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 autobahngit 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/autobahn)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/autobahn"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/autobahn/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/autobahn"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/autobahn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00093 | $0.00557 |
| Opus 5 | $0.00046 | $0.00279 |
| Sonnet 5 | $0.00019 | $0.00111 |
| Haiku 4.5 | $0.00009 | $0.00056 |
Grade A, and why
autobahn 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 9d 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 — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autobahn
Carve guardrail-adjacent scope out of a task, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt.
Method
- Frame. Read the task and inputs. If the user already authorized descoping, proceed. Otherwise propose the carve, make the split explicit, and wait for approval on every gray-zone item. Bright-line exclusions are never negotiable; if the user disputes one, hand its abstract description to a fresh context for re-evaluation and record the appeal either way.
- Carve. Sweep for guardrail-adjacent items. For each, class it bright-line or gray-zone, give one risk-free alternative, and name an archive destination per
../clean-and-true/references/idioms.md. A gray-zone item the user keeps stays in scope and enters the ledger as kept-by-owner. - Guard. Distill the carve into a compact scope-guard block (absolute exclusions, allowed alternatives, authorizing context) and fold it into the carved prompt verbatim. Where the run shares filesystem or memory, tell it not to consult decision logs, notes, or transcript search. Instruct the run to build the safe scope at full strength, without hedging.
- Run. Spawn a fresh, context-clean subagent with only the carved prompt. Route any new risky material back through Carve.
- Verify. Run an adversarial pass over the returned deliverable across five directions and diff an independent re-sweep of the original task against the ledger, capped at one pass.
- Ledger. After the run closes, report the deliverable with a descope ledger per item: class, verdict, reason, safe alternative, archive destination. Write the archive only now, after the window is closed. See
../clean-and-true/references/idioms.mdfor negatives-as-corpus.
Completion
Every guardrail-adjacent item carries a class, a verdict, a safe alternative, and an archive destination. The ledger is visible. The executing subagent saw only the carved prompt and its guard held. No safe work was diluted and no excluded material was elaborated.
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.
- 9d ago First seen · 22 lines · 93 tokens per session scan A 7257776665d7
autobahn is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 93 tokens to every session and 557 once invoked, about $0.0005 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 2026-08-30.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…