Summarize the most recent activity (sessions and memory) into a tight bullet list.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
You are summarizing recent activity for the user.
Use the `list_sessions` tool to fetch the latest 10 sessions. For each session, briefly note channel, last message timestamp, and a one-line summary of the last user message. Then call `recall` with the query "recent activity" and include the top 3 memory hits (compressed).
Output format:
**Recent sessions**
- one bullet per session
**Recent memory**
- one bullet per memory item
User asked: {{input}}
The line at the top of this page pins the label git:20260505.5ee9157, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (576 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
spshulem/openagi · 19 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_m2lshl3asrase7oq
GET https://markdownregistry.com/api/v1/resolve?ref=spshulem/openagi/recap
GET https://markdownregistry.com/api/v1/blob/c2aa19f03783fb663c321e982276cbee3000e58b2a9d17fb665b9604d07b01e1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
spshulem/openagi · .agents/skills/openagi-audit-improve/SKILL.md · Audit a running OpenAGI installation and implement verified generic fixes when the user requests improvements or an…
spshulem/openagi · .agents/skills/openagi-sqlite-test-isolation/SKILL.md · Prevent and diagnose SQLite database locking failures in openAGI tests and store changes.
spshulem/openagi · examples/skills/connect-mcp/SKILL.md · Connect an MCP server (catalog or custom URL/stdio) and make its tools usable — including completing OAuth on a…
spshulem/openagi · examples/skills/deploy-update-node/SKILL.md · Roll out new openAGI code to the main and to Mac nodes (iMessage / computer-use), and restart them safely.
spshulem/openagi · examples/skills/diagnose-no-imessage-replies/SKILL.md · Troubleshoot why the agent stopped replying to iMessages, in priority order.
spshulem/openagi · examples/skills/drive-computer-use/SKILL.md · Operate a connected computer-use node to accomplish an on-screen task — screenshot, reason, act in a loop.
spshulem/openagi · examples/skills/fleet-supervisor/SKILL.md · Keep every Codex, Claude, and Conductor coding thread moving until its PR is truly merge-ready; ping the owner only…
davepoon/buildwithclaude · plugins/cashflow/skills/recap/SKILL.md · Triggered by "monthly recap", "how did I do this month", "spending summary", "financial review", "weekly recap"…
parcha-ai/parcha-skills · recap/skills/recap/SKILL.md · Reconstruct what a Claude Code or Codex agent actually did during one exact session, including goals, decisions…
kurrent-io/kcap-cli · kcap/skills/recap/SKILL.md · This skill should be used to read, search, or recall past kcap sessions. Triggers include: "read a previous session"…
kurrent-io/kcap · kcap/skills/recap/SKILL.md · This skill should be used to read, search, or recall past kcap sessions. Triggers include: "read a previous session"…
mikeprasad/aria-knowledge · plugin-openai-codex/skills/recap/SKILL.md · Read-only orientation: render a scannable What/Where/Status table for this session, the current arc, or recent git…
mikeprasad/aria-knowledge · plugin-antigravity/skills/recap/SKILL.md · Read-only orientation — render a scannable table of what just happened so you can situate yourself. Modes: '/recap'…
