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 dragthelake/ambient-context --skill ambient-context-catch-me-upgit clone --depth 1 https://github.com/dragthelake/ambient-contextWrote 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/dragthelake/ambient-context/ambient-context-catch-me-up)<a href="https://agentmods.dev/skills/dragthelake/ambient-context/ambient-context-catch-me-up"><img src="https://agentmods.dev/badge/skills/dragthelake/ambient-context/ambient-context-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/dragthelake/ambient-context/ambient-context-catch-me-up"><img src="https://agentmods.dev/badge/skills/dragthelake/ambient-context/ambient-context-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 | $0.00047 | $0.00401 |
| Opus 5 | $0.00023 | $0.00200 |
| Sonnet 5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
ambient-context-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 3d 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.
What it actually says
Catch me up
Follow the ambient-context skill's conventions: narrowest read first, quote little, zero is a normal result.
Steps
- Call
list_daysonce. Note whether today and yesterday have a summary. - Read today's summary with
read_summary. Before 10:00 local time, read yesterday's as well; the morning question is usually about yesterday. - If a day has no summary, read the headings of its record instead:
read_daywithfileset toapps, and treat the##headings as the timeline. Read block bodies only for the last hour before the user stopped. - For anything the summary calls unfinished, open, blocked or waiting, check
read_kbwithfileset tothreads.mdand thencommitments.mdfor the citation, thenread_dayon that time window if the summary is not enough. - If the user names a thing the summary does not mention,
search_recordfor it before saying it is not there.
Reply
Under 200 words unless asked for more, in this order:
- Where you were. The last thing they were doing, with the app and the time.
- Open threads. One line each: what, with whom, what it is waiting on.
- Pick up here. One suggestion, drawn from the record, not invented.
Cite times as the record does (09:14–09:41). Do not list every block of the day.
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.
- 3d ago First seen · 30 lines · 47 tokens per session scan A 1b9dc4ec7e43
ambient-context-catch-me-up is a skill published in the GitHub repository dragthelake/ambient-context (167 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 401 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 2026-09-07.
Other skills, from other repositories
recall-assistant
Proactive context recovery, highlight sharing, and session linking for the recall plugin. Detects context loss, suggests /recall commands, flags findings for connected sessions, and translates natural language into recall operations. Enable with /recall config skillenabled true.
engineer-brain
Your self-updating engineering brain — tracks work patterns, expertise, habits, progress gaps, and generates daily sync-up notes and quarterly review content. Invoke when you say "engineer brain", "update brain", "daily sync", "standup", "sync up", "quarterly connections", "what did I work on", "my progress", "where…
sitrep
Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.
AgentMail
Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. [email protected]).
Apple Notes
Open Notes.app and create or update iCloud notes on macOS using memo when possible and AppleScript when direct app automation is more reliable.
Himalaya Email
Work with IMAP email from the terminal using Himalaya for inbox reads, draft review, and carefully confirmed outbound sends.