agentleFS
conorbronsdonconorbronsdon/agent-context-os/.agents/skills/context-setup/SKILL.md

context-setup

Skill30 starsChanged 37 days agoMITView on GitHub

Build, import, or refresh this workspace's identity, project, reusable-workflow, and weekly-state files through a guided review. Use only when the user explicitly asks to initialize or redo workspace context.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. jyjeanne/dita-skills★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository14 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When the host executes commands inside Bash, replace the bash executable shown below with "$BASH" to reuse that shell.

    line 12
  2. Very specific:

    Use the exact roots supplied by the host attachment: KernelRoot is the trusted Context OS product containing scripts/contextos.sh.

    line 17
  3. Distinctive:

    Do not search upward or infer a root from cwd or the skill installation.

    line 26
  4. Distinctive:

    Ask questions one at a time and inspect existing files before proposing changes.

    line 43
  5. Distinctive:

    Never request or store credentials or ingest a raw account export into tracked context.

    line 46
  6. Very specific:

    Ask whether to start from answers, selected existing material, or both.

    line 60
  7. Distinctive:

    Run exactly one of these forms:

    line 88
  8. Very specific:

    Do not run a ContextRoot-relative product validator from WorkingRoot.

    line 114

≈ “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

Set up workspace context

Execution roots (required)

When the host executes commands inside Bash, replace the bash executable shown below with "$BASH" to reuse that shell. This avoids selecting a different Bash from PATH, such as the Windows WSL launcher inside a Git Bash session. In a terminal outside Bash, select the installed Bash explicitly.

Use the exact roots supplied by the host attachment: KernelRoot is the trusted Context OS product containing scripts/contextos.sh; ContextRoot owns tracked identity and lifecycle state; and WorkingRoot is the ordinary application. For an external attachment, require all three exact absolute paths and run:

bash <KernelRoot>/scripts/contextos.sh --context-root <ContextRoot> --working-root <WorkingRoot> <command>

Do not search upward or infer a root from cwd or the skill installation. The kernel must validate the ignored local binding before strict lifecycle work. A missing, moved, stale, linked, nested, or mismatched binding stops the workflow; use the explicit project rebind proposal after a legitimate move. ContextRoot owns all lifecycle writes. WorkingRoot is read-only evidence. The colocated bash scripts/contextos.sh <command> compatibility form remains valid.

Throughout this procedure, resolve every context path beneath ContextRoot. In split mode, spell local paths as absolute <ContextRoot>/... paths and invoke every lifecycle command through the absolute KernelRoot wrapper with both exact role options. In colocated mode, run the relative compatibility commands from the colocated root, where ContextRoot and WorkingRoot are the same directory.

Build useful context without silently overwriting user data.

Guardrails

  • Ask questions one at a time and inspect existing files before proposing changes.
  • Preserve the user's wording; do not embellish credentials, goals, or biography.
  • Require approval before replacing populated files, broad writes, commits, or pushes.
  • Never request or store credentials or ingest a raw account export into tracked context.

Procedure

1. Confirm storage and audience

Explain that tracked identity, project, state, session, and imported context is visible to repository collaborators and configured agents. Deleting it later does not erase git history. Recommend local-only or private storage by default; a public remote requires deliberately sanitized content. Stop before collecting personal information unless the user explicitly confirms the audience.

2. Choose and inspect the starting point

Ask whether to start from answers, selected existing material, or both. For existing material, follow <KernelRoot>/docs/migration-guide.md and accept only a reviewed, narrow packet. Read the existing identity, project index, current state, weekly priorities, and routing files beneath ContextRoot. Classify each as missing, placeholder, or populated. Do not read similarly named files from WorkingRoot as shared context.

3. Gather reviewed context

One question at a time, gather identity, current focus, relevant background, three-month goals, working preferences, optional useful personal context, verifiable proof points, and approved public links. Then gather one recurring project: purpose, audience, current focus, non-goals, prior decisions, and repeated workflows. Finally gather weekly outcomes, non-goals, success criteria, and blockers. Draft the smallest coherent file map and routing additions.

Portable repeated workflows belong under <ContextRoot>/.agents/skills/; facts stay in their ContextRoot identity, project, or state source and are referenced rather than copied.

4. Propose and apply deterministically

Encode the reviewed file map as JSON under <ContextRoot>/.context-os/inputs/, with files mapping ContextRoot-relative paths to complete desired content. Add a path to replace_populated only after explicit approval to replace that populated file. Use {{TODAY}} where the deterministic local date belongs.

Run exactly one of these forms:

split:     bash <KernelRoot>/scripts/contextos.sh --context-root <ContextRoot> --working-root <WorkingRoot> propose setup --input <ContextRoot>/.context-os/inputs/<payload.json>
colocated: bash scripts/contextos.sh propose setup --input .context-os/inputs/<payload.json>

Present every returned diff and its proposal digest. The digest binds the exact content but does not authenticate a human approver; rely on the host permission boundary. After explicit approval of that exact proposal, run the matching form:

split:     bash <KernelRoot>/scripts/contextos.sh --context-root <ContextRoot> --working-root <WorkingRoot> apply <ContextRoot>/<proposal> --confirm <digest> --runtime <active-runtime>
colocated: bash scripts/contextos.sh apply <proposal> --confirm <digest> --runtime <active-runtime>

The kernel must refuse path escapes, writes outside context paths, unapproved populated replacements, changed targets, or concurrent applies.

Validate with the matching mode:

split:     bash <KernelRoot>/scripts/contextos.sh --context-root <ContextRoot> --working-root <WorkingRoot> doctor
colocated: bash scripts/validate-all.sh --workspace

Do not run a ContextRoot-relative product validator from WorkingRoot. Report the receipt and result, and offer a ContextRoot commit only after final diff review. Suggest $start next and $end to close.

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.