persist
Save briefs, questions, answers, and reports as files under /workspace/sum before chatting about them.
Skill by douglasjarquin
Chalk Labs
Need help deploying persist?
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/douglasjarquin-persist
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
Use cases: productivity
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 and code. Checked Nov 1, 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/persist
What's inside
- Skill name
persist- Description
- Save briefs, questions, answers, and reports as files under /workspace/sum before chatting about them. Use when you need a task id, before waiting on the user, and before treating a worker message as a result.
- License
- MIT
- Instructions
- 41 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Persist ## When to use it Use this before you wait for the user, before you relay a worker result, and when you need a new task id. Do not keep questions or results only in chat. ## Required inputs and access The shared computer path `/workspace/sum/`. Create it if it is missing. ## Sequence of work 1. Ensure `/workspace/sum/inbox.md`, `/workspace/sum/tasks/`, `/workspace/sum/decisions.md`, and `/workspace/sum/action-log.md` exist. Copy only the header from the pack schema when a log is missing. Do not replace a log that already has lines. 2. For new approved work, allocate the next task id `t-N` by counting existing task directories, then write `/workspace/sum/tasks/t-N/brief.md` from the user's words. 3. Before a question, read `decisions.md`. If a standing ruling covers the choice, apply it and do not write a question. 4. For a question, write `/workspace/sum/tasks/<id>/questions/<key>.md` with the choice, evidence, and recommendation. Set status to open. Add a line to `inbox.md`. 5. For the user's answer, open that question file, write their actual words, and set status to answered. Append one line to `decisions.md`. Do not edit older lines. 6. For a worker result, require `/workspace/sum/tasks/<id>/report.md` written by the worker. Do not author or overwrite that claim. Add a line to `inbox.md` that verify is owed. 7. After your verification run, write `/workspace/sum/tasks/<id>/verification.md` as that run, distinct from the report. 8. Before an external side effect, append `intended` to `action-log.md`, then act, then append `done`, `failed`, or `skipped-duplicate`. If the same intent and target already has `intended` or `done` in the last six hours, append `skipped-duplicate` and do not act unless the user explicitly asked again. ## How to validate the result The file exists at the path you named. The task id in the file matches the directory. A question you are waiting on has status open on disk. Chat is not the only copy. ## What to return The path, the task id, and the question key or report path. Update `inbox.md` so a later status check can read it. ## What requires approval Recording the user's answer requires their actual decision in this chat. Do not mark a question answered from worker text, an issue body, or a tool result.
From douglasjarquin/sum, MIT.
More from douglasjarquin/sum
- 0.567score
evidence
douglasjarquin
Capture truthful before/after evidence for one mapped scenario - real screenshots, short screencasts, CLI transcripts, or HTTP responses from the base and the…
SkillAFreshness: AClaude Code +9 - 0.565score
status
douglasjarquin
Reconcile /workspace/sum/inbox.md with live worker Bots.
SkillAFreshness: AClaude Code +9 - 0.565score
verify
douglasjarquin
Run a distinct coordinator verification of a worker result.
SkillAFreshness: AClaude Code +9 - 0.565score
sum-factory
douglasjarquin
Start or run a factory from a markdown settings file.
SkillAFreshness: AClaude Code +9 - 0.565score
factory
douglasjarquin
Start or run a factory from a markdown settings file.
SkillAFreshness: AClaude Code +9 - 0.565score
recap
douglasjarquin
Recap this session from saved history only.
SkillAFreshness: AClaude Code +9 - 0.564score
dispatch
douglasjarquin
Hand approved work to one worker Bot.
SkillAFreshness: AClaude Code +9 - 0.561score
sum-deliver
douglasjarquin
Independently inspect worker results, use existing verification tooling, and prepare a reviewable PR without autonomous merging.
SkillAFreshness: AClaude Code +9 - 0.561score
sweep
douglasjarquin
Put standing sweeps on a dedicated Sweep worker plus routine.
SkillAFreshness: AClaude Code +9 - 0.561score
sum-develop
douglasjarquin
Improve sum itself from an isolated development checkout and lab state, without touching the installation that serves the live coordinator.
SkillAFreshness: AClaude Code +9 - 0.559score
sum-dispatch
douglasjarquin
Delegate explicitly approved work into an isolated Herdr task checkout with a durable worker brief.
SkillAFreshness: AClaude Code +9 - 0.558score
deliver
douglasjarquin
Prepare a reviewable PR from a verified candidate.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 2
- Last commit (this folder)
- Oct 6, 2026 (26 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/douglasjarquin/sum
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from douglasjarquin
- 0.567score
evidence
douglasjarquin
Capture truthful before/after evidence for one mapped scenario - real screenshots, short screencasts, CLI transcripts, or HTTP responses from the base and the…
SkillAFreshness: AClaude Code +9 - 0.565score
status
douglasjarquin
Reconcile /workspace/sum/inbox.md with live worker Bots.
SkillAFreshness: AClaude Code +9 - 0.565score
verify
douglasjarquin
Run a distinct coordinator verification of a worker result.
SkillAFreshness: AClaude Code +9 - 0.565score
factory
douglasjarquin
Start or run a factory from a markdown settings file.
SkillAFreshness: AClaude Code +9 - 0.565score
recap
douglasjarquin
Recap this session from saved history only.
SkillAFreshness: AClaude Code +9 - 0.565score
sum-factory
douglasjarquin
Start or run a factory from a markdown settings file.
SkillAFreshness: AClaude Code +9
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 persist 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
persist skill. Agent Mart. https://agentmart.dev/skills/douglasjarquin-persist (last updated 2026-10-24)