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/odin-claude-plugin --skill address-sanitizergit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/odin-claude-plugin/address-sanitizer)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/address-sanitizer"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/address-sanitizer/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/odin-claude-plugin/address-sanitizer"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/address-sanitizer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.01435 |
| Opus 5 | $0.00020 | $0.00718 |
| Sonnet 5 | $0.00008 | $0.00287 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
address-sanitizer 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 6d 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.
This is a copy
95% identical to address-sanitizer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AddressSanitizer
Contract
| Field | Bound contract |
|---|---|
| Trigger | User needs to build or run native code with ASan, interpret an ASan report, or debug a memory-corruption failure. |
| Authority | Reversible local: writes only the instrumented build artifacts and test invocations named by the user; rollback is discarding the instrumented binary and rebuilding without -fsanitize=address. No remote mutation. |
| Side effect | Instrumented native build and test process under the target project directory. |
| Done | When building or running: the target is instrumented, exercised, and any reported memory error is explained with a reproducible location. When interpreting an existing report: the error type, faulting source location, and allocation/deallocation sites are extracted from the report and mapped to a root cause, without requiring a fresh instrumented run. |
Inputs
Required when building or running: the native source or build target to instrument (C/C++ source, Rust crate with unsafe blocks or FFI, or an existing fuzz harness) and the command that exercises it.
Required when interpreting a report: a specific ASan report file or captured ASan output.
Optional: a preferred sanitizer combination, or a fuzzer in use (libFuzzer, AFL++, cargo-fuzz, honggfuzz). When interpreting a report, the build target and exercise command are also optional and used only to confirm the root cause against source.
Procedure
- Determine the invocation mode. If the user supplies an existing ASan report or captured output, take the report-interpretation branch (step 2R) and skip the build-and-run steps (3–9). If the user asks to build or run a target under ASan, take the build-and-run branch (steps 3–9). Done when: the mode is selected.
2R. Report interpretation. Read the supplied ASan report and extract the error type (heap-buffer-overflow, use-after-free, double-free, stack-buffer-overflow, memory leak), the faulting stack trace with source file and line, and the allocation/deallocation traces. If source is available, correlate the faulting and alloc/dealloc frames to the source to state the root cause. Done when: the error type, faulting location, and alloc/dealloc locations are extracted from the report and the root cause is stated. This branch does not require a fresh instrumented run.
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.
- 6d ago First seen · 49 lines · 40 tokens per session scan A 7a5a025c46c0
address-sanitizer is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,435 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to address-sanitizer, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…