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 strike-the-rootgit 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/strike-the-root)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/strike-the-root"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/strike-the-root/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/strike-the-root"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/strike-the-root.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 | $0.00052 | $0.02237 |
| Opus 5 | $0.00026 | $0.01118 |
| Sonnet 5 | $0.00010 | $0.00447 |
| Haiku 4.5 | $0.00005 | $0.00224 |
Grade A, and why
strike-the-root 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strike the root
Find the core and make it not break next time. Grill the real core and solve it from first principles, not the outskirts. Be sharp and work for the longer horizon.
A bug is evidence about the design that produced it. When the design is wrong, blocking symptoms is unlimited treadmill work: the same fault keeps spawning new bugs no matter how many are fixed. Sharp means acting on evidence in the code, never on speculation. Long horizon means the repair is still right in six months, under the next feature, with the next maintainer.
Contract
| Field | Bound contract |
|---|---|
| Trigger | A bug, failure, flake, regression, slowness, review finding, or ticket needs root-shape repair, not the nearest patch. |
| Authority | Reversible local: writes only named local artifacts (an evidence ledger, tagged instrumentation, the fix, and a regression test); rollback is undo (revert those local writes). No remote mutation. |
| Side effect | A confirmed root cause, a root-shape fix, a passing regression test, and a clean tree with all instrumentation removed. |
| Done | The fault class named at the core can no longer produce the reported bug family; the full project check set passes with no monkey patch, shim, special-cased input, or suppressed symptom left in the diff; every review comment on the touched surface carries an explicit verdict. |
Refusals
- No symptom patches. A conditional that special-cases the reported input, a wrapper that catches the fault downstream, or a config flag that hides it all leave the design fault in place. Remove the fault instead.
- No suppression. No
@ts-ignore,# type: ignore,// eslint-disable, ignore flags, or deleted tests to silence errors. - No special-casing inputs. The repair removes the fault class, not the reported instance.
- No outskirts work. Renames, formatting, and comment edits around a bug change nothing. Spend the effort where the failure lives.
- No speculative redesign. The wide view informs the repair; it does not license rewriting subsystems the fault does not touch.
- No patch without a reproduced root cause. When the input is a ticket, reproduction and root-cause analysis precede any fix. An unstructured fix that skips reproduction is refused.
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.
- 2d ago First seen · 68 lines · 52 tokens per session scan A 87ac2aab2d14
strike-the-root is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 2,237 once invoked, about $0.0003 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.
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…