agentleFS
ScottRBKScottRBK/forgetful/skills/forgetful-entities/SKILL.md

forgetful-entities

Skill341 starsChanged 23 days agoMITView on GitHub

Model the things knowledge attaches to — people, organisations, devices, products, system components. Use when a new thing surfaces that memories will reference, when relationships between things need recording (owns, depends on, part of), or when another skill routes a pointable thing here. Litmus: an entity is a noun you could point at; knowledge about it stays a memory.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Before creating, search_entities for the thing under its likely names — it matches both name and aka.

    line 40
  2. Very specific:

    Check get_entity_relationships on either entity first and reuse the types already in the graph before coining new ones.

    line 67
  3. Very specific:

    When ENTITY_WRITE_PLUGIN is configured, create/update/delete may return plugin_warnings or fail with WRITE_PLUGIN_REJECTED / …

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Modelling entities in Forgetful

Entities are the graph's nouns. Model the thing once, then let knowledge accrue to it through links — that is what makes get_entity_memories a useful reverse lookup later.

Invoking operations

Operations are named by registry name (create_entity, link_entity_to_memory, ...). Invoke via whichever surface this agent has:

  • MCP: execute_forgetful_tool(tool_name="create_entity", arguments={...})
  • CLI: forgetful call create_entity --args '{"name": "..."}' --json

Get any operation's schema at runtime: how_to_use_forgetful_tool (MCP) or forgetful tools info <operation> (CLI) — schemas are deliberately not repeated here.

Step 1 — Apply the litmus, then dedupe

Can you point at it? "Sarah Chen" is an entity; "Sarah is great at debugging async issues" is a memory linked to her. The fact stays a memory (forgetful-remember); the thing it is about becomes the entity.

Before creating, search_entities for the thing under its likely names — it matches both name and aka. Set aka at creation time for any alternative names the thing goes by, so a later dedupe search under a different name still finds it.

Done when: the thing either already exists (use it) or is confirmed new.

Step 2 — Create with a type

create_entity with a name and type: Organization, Individual, Team, Device, System, or Other (custom_type required when Other). Stored Title-case; matched case-insensitively on input. Check list_entities for the types already in use and match them — a graph where servers are sometimes typed "Device" and sometimes "System" fragments reverse lookups.

Done when: the entity exists once, typed consistently with the existing graph.

Step 3 — Link knowledge and projects as they accrue

  • link_entity_to_memory whenever a memory is about the entity — done at capture time, this is one line; done later, it is an archaeology project.
  • link_entity_to_project when the entity belongs to a project's world.

Done when: knowledge about the thing is reachable from the thing (get_entity_memories).

Step 4 — Record relationships between entities

create_entity_relationship with a direction and a type. Keep the vocabulary small and consistent — owns, depends_on, part_of, uses, created_by cover most structure. Check get_entity_relationships on either entity first and reuse the types already in the graph before coining new ones. Direction carries meaning: A depends_on B is a statement about A.

Done when: the relationships that answer real questions (impact, structure, responsibility) are recorded, and none duplicate an existing edge.

Entity Plugin (administrator)

When ENTITY_WRITE_PLUGIN is configured, create/update/delete may return plugin_warnings or fail with WRITE_PLUGIN_REJECTED / WRITE_PLUGIN_UNAVAILABLE before persistence. After-save warnings are advisory; the mutation already succeeded.

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.