coherence-sweep

coherence-sweep is a skill for Claude Code, Codex from Abilityai/cornelius. It costs 31 tokens per session (595 once invoked), scanned A, original, MIT.

A consistency check for a linked knowledge base, where notes are connected by dependencies. It finds outdated notes, changes in their status, and structural problems, then creates a report.

In plain words
What is it for?
Use it to review the health of an indexed knowledge base, find stale notes, track lifecycle changes, and identify structural issues.
Why use it?
It helps reveal notes that may no longer match related information. This reduces the need to inspect a large collection of notes by hand.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/abilityai/cornelius/coherence-sweep
Any agent
npx skills add Abilityai/cornelius --skill coherence-sweep
Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius

Made for: Claude Code, Codex.

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 coherence-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/abilityai/cornelius/coherence-sweep.svg)](https://agentmods.dev/skills/abilityai/cornelius/coherence-sweep)
Your own site
<a href="https://agentmods.dev/skills/abilityai/cornelius/coherence-sweep"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/coherence-sweep.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 595 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00595
Opus 5 $0.00015 $0.00298
Sonnet 5 $0.00006 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 5d ago against content hash 6c5a8706fb3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coherence-sweep 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 5d ago.

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/coherence-sweep/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brain Coherence Sweep

Run a full coherence analysis of the knowledge base using the Brain Dependency Graph engine. Identifies stale notes, lifecycle transitions, structural issues, and optionally productive tensions.

State Dependencies

Source Location Read Write Description
LBS Graph resources/local-brain-search/data/brain_graph.pkl NetworkX graph
Enrichments resources/brain-graph/data/graph_enrichments.json Node/edge enrichments
Reports resources/brain-graph/reports/ Generated reports

Prerequisites

  • Brain Dependency Graph must be bootstrapped (run_brain_graph.sh bootstrap)
  • Local Brain Search index must exist

Process

Step 1: Check bootstrap status

cd $PROJECT_ROOT/resources/brain-graph
../local-brain-search/venv/bin/python cli.py status

If not bootstrapped, run bootstrap first:

../local-brain-search/venv/bin/python cli.py bootstrap

Step 2: Run coherence sweep

Default (7-day lookback, lifecycle included, no tensions):

../local-brain-search/venv/bin/python cli.py coherence

With options:

# Include tension detection (slower)
../local-brain-search/venv/bin/python cli.py coherence --tensions

# Custom lookback period
../local-brain-search/venv/bin/python cli.py coherence --days 14

# JSON output
../local-brain-search/venv/bin/python cli.py coherence --json

Step 3: Present results

Read the generated report and present key findings to the user:

  1. Staleness alerts - Notes that need review due to upstream changes
  2. Lifecycle transitions - Notes crossing phase boundaries (reflective -> crystallizing -> generative)
  3. Structural health - Orphans, overloaded hubs, missing MOCs
  4. Tensions (if enabled) - Productive contradictions for synthesis

Report is saved to: resources/brain-graph/reports/coherence-report-YYYY-MM-DD.md

Output Format

Present a concise summary with:

  • Count of stale notes with top 5 most affected
  • Notable lifecycle transitions (especially new generative notes)
  • Structural issues requiring attention
  • Path to full report

Read the full file on GitHub · 78 lines

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. 5d ago First seen · 78 lines · 31 tokens per session scan A 6c5a8706fb3d

Subscribe to this mod's changes

coherence-sweep is a skill published in the GitHub repository Abilityai/cornelius (105 stars, last pushed 11d ago), licensed MIT. It adds 31 tokens to every session and 595 once invoked, about $0.0002 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 2026-08-30.

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

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 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