Agent skill

Coherence Sweep

by Abilityai in Abilityai/cornelius

Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report

MITAuto-check: notes

Install Coherence Sweep

skills CLI
$ npx skills add Abilityai/cornelius --skill coherence-sweep -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Abilityai/cornelius coherence-sweep --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/coherence-sweep .claude/skills/coherence-sweep && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
coherence-sweep
GitHub stars
109
Token cost
~627 tokens
SKILL.md length
178 words
Files
1
Skills in repo
51
Repo updated
First seen
Licence
MIT

At a glance

Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report

  • Works in 3 steps: Check bootstrap status → Run coherence sweep → Present results
  • SKILL.md covers State Dependencies, Prerequisites, Process and Output Format
  • Calls python

What it does

Coherence Sweep is an agent skill from Abilityai/cornelius. Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report

Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: AI-powered second brain template for Claude Code + Obsidian. The licence is MIT.

Example prompts

  • “/coherence-sweep”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash, Read, Write

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Check bootstrap status
  2. Run coherence sweep
  3. Present results

What it can do on your machine

Read from SKILL.md and the folder at commit fd5e9a4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Coherence Sweep loads about 627 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 178 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~627

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Abilityai/cornelius at commit fd5e9a4, republished under its MIT licence (© Abilityai). 178 words, ~627 tokens.

Download SKILL.mdSave it as .claude/skills/coherence-sweep/SKILL.md (or your agent's skills folder).
name
coherence-sweep
description
Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report
allowed-tools
Bash, Read, Write
argument-hint
[--days N] [--tensions] [--json]
user-invocable
true
automation
gated

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

SourceLocationReadWriteDescription
LBS Graphresources/local-brain-search/data/brain_graph.pkl✓NetworkX graph
Enrichmentsresources/brain-graph/data/graph_enrichments.json✓✓Node/edge enrichments
Reportsresources/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
bash
cd $PROJECT_ROOT/resources/brain-graph
../local-brain-search/venv/bin/python cli.py status

If not bootstrapped, run bootstrap first:

bash
../local-brain-search/venv/bin/python cli.py bootstrap
Step 2: Run coherence sweep

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

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

With options:

bash
# 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

© Abilityai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/coherence-sweep of Abilityai/cornelius.

Open the folder on GitHubat commit fd5e9a4

Compare with similar skills

Coherence Sweep next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Coherence Sweep compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Coherence Sweep this skillAbilityai/cornelius109—~627Automated safety check: NotesMIT
Dependency Scanningsickn33/agentic-awesome-skills47k1 repos~2.4kAutomated safety check: PassMIT
Dependency Checkruvnet/ruflo74k—~258Automated safety check: PassMIT
Second Brain Graphundefined-ui/second-brain-os1k—~533Automated safety check: PassMIT
Graphagenticnotetaking/arscontexta3.5k1 repos~4.9kAutomated safety check: NotesMIT
Bigquery Graphgoogle/adk-python22k—~4.8kAutomated safety check: PassApache-2.0

Similar skills

  • Dependency Scanning

    sickn33/agentic-awesome-skills

    Scan package dependencies for known vulnerabilities using Snyk, Dependabot, and OWASP Dependency-Check.

    47k GitHub starsUsed in 1 repo~2.4k tokens
    SecurityAuto-check passed
  • Dependency Check

    ruvnet/ruflo

    Scan project dependencies for known vulnerabilities and CVEs.

    74k GitHub stars~258 tokensUpdated today
    SecurityAuto-check passed
  • Second Brain Graph

    undefined-ui/second-brain-os

    Analyse the vault's link graph and report on its shape: orphan rate, average degree, components, hubs, bridges and clusters, with what each number means for retrieval.

    1k GitHub stars~533 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Graph

    agenticnotetaking/arscontexta

    Interactive knowledge graph analysis. An agent skill from agenticnotetaking/arscontexta.

    3.5k GitHub starsUsed in 1 repo~4.9k tokens
    Knowledge ManagementAuto-check: notes
  • Bigquery Graph

    google/adk-python

    Official

    Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph.

    22k GitHub stars~4.8k tokensUpdated today
    DatabasesAuto-check passed
  • Dependency Update

    codewhale-hq/Codewhale

    Read release notes/changelogs, update a defined dependency scope, handle breaking changes, and verify.

    41k GitHub stars~142 tokensUpdated today
    DevelopmentAuto-check passed

More from Abilityai/cornelius

All 51 skills in this repo
  • Nano Banana Image Generator

    Abilityai/cornelius

    Generate images using Google's Nano Banana (Gemini 2.5 Flash Image).

    109 GitHub stars~1.2k tokensUpdated 16 days ago
    Auto-check: notes
  • Changelog Protocol

    Abilityai/cornelius

    Protocol for creating dated changelog files after significant agent sessions.

    109 GitHub stars~555 tokensUpdated 16 days ago
    Auto-check passed
  • Create Article

    Abilityai/cornelius

    Create long-form articles from knowledge base insights. An agent skill from Abilityai/cornelius.

    109 GitHub stars~2.1k tokensUpdated 16 days ago
    Auto-check: notes
  • Epistemic Classification

    Abilityai/cornelius

    Framework for distinguishing research findings from hypotheses and speculative synthesis.

    109 GitHub stars~1.5k tokensUpdated 16 days ago
    Auto-check passed
  • Get Youtube Transcript

    Abilityai/cornelius

    Extract the transcript from a YouTube video by URL or video ID.

    109 GitHub stars~525 tokensUpdated 16 days ago
    Auto-check: notes
  • Insight Capture Format

    Abilityai/cornelius

    Standard format for capturing and documenting insights in the knowledge base.

    109 GitHub stars~616 tokensUpdated 16 days ago
    Auto-check passed

Questions about Coherence Sweep

What does Coherence Sweep do?

Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report. Coherence Sweep is an agent skill from Abilityai/cornelius.

How do I install Coherence Sweep in Claude Code?

Run `npx skills add Abilityai/cornelius --skill coherence-sweep -a claude-code`. Or copy the skill folder (.claude/skills/coherence-sweep in Abilityai/cornelius) into .claude/skills/coherence-sweep in your project. Claude Code loads it when a task matches its description.

How do I install Coherence Sweep in Codex?

Run `npx skills add Abilityai/cornelius --skill coherence-sweep -a codex`. Or copy the skill folder (.claude/skills/coherence-sweep in Abilityai/cornelius) into .agents/skills/coherence-sweep in your project. Codex loads it when a task matches its description.

Can I use Coherence Sweep in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Abilityai/cornelius --skill coherence-sweep -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/coherence-sweep, .gemini/skills/coherence-sweep, .github/skills/coherence-sweep and .opencode/skills/coherence-sweep in your project.

What does Coherence Sweep need to run?

Going by SKILL.md and its folder, Coherence Sweep needs the command-line tools its instructions call (python). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Write.

Does Coherence Sweep access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Coherence Sweep safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Coherence Sweep use?

Coherence Sweep is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Coherence Sweep use?

About 627 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Coherence Sweep?

Skills that share tags, products or a category with Coherence Sweep: Dependency Scanning (sickn33/agentic-awesome-skills, 47k stars), Dependency Check (ruvnet/ruflo, 74k stars), Second Brain Graph (undefined-ui/second-brain-os, 1k stars) and Graph (agenticnotetaking/arscontexta, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Coherence Sweep?

Abilityai (a GitHub organization) maintains it in Abilityai/cornelius, which has 109 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on September 22, 2026.

Source: Abilityai/cornelius on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.