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 post-merge-cleanupgit 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/post-merge-cleanup)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/post-merge-cleanup"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/post-merge-cleanup/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/post-merge-cleanup"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/post-merge-cleanup.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 | $0.00048 | $0.01168 |
| Opus 5 | $0.00024 | $0.00584 |
| Sonnet 5 | $0.00010 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
post-merge-cleanup 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post-merge cleanup
Contract
| Field | Bound contract |
|---|---|
| Trigger | A merge, release, or completed change has landed and its cleanup surface must be reconciled. |
| Authority | Human-gated: previews and gets authorization before creating remote PRs or tickets for out-of-budget or escalated items; otherwise reversible local: writes only source files in a worktree; rollback is version control. No remote mutation without the gate. States the rollback path before any mutation. |
| Side effect | Reconciles stale TODOs, deprecation notices, feature flags, and documentation gaps. Makes bounded safe fixes or files tracked tickets with ownership assigned. |
| Done | Each follow-up is either completed with focused verification or recorded as a ticket with an owner assigned or explicitly tracked. No unrelated refactor was smuggled in. |
Inputs
- Merge reference (required): merge commit SHA, merged PR number, or release tag that just landed.
- Working branch (optional): a named branch to stage proposed fixes. Defaults to
cleanup/<merge-sha>. - Size budget (optional): maximum files and lines changed. Defaults to 5 files and 100 lines total. A single unified budget applies to every candidate.
- State file (optional): a
post-merge-state.mdtracking completed, pending, and deferred items. Created on first run if absent, updated on subsequent runs.
Procedure
- Resolve the merge reference and scan the diff for cleanup candidates. Fetch the diff of the landed commit or PR. Confirm it merges into the tracked branch (main, trunk, or equivalent). Reject if the reference does not resolve or is not on the tracked branch. Collect candidates across every surface: stale TODO/FIXME/XXX comments with or without linked tickets; deprecation notices satisfied by the diff;
// remove after <date>or// TODO: remove after <event>comments fulfilled by the merge; unused feature flags defined in the diff but not referenced downstream; documentation gaps where doc comments, README entries, or API examples are inconsistent with the landed diff; changelog entries now stale or redundant. Done when: the merge reference resolves and all cleanup candidates are collected. - Filter noise and classify candidates by the single unified size budget. Reject commits authored by
dependabot,renovate, or any automated dependency bot. Reject items in denylisted paths (auth/,payments/, and any path touching a public API contract). Flag items referenced in a sibling or child repository for escalation rather than acting on them. Reject candidates with fewer than 3 lines of diff context unless they carry a linked ticket. Classify each remaining candidate as within-budget (touches no more than 5 files, changes no more than 100 lines total, does not alter behavior except explicit dead-code removal) or out-of-budget. Done when: noise is filtered, escalations are flagged, and each candidate is classified. - Apply safe, in-budget fixes in a worktree and verify with tests. For each within-budget candidate: create a named worktree from the tracked branch, apply the minimal fix, and run the project's existing test suite. Revert immediately if any test fails and reclassify the item as deferred. Do not open a single cleanup PR touching more than 10 files without human approval. Done when: every in-budget candidate has a verified fix or is reverted and deferred.
- File tickets for out-of-budget or escalated items with ownership assigned. For each out-of-budget item, large change, or flagged escalation: create a ticket with the merge SHA, affected path, candidate class, and an owner. If no owner can be determined, assign the ticket to the merge author or the team owning the affected path, and mark ownership as
auto-assignedso it is explicitly tracked rather than unset. Done when: every out-of-budget or escalated item has a ticket with ownership assigned or explicitly tracked. - Update the state file and summarize. Record each item as
completed,deferred, orticket-createdin the state file. Prune entries older than 14 days. Write a report summarizing the merge reference, candidates found, candidates acted on with worktree or PR link, candidates deferred with reason, and tickets created with owner. Done when: the state file is updated and the report is written.
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 · 45 lines · 48 tokens per session scan A 4819922a5c9f
post-merge-cleanup is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,168 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…