mcpbeat

Agentlas Auto Activation

agentlas-ai/agentlas-auto-activation

Use when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .agentlas memory and sitemap files.

559 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1165
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/agentlas-ai/Agentlas-OS --skill agentlas-auto-activation

The instruction itself

5 sections, as written by the author

Agentlas Auto-Activation

Use this skill when a local runtime should activate Agentlas project continuity

for a folder.

Procedure

  • For explicit activation, call hephaestus project ensure --project <folder>

from Agentlas Core.

  • For automatic activation, require a trusted writable host, an allowed root,

a workspace marker, and host-side opt-in. Passive search, read-only work,

and MCP requests do not imply write consent.

  • Never create project state in the user's home directory, filesystem root, or

outside the host's allowed project roots.

  • Install the managed privacy .gitignore block before local memory/indexes.
  • Add missing seed files, ontology/career indexes, and the bounded code map

without overwriting existing user content.

  • Inject relevant project memory into future agent prompts.
  • Ask workers to emit ## Memory Events only for durable facts.
  • Route Memory Events through Memory Tickets and Memory Curator.
  • Use sitemap/task-bias state to avoid stale or unvalidated surfaces.

Minimum Files

  • .agentlas/project-soul-memory.md
  • .agentlas/sitemap.json
  • .agentlas/memory-map.json
  • .agentlas/memory-tickets.jsonl
  • .agentlas/vault-references.json
  • .agentlas/skill-registry.json
  • .agentlas/skill-trials.jsonl
  • .agentlas/curator-decisions.jsonl
  • .agentlas/activation.json
  • .agentlas/code-map/project-map.json
  • .agentlas/ontology-runtime.json
  • .agentlas/ontology-runtime.sqlite
  • .agentlas/career-graph.json
  • .agentlas/career-graph.sqlite

Safety

Never store secrets, raw logs, full transcripts, cookies, private keys, service

accounts, or payment material in .agentlas.

Keep MCP auto-bootstrap disabled unless the host separately opts in. Automatic

receipts must not expose absolute project paths or raw filesystem errors.

If private files were already tracked before activation, report them as

trackedSensitivePaths; never mutate the user's Git index automatically.

Reference

See docs/agentlas-auto-activation.md.

How to use it

Copy the folder

Take agentlas-ai/agentlas-auto-activation from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.