an AI agent drive LLDB over MCP to analyze crashes, fuzz targets, and debug kernels. Target: Apple Mach-O, arm64(e). Agent-first design: every capability is an MCP tool call.
Choose the entry point by goal
| Goal | Entry point |
|---|---|
| Post-mortem analysis of a single crash | Crash triage |
| LLM-driven fuzzing campaign | Fuzzing |
| Kernel / remote-stub debugging (VZ, QEMU, KDP) | Kernel debugging |
| Let an agent freely explore a live target | Interactive exploration |
| Plug alf into Claude Code / Codex / Gemini CLI | ACP integration |
When in doubt: alf server --transport stdio exposes every capability as MCP tools. Everything else is a higher-level orchestrator around that same tool surface.
Before anything else, verify the host is configured: uv run alf doctor. A failing lldb_launch check almost always means macOS Developer Mode is off — see Gotchas.
Crash triage
Use when: the user has a binary and a crashing input (from libFuzzer, AFL++, Jackalope, etc.) and wants to understand the root cause, classify it, and/or generate a minimized/expanded corpus.
Three levels, pick by how much autonomy the agent should have:
| Level | Command | When |
|---|---|---|
| Fully scripted pipeline | uv run alf analyze --pipeline --binary <bin> --crash <input> |
Same output every run; good for CI |
| LLM-in-the-loop director | uv run alf director --binary <bin> --crash <input> --mode auto |
Need the agent to pick which commands to run |
| Raw MCP surface | alf server + lldb_launch → lldb_crash_context → ... |
Building a custom workflow, or an outer agent already orchestrates |
Sub-commands (alf analyze <subcommand>):
triage— capture backtrace, registers, disassembly →logs/*.jsonclassify— heuristic exploitability + LLM bucketingreport— render a markdown RCA from a triage JSONminimize— shrink a crash input while preserving the stack hashcorpus— synthesize new seeds from a crash (add--llmfor LLM-guided)
What ships with it
8 files 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.
- 5d ago First seen · 219 lines · 177 tokens per session scan A ab6dcd05ea76
alf is a skill published in the GitHub repository blacktop/alf (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 177 tokens to every session and 3,537 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
memory-audit
记忆审计入口。当我主动决定审视记忆质量时，先读此文件判断应使用哪个子技能。.
memory-audit-discoverability
可发现性审计。当disclosure写法有问题、parent放错、alias缺失、子节点过多时使用。.
memory-audit-pattern-extraction
模式提取与失效解药分析。当发现多条记忆在讲同一个教训，或发现自己在一而再再而三地犯同样的错误时使用。.
quantum-ground-state
求解并科学验收用户提供的二量子位实 Pauli Hamiltonian 在固定 hamming-weight=1 扇区内的无噪 statevector VQE 基态。用于给定 Hamiltonian 的扇区基态、VQE 收敛与精确参考比较；不用于从分子几何生成 Hamiltonian、QAOA、shots、噪声、真实量子硬件或多于二量子位的问题。.
qmclaw-workbench
使用 OpenQuantum 的 QMClaw Local Tool 对超导量子比特 S21、能谱、Rabi、Ramsey、T1、SingleShot、DRAG、π 脉冲、功率偏移、Delta 和 RB 等 13 类测控实验做有界、确定性的本地模拟，并组织单比特调校工作流。用于实验规划、接口联调、教学和无硬件预检；不连接 LabRAD/lqms、真实仪器或量子云，不修改校准参数，也不替代 Scientific Validator。.
tyxonq-workbench
使用 OpenQuantum 通过 Harness MCP Client 注册的 TyxonQ Tool 构建并运行有界量子电路，比较无噪声 statevector 与 density-matrix 噪声采样结果。用于 TyxonQ 电路验证、Bell/GHZ 等小规模态制备、采样分布和退极化/振幅阻尼/相位阻尼/Pauli 噪声分析；不用于真实量子硬件、云任务、任意 Python 执行或替代独立科学 Validator。.