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 watch-and-repair-prgit 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/watch-and-repair-pr)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/watch-and-repair-pr"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/watch-and-repair-pr/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/watch-and-repair-pr"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/watch-and-repair-pr.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 | $0.00045 | $0.01068 |
| Opus 5 | $0.00023 | $0.00534 |
| Sonnet 5 | $0.00009 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
watch-and-repair-pr 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR review triage
Contract
| Field | Bound contract |
|---|---|
| Trigger | A human explicitly invokes a watcher cycle for an open pull request that must be watched until it is mergeable or blocked. |
| Authority | Remote: pushes commits to the candidate pull request's own branch and may publish a status report; requires explicit human invocation. Preview the exact pull request, candidate branch, proposed commits or status report, and remote consequence before using credentials; proceed only within the invoked cycle. |
| Side effect | May publish a status report and push commits that address bounded review findings only to the candidate pull request's own branch; never merge or force-push. |
| Done | The cycle has re-read checks, review threads, conflicts, and branch protection, then classified the pull request as mergeable, blocked-with-owner, or handed-off. |
Inputs
Required: the open pull request, its repository and candidate branch, access to its complete current checks, review threads, conflict state, and branch-protection state, plus the human's explicit invocation for this cycle. To push a fix or publish a report, also require valid credentials and an exact preview of the remote target and consequence. Optional: a human-supplied bound on findings to address; without one, do not mutate and return a classification from the review tape.
Procedure
- Confirm the pull request is open, identify its own candidate branch, record the human-authorized scope for this cycle, and reject any target that would require another branch, a merge, or a force-push. Done when: PR is confirmed open, candidate branch is identified, and scope is recorded with invalid targets rejected.
- Re-read the full current review tape in the same cycle: all checks, every review thread including resolved threads needed for context, conflict state, and applicable branch-protection requirements. Do not rely on a prior cycle's snapshot. Done when: complete review tape is read in this cycle.
- Classify each obstacle as an actionable review finding, an external wait, a conflict, a protection requirement, or a decision requiring another owner. Bound actionable work to findings supported by the current tape and within the invoked scope; do not widen scope or invent evidence. Done when: every obstacle is classified and actionable work is bounded.
- Before any remote mutation, present the exact pull request and branch, the proposed status report or commits, and the consequence of publishing or pushing. Do not use credentials or mutate the remote unless the human has explicitly authorized that preview. Done when: preview is presented and human authorization is confirmed or withheld.
- For authorized actionable findings, change only what each finding requires, verify the affected observable behavior with the narrowest applicable check, and push the resulting commits only to the candidate pull request's own branch. Never merge and never force-push. Done when: commits are pushed to the candidate branch with verification evidence, or the step has stopped on verification or push failure.
- After any push or newly observed review activity, start a fresh cycle by re-reading the complete review tape rather than carrying forward a partial view. Done when: fresh cycle is started with a complete re-read.
- End the cycle with exactly one terminal classification:
mergeablewhen all required checks and protection conditions pass, no blocking thread or conflict remains, and no required owner action is outstanding;blocked-with-ownerwhen a named obstacle and responsible owner remain; orhanded-offwhen responsibility has been explicitly transferred with the current tape and remaining actions identified. Done when: one terminal classification is emitted.
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.
- 5d ago First seen · 41 lines · 45 tokens per session scan A fd4e25162a9c
watch-and-repair-pr is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,068 once invoked, about $0.0002 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…
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…