agentleFS
Sign inStart free
Echo-ScionEcho-Scion/orioncortex/.agents/skills/brain-graph/SKILL.md

brain-graph

Skill2 starsChanged 6 days agoMITView on GitHub

Use when ingesting documents into the Brain Graph, querying knowledge nodes, extracting semantic triplets, or checking graph integrity.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 0 are distinctive, and 5 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.

  • 5

    Very specific

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

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

    Run python .agents/scripts/orion.py diagnostics to inspect persisted RAG relevance and faithfulness summaries.

    line 11
  2. Very specific:

    If [TRIPLET_REQUEST] is printed:

    line 30
  3. Very specific:

    Write triplets JSON array to .orion/scratch/triplets.json and inject them into the SQLite graph via python .agents/scripts/orion.py brain …

    line 33
  4. Very specific:

    Typed Relationships: Use page|extends, page|contradicts, page|implements.

    line 43
  5. Very specific:

    Context Pillar Boundary: Never write into context/ without explicit user intent.

    line 46

≈ “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

Skill: Brain Graph Management & Orion Ops (brain-graph)

Retrieval Diagnostics

Run python .agents/scripts/orion.py diagnostics to inspect persisted RAG relevance and faithfulness summaries. Brain sync records one rag_evaluations row for each retrieval.

This skill integrates a structural Brain Graph pattern to give AI a persistent, compounding memory across the entire project. It uses a Smart Vibe Coding (Autonomy Matrix) to balance automation with human oversight.

1. Operations

/orion-ingest <path-or-glob>

Executes python .agents/scripts/orion.py orion_ops ingest <path>. Classifies a raw markdown file, calculates its source_sha256, and updates the .orion/ graph.

Phase 1 (Python / Background):

  1. Diff against the existing .orion/ graph.
  2. Analyze topological dependencies (parent concepts ingested before child concepts).
  3. Evaluate Autonomy Matrix:
    • [NEW], [EXTEND]: Ingests and updates graph indices.
    • [CONTRADICT], [VIOLATION]: Under strict autonomy, halts ingestion; under balanced autonomy, records contradictory relationship in graph.
  4. Outputs [TRIPLET_REQUEST] if successful.

Phase 2 (IDE Agent Delegation): If [TRIPLET_REQUEST] is printed:

  1. The IDE Agent MUST read the content of each ingested file.
  2. Extract 3-5 Subject|Predicate|Object semantic triplets.
  3. Write triplets JSON array to .orion/scratch/triplets.json and inject them into the SQLite graph via python .agents/scripts/orion.py brain inject_triplets .orion/scratch/triplets.json.

/orion-query <node_name>

CRITICAL ACTION: Execute run_command with python .agents/scripts/orion.py orion_ops resolve "<node_name>". Do not use manual grep_search. The resolver automatically injects target file content, forward links, and backlinks into context.

/orion-contradict

Executes python .agents/scripts/orion.py contradict detect and python .agents/scripts/orion.py contradict list to inspect active semantic contradictions, conflicting claims, and source drift across ingested nodes.

2. Harmonization Rules

  • Typed Relationships: Use page|extends, page|contradicts, page|implements. Do not use plain wikilinks.
  • Context Weighting: Assign weight: <1-10> in the frontmatter. High-impact nodes (e.g., core architecture) receive higher weights. orion.py resolve prioritizes high-weight nodes during token eviction.
  • Canon Supremacy: Canons (.agents/canons/) always receive confidence: canonical. Any context that contradicts a canon is a [VIOLATION].
  • Context Pillar Boundary: Never write into context/ without explicit user intent. All orion outputs go to .orion/.

📚 Mandatory Knowledge Routing (JIT References)

If your current task intersects with these domains, you MUST execute view_file on the target BEFORE writing code:

If User Prompt/Task Relates To...Immediately Load (view_file)
Knowledge Extraction / Graph Triplets.agents/skills/brain-graph/references/knowledge-extraction.md

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