agentleFS
Sign inStart free
ARCASSystemsARCASSystems/FounderOS/skills/context-persistence/SKILL.md

context-persistence

Skill7 starsChanged 19 days agoMITView on GitHub

Pull what we already know about a topic before re-explaining. Say "what do we know about <topic>", "give me the prior context", or "remind me where we left off". Fires at session start, after a gap, or when the founder references prior context. Prevents the agent from stating facts without source paths.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 14 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈14

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If a fact already exists in the OS, find it before asking.

    line 14
  2. Distinctive:

    Read only what the task needs, in this order:

    line 25
  3. Distinctive:

    Do not load every file by default.

    line 36
  4. Distinctive:

    Search recent and canonical sources.

    line 41
  5. Distinctive:

    If one match is clear, answer with the source path.

    line 42
  6. Distinctive:

    If two or three matches are plausible, offer the best candidates and ask the user to pick.

    line 43
  7. Distinctive:

    If no match is found, say where you looked and ask one narrow question.

    line 44
  8. Distinctive:

    If the user corrects a stored fact, update the right file only after approval.

    line 45
  9. Distinctive:

    If current user input conflicts with a file:

    line 65
  10. Distinctive:

    Treat the current user statement as the freshest signal.

    line 67
  11. Distinctive:

    Ask before editing canonical files.

    line 69
  12. Distinctive:

    Do not ask "can you remind me" before searching.

    line 74
  13. Distinctive:

    Do not cite memory without a file path when the fact affects action.

    line 75
  14. Distinctive:

    Do not summarize the whole prior session unless the user asks.

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Context Persistence

Runs on: reasoning - reads your files and reasons; any capable agent can run this.

If a fact already exists in the OS, find it before asking. If you cannot find it, say where you looked and what is missing.

When To Run

  • New session start.
  • The founder says "as I mentioned", "like last time", "the thing from yesterday", or similar.
  • The agent is about to ask a question whose answer may live in the files.
  • The agent is about to state a founder-specific, client-specific, or company-specific fact.

Source Order

Read only what the task needs, in this order:

  1. CLAUDE.md - boot rules and live file map.
  2. core/identity.md - founder profile.
  3. context/priorities.md - current focus.
  4. context/decisions.md - open and resolved decisions.
  5. context/clients.md - prospect and client state.
  6. cadence/daily-anchors.md and cadence/weekly-commitments.md - current time-bound work.
  7. brain/log.md, brain/flags.md, brain/patterns.md, and brain/knowledge/ when history or patterns matter.
  8. stack.json when tool behavior matters.

Do not load every file by default. Load the smallest set that can answer the question with source support.

Procedure

  1. Parse the user's reference.
  2. Search recent and canonical sources.
  3. If one match is clear, answer with the source path.
  4. If two or three matches are plausible, offer the best candidates and ask the user to pick.
  5. If no match is found, say where you looked and ask one narrow question.
  6. If the user corrects a stored fact, update the right file only after approval.

Output Pattern

I found the reference: <specific thing>.
Source: <file path or heading>
Answer: <action or context>

If not found:

I could not find that in <files searched>.
Missing: <specific fact>
Question: <one narrow question>

Drift Handling

If current user input conflicts with a file:

  1. Treat the current user statement as the freshest signal.
  2. Name the file that may be stale.
  3. Ask before editing canonical files.
  4. Log material corrections to brain/log.md.

Rules

  • Do not ask "can you remind me" before searching.
  • Do not cite memory without a file path when the fact affects action.
  • Do not summarize the whole prior session unless the user asks.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free