Borrowing it
Nothing to install: this file belongs to hlalljie/agent-workflow-presets. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hlalljie/agent-workflow-presets/main/.cursor/skills/catch-me-up/SKILL.mdgit clone --depth 1 https://github.com/hlalljie/agent-workflow-presetsWrote 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/hlalljie/agent-workflow-presets/catch-me-up)<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/catch-me-up"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/catch-me-up/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/hlalljie/agent-workflow-presets/catch-me-up"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/catch-me-up.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00067 | $0.01194 |
| Opus 5.5 | $0.00027 | $0.00478 |
| Sonnet 5.5 | $0.00013 | $0.00239 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
catch-me-up 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 19d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catch me up
When to use
When the user comes back to a project, or opens a new chat, and wants to get back on track: what was done most recently and, if it is clear, where they stopped. Read-only: write no file and run no git command that changes anything (git-safety.mdc).
Only look at what was done recently. Do not look up open issues or PRs to find work. An issue number appears only if a chat or commit names it.
Gather
Chat history is the main source; the rest confirms it. Skip any source that does not exist, without comment. Stop once the picture is clear. This is a recap, not an audit.
-
Recent chats. List the 5 newest transcripts using the folder from the commit skill (chat ID section):
ls -t ~/.cursor/projects/<project>/agent-transcripts/*/*.jsonl | head -5Transcripts are large; never open them whole. Skip the current chat. For each chat, get its asks, one truncated line each (the first is the goal):
jq -r 'select(.role=="user") | .message.content[0].text | gsub("\n";" ") | gsub("</?(timestamp|user_query)>";"") | .[0:140]' <file> | rg -v 'Perform any necessary follow-up'Ignore bare approvals (
y) when reading them. For the newest chat, and any chat that ended without a commit, also read where it stopped, which is the end of the last assistant message:jq -r 'select(.role=="assistant") | .message.content[]? | select(.type=="text") | .text' <file> | tail -n 25Without
jq, userg -o '<user_query>.{0,140}' <file>for asks and the Read tool on the file's last lines. On Windows, use the Glob and Grep tools.A chat whose ID is in no commit's
chat:trailer ended without a commit: exploration or unfinished work. -
Commits and uncommitted work. From the repo root:
git status -sb git log --all -n 10 --date=short --format='%h|%ad|%D|%s|%(trailers:key=chat,valueonly,separator=)'-sbshows uncommitted files and whether the branch is ahead of its remote.--allcatches work on other branches;%Dshows which branch a commit is on. Use thechat:trailer to match each commit to its chat.
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.
- 19d ago First seen · 73 lines · 67 tokens per session scan A 112e2fc7b7d7
catch-me-up is a skill published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 20d ago), licensed MIT. It adds 67 tokens to every session and 1,194 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-10.
Other skills, from other repositories
ctx
Use ctx as working memory for prior agent work. Before starting or continuing work in an unfamiliar area, resuming earlier work, or revisiting an investigation, search prior sessions to ground yourself in earlier context. Use ctx blame to trace a line, file, commit, or PR to the agent session that produced it. Use…
handoff
Save state at the end of a session, or resume from the last one. Triggers "wrapping up", "running out of context", "done for today", "continue where we left off", "resume".
share-learning
Promote a team-relevant learning to the shared team-knowledge repo after deduping against existing notes. Triggers "share this", "add to the knowledge base", or a gotcha, decision, or convention worth team-wide awareness.
session-end
MUST use when user says 'bye', 'goodbye', 'good night', 'gnight', 'done for today', 'that's all', 'that's it', 'see you', 'see ya', 'let's stop', 'stopping here', 'wrapping up', 'signing off', 'closing down', 'done', 'finished for now', 'talk later', 'cya'. The user does NOT use slash commands; detect these natural…
save-session
MUST use when user says 'save', 'save session', or explicitly wants to preserve session state. {USERNAME} does NOT use slash commands; also trigger proactively when significant work has been completed and session context should be persisted. For session endings (bye/done/goodbye), use the session-end skill instead…
memory-manage
Manage Active updates, atomic session handoffs, and human-gated Long-Term proposals. Use when asked to remember something, preserve a decision, log meaningful work, or review memory.