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 catchupgit 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/catchup)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/catchup"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/catchup.svg" alt="Measured on agentmods" 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 | $0.01682 |
| Opus 5 | $0.00023 | $0.00841 |
| Sonnet 5 | $0.00009 | $0.00336 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
catchup 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 yesterday.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catchup
Contract
| Field | Bound contract |
|---|---|
| Trigger | The human returns after a gap, says they can't follow the project, asks what happened or what a term means, faces a decision with a stale mental model, or asks for a visual recap page of the project. |
| Authority | Reversible local: mode visual writes only the recap page under <project-root>/diagrams/; mode briefing writes nothing; rollback is deleting the written file. No remote mutation. |
| Side effect | Mode briefing: none; it briefs, it does not act. Mode visual: writes the 8-section recap page to the diagrams directory and opens it. |
| Done | Mode briefing: a cold-read of the briefing requires no pre-gap memory or unglossed coined term to parse; needs-you items are each actionable without opening another file; every claim has a checkable source; it fits on a screen with expansion offered rather than delivered. Mode visual: a returning developer can rebuild the mental model from the page, and next steps derive only from evidence. |
Inputs
- Mode:
briefing(default) orvisual. - The project working directory or project root path, inferred from the current repository when not supplied. Required for mode visual.
- The human's last touch point (their last message, judgment, or commit) for mode briefing; inferred from session history or the most recent commit when not supplied.
- Branch name for mode visual. Optional; defaults to the current VCS branch or HEAD.
Procedure
Mode briefing (default):
- Read only live state: recent file mtimes, git log and diffs, plan and state docs, task boards, and re0-memo notes. Never brief from conversation memory alone; that memory may have drifted. Done when: live state is read from the project, not from conversation memory.
- Anchor on the human's last touch (their last message, judgment, or commit). Everything after that point is the delta; everything before it is assumed known and stays out. Done when: the last touch point is identified and the delta boundary is set.
- Compose in decision order, not chronological order:
- Needs you: decisions, judgments, or inputs only the human can give, each self-contained enough to act on without opening another file.
- Changed while you were away: outcomes, not process. Prefer "The plan's scoring rule was replaced" to "I ran three analysis passes."
- New words: every term coined or repurposed since their last touch, one line each, with where it lives. Skip terms they already used themselves. Done when: the three sections are composed in decision order.
- Gloss on first use: any project-specific term appearing in the briefing gets an inline plain-language aside at its first occurrence, even if a glossary section follows. Done when: every project-specific term is glossed at first use.
- Keep the default short (a screen or less). End with drill-down offers per section, not with everything expanded. Done when: the briefing fits on a screen with drill-down offers, not full expansion.
- Cold-read the briefing for pre-gap memory dependence or unglossed coined terms; confirm each needs-you item is actionable without opening another file; confirm every claim has a checkable source (file, commit, or artifact path). Done when: the cold-read passes with no pre-gap memory dependence, no unglossed terms, actionable needs-you items, and sourced claims.
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.
- yesterday First seen · 74 lines · 45 tokens per session scan A 084c3089030a
catchup is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 1,682 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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…