Chalk Labs
Need help deploying sum?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/duplonicus-sum
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/sum
What's inside
- Skill name
sum- Description
- End-of-session wrap-up. Writes the project's NOW.md and one LOG.md line so the next session starts from exactly here, and shows a short summary. Use on /sum, and whenever the user is wrapping up, switching machines or agents, running low on context, or asks to "save where we are", even if they never say "sum".
- License
- MIT
- Instructions
- 28 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: templates/NOW.md
Files (1)
- SKILL.md
SKILL.md (first lines)
# /sum Goal: the next session continues from exactly here, without re-reading this conversation and without the user explaining anything twice. The reader is an agent that starts cold, takes every line as fact, and acts on it. ## 1. Update the project's NOW.md The project is the folder this session was started in (its git root). Overwrite its `NOW.md` in place; it is current state, not history. Keep the six sections, and write "none" in an empty one: State · Where things live · Next · Decisions (incl. things decided against) · Open threads (waiting on whom) · Gotchas. If there is no NOW.md yet, start from `templates/NOW.md` in the agent-memory repo, and add `/NOW.md` and `/state/` to `.git/info/exclude`. - **Write what was observed, not what was intended.** "Tests pass" only if you saw them pass this session; otherwise "suite not re-run; last run 14 passed, 1 failed". - **Every open thread says who or what it waits on.** Add `(review by YYYY-MM-DD)` to anything that should not sit forever. - **Decisions not to do something go in Decisions.** They leave no trace anywhere else. - **Anything claimed but not checked says "not verified"** in those words. - **Absolute dates**, never "tomorrow". - **No secrets.** Say where a secret is stored, never its value. ## 2. Append one LOG.md line In the notes folder's `LOG.md` (the session-start brief names it), newest at the bottom: `- YYYY-MM-DD · <agent> · <project> · <what happened, one line> · s:<id8>` `<id8>` is the first 8 characters of this session's id; the brief printed it as the LOG.md tag. Several projects: `api + web`. ## 3. Reply Two to five lines: what was saved where, and anything the user must do before the next session. No sign-off advice.
From duplonicus/agent-memory, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/duplonicus/agent-memory
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from duplonicus
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get sum running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
sum skill. Agent Mart. https://agentmart.dev/skills/duplonicus-sum (last updated 2026-10-24)