open-brain-server: Skill for Claude Code

.claude/skills/discover/SKILL.md

discover is a skill for Claude Code from Bobby-cell-commits/open-brain-server. It costs 137 tokens per session (4,812 once invoked), scanned A, original, MIT.

An incremental research workflow for recent thoughts stored in Open Brain, a connected collection of personal notes or ideas. It compares new thoughts with earlier groups, checks them against priorities in TRACKER.md, and can start further research.

In plain words
What is it for?
Reviewing recent thoughts, grouping related ideas, identifying new or outdated topics, checking priorities, and launching deeper research when needed.
Why use it?
It helps find what has changed since the last review without repeatedly processing all stored thoughts.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is Bobby-cell-commits/open-brain-server's own configuration. It tells Claude Code how to work on open-brain-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-brain-server configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 SCRIPTS_DIR/adaptive_tracks.py pre-cluster \.

Reuse

Borrowing it

Nothing to install: this file belongs to Bobby-cell-commits/open-brain-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Bobby-cell-commits/open-brain-server/master/.claude/skills/discover/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Bobby-cell-commits/open-brain-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for discover

README.md
[![agentmods](https://agentmods.dev/badge/skills/bobby-cell-commits/open-brain-server/discover.svg)](https://agentmods.dev/skills/bobby-cell-commits/open-brain-server/discover)
Your own site
<a href="https://agentmods.dev/skills/bobby-cell-commits/open-brain-server/discover"><img src="https://agentmods.dev/badge/skills/bobby-cell-commits/open-brain-server/discover.svg" alt="Measured on agentmods" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00137 $0.04812
Opus 5 $0.00068 $0.02406
Sonnet 5 $0.00027 $0.00962
Haiku 4.5 $0.00014 $0.00481

Measured 6d ago against content hash dba725000591, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

discover scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/parse_thoughts.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/discover/SKILL.md · 488 lines

How it starts

The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Brain Discovery (Incremental)

Analyze recent Open Brain thoughts incrementally — building on the previous report, informed by TRACKER.md priorities, with tiered light/full runs.

Prerequisites

Open Brain MCP tools must be available: list_thoughts, search_thoughts, thought_stats, analyze, get_connections. Verify before proceeding.

Scripts (in the skill's scripts/ directory):

  • adaptive_tracks.py — centroid math, pre-clustering, lifecycle, state I/O
  • weak_signal_score.py — OpenRouter-based weak-signal scoring
  • parse_thoughts.py — existing thought parser

Environment variables (required for adaptive tracking):

  • SUPABASE_URL, SUPABASE_SERVICE_ROLE_KEY — for embedding fetch
  • BRAIN_ID — the brain UUID (read from MCP auth context or .env)
  • OPENROUTER_API_KEY — for weak-signal scoring

Load these from the project's pipeline/.env and openbrain/.env.local before calling scripts:

source pipeline/.env 2>/dev/null; source openbrain/.env.local 2>/dev/null

Arguments

Parse from user message:

  • days: Time window — bypasses incremental mode. Legacy fallback for one-off deep dives. Example: /discover last 7 days
  • full: Force full run regardless of delta. Example: /discover full
  • light: Force light pass regardless of delta. Example: /discover light
  • copy: Extra save location. Example: /discover copy to ~/Documents
  • focus: Narrow to specific topics. Example: /discover focus on AI agents
  • --tracker: Path to tracker file. Example: /discover --tracker STATUS.md
  • --no-tracker: Skip TRACKER sync entirely. Example: /discover --no-tracker

days=N and incremental mode are mutually exclusive. If days is provided, operate in legacy mode (no state file read, no previous report continuity). State file is still written on completion so the next run can resume incremental mode.

Workflow

Phase 0: Read State

Four inputs to read (in parallel where possible):

  1. State file: Read DISCOVERIES_DIR/.discover-state.json.
    • If found: extract all fields. If it contains tracks array with centroid_b64 fields, this is the enhanced format — adaptive tracking is active.
    • If found but only has legacy fields (last_run, last_report, thoughts_processed, run_type, tracker_hash): this is a legacy state file. Adaptive tracking will bootstrap on this run.
    • If not found: first run.

Read the full file on GitHub · 488 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 488 lines · 137 tokens per session scan A dba725000591

Subscribe to this mod's changes

discover is a skill published in the GitHub repository Bobby-cell-commits/open-brain-server (8 stars, last pushed 4mo ago), licensed MIT. It adds 137 tokens to every session and 4,812 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens