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 agentmods add skills/jeanfbrito/rocket-cli/rocket-catchupnpx skills add jeanfbrito/rocket-cli --skill rocket-catchupgit clone --depth 1 https://github.com/jeanfbrito/rocket-cliWhat 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 | $0.00120 | $0.00898 |
| Opus 5 | $0.00060 | $0.00449 |
| Sonnet 5 | $0.00024 | $0.00180 |
| Haiku 4.5 | $0.00012 | $0.00090 |
Grade A, and why
rocket-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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rocket-catchup
Recap a single named room or thread. Bounded read, honest about how far back the cache reaches.
Transport
- Prefer MCP tools when connected:
list_rooms,get_messages,list_threads,get_thread_messages,sync_history. - Otherwise shell out:
rocket-cli rooms --json,rocket-cli messages <room> --json,rocket-cli threads <room> --json,rocket-cli thread <id> --json,rocket-cli sync [room]. - Multi-server:
--profile <name>(CLI) orROCKET_CLI_PROFILE(MCP env).
Workflow
- Resolve the room. If the user named it precisely (
#general,@alice, an id), pass it straight toget_messages— itsroomarg accepts id,#channel,@username, name, or display name. If the name is fuzzy or ambiguous, calllist_roomswithfilter(andtype=channel/group/dm) first and confirm the match. - Read the window. Call
get_messages(params:room,count1-100 default 30,before/afterISO-8601 for paging,includeSystemdefault false). Newest-first. The response is an envelope withroom,syncedThrough,coverage, and possiblyrefreshing: true. - State coverage honestly. Summarize only what
syncedThrough/coverageactually span. Never imply you've read the whole channel's history if the cache only reaches back e.g. 30 messages / a few hours. Ifrefreshing: true, note the data may be seconds stale. - Go deeper only on demand. Use
sync_historyONLY when the user explicitly asks beyond the cached window ("the last month", "since last Tuesday"). Params:room(omit = most stale unread room — but here always pass the room),depth(1-5000, additional older messages). After it completes, re-read withget_messagesusingbefore/after. Never callsync_historyambiently to "be thorough". - Handle threads when the content is thread-shaped. Thread parents in
get_messagescarry areplyCount— those are conversations, not one-offs.- For a broad room recap with active discussions:
list_threads(params:room,count1-100 default 25,textfilter) to enumerate active threads, thenget_thread_messages(params:threadId,count1-200 default 50) on the ones worth summarizing. - If the user pointed at a thread specifically ("summarize this thread"), go straight to
get_thread_messageswith its parent id (a pasted message link also works asthreadId).
- For a broad room recap with active discussions:
- Summarize with permalinks. Group by topic/thread. For each key point, include the permalink to the anchoring message so the user can jump straight in. Call out decisions, open questions, and anything that names or pings the user.
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 · 33 lines · 120 tokens per session scan A c044db0140cf
rocket-catchup is a skill published in the GitHub repository jeanfbrito/rocket-cli (2 stars, last pushed 15d ago), licensed MIT. It adds 120 tokens to every session and 898 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…