Agent skill

Ref Supersede

by Abilityai in Abilityai/cornelius

Handle a validity transition on a reference entity — a contract renewal, role change, or re-termed price where a full prior snapshot matters.

MITAuto-check: notes

Install Ref Supersede

skills CLI
$ npx skills add Abilityai/cornelius --skill ref-supersede -a claude-code

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

GitHub CLI
$ gh skill install Abilityai/cornelius ref-supersede --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/ref-supersede .claude/skills/ref-supersede && 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
ref-supersede
GitHub stars
109
Token cost
~1.2k tokens
SKILL.md length
437 words
Files
1
Skills in repo
56
Repo updated
First seen
Licence
MIT

At a glance

Handle a validity transition on a reference entity — a contract renewal, role change, or re-termed price where a full prior snapshot matters.

  • Works in 4 steps: Identify the transition → Draft both notes + get approval → Write + chain + log → …
  • SKILL.md covers State Dependencies, Process, Verification and This skill must refuse to
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ref Supersede is an agent skill from Abilityai/cornelius. Handle a validity transition on a reference entity — a contract renewal, role change, or re-termed price where a full prior snapshot matters. Creates the new status:active note (with validfrom/validuntil), marks the old note status:superseded + supersededby:[[New]], keeps both for history, and reindexes. Human-gated. Distinct from ref-ingest overwrite (which replaces the body + logs one line); use supersede only when the prior snapshot must be preserved. Company is the default scope.

Its SKILL.md is about 1.2k 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

  • “/ref-supersede”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion

Workflow steps

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

  1. Identify the transition
  2. Draft both notes + get approval
  3. Write + chain + log
  4. Reindex

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:

    • Read
    • Write
    • Edit
    • Bash
    • Glob
    • Grep
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).

    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

Ref Supersede loads about 1.2k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 437 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion

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). 437 words, ~1,167 tokens.

Download SKILL.mdSave it as .claude/skills/ref-supersede/SKILL.md (or your agent's skills folder).
name
ref-supersede
description
Handle a validity transition on a reference entity — a contract renewal, role change, or re-termed price where a full prior snapshot matters. Creates the new status:active note (with valid_from/valid_until), marks the old note status:superseded + superseded_by:[[New]], keeps both for history, and reindexes. Human-gated. Distinct from ref-ingest overwrite (which replaces the body + logs one line); use supersede only when the prior snapshot must be preserved. Company is the default scope.
allowed-tools
Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
automation
gated
user-invocable
true
argument-hint
[scope=Company] <entity or engagement being superseded>
metadata.version
1.0
metadata.created
2026-07-08
metadata.author
Cornelius
metadata.changelog
1.0: Initial version — validity-transition supersede: new active note + old superseded + superseded_by chain, valid_from/until, Change Log both, reindex

Ref Supersede

ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. ref-supersede v1.0 — recent: initial version. Then proceed.

A validity transition with history preserved. Overwrite-in-place (ref-ingest) is right when the latest fact simply replaces the old one. Supersede is right when the old snapshot itself matters — you want to be able to answer "what was the term of the 2026 Acme Corp engagement?" after the 2027 renewal exists. It keeps both notes: old superseded, new active, linked by superseded_by:.

Read first: resources/layered-brains/COMPANY-BRAIN-SCHEMA.md → "Canonical source of truth" (overwrite body vs. supersede-with-snapshot) + "The temporal model"; resources/layered-brains/REFERENCE-SCOPE-SCHEMA.md → "History".

Human-gated in every scope. Even in market/, a supersede (a structural, two-note change) is a human act — the autonomous market path overwrites, it never supersedes (ref-ingest flags such cases here instead).

State Dependencies

SourceLocationReadWriteDescription
Company familyBrain/Company/*/*.md✓✓ (gated)Old + new entity notes
LBS indexresources/local-brain-search/data/✓✓ (reindex)Rebuilt after the write

Process

Step 1 — Identify the transition

Resolve the note being superseded (Grep by name/alias). Confirm it is a validity transition (a term/window closed, a role or price was re-termed) and that a prior snapshot is worth keeping — otherwise this is an overwrite; route to /ref-ingest instead.

Step 2 — Draft both notes + get approval

Present the before/after and get explicit approval (AskUserQuestion) before writing:

  • New note (status: active): the current fact, with valid_from: (and valid_until: if it has a term), fresh as_of/updated, provenance: reference, and the entity's relations. Give it a name that disambiguates the window when needed (e.g. Acme Corp - Trinity Enterprise Build 2027).
  • Old note (status: superseded): add superseded_by: "[[<New note title>]]"; leave its body as the historical snapshot; re-stamp updated only.
Show full SKILL.md (147 more words)Show less
Step 3 — Write + chain + log

Write the new note; edit the old note to status: superseded + the superseded_by: link. Append a ## Change Log line to both:

markdown
## Change Log
- 2026-07-08 — superseded by [[<New>]] on renewal (source: <...>)   # on the old note
- 2026-07-08 — supersedes [[<Old>]]; new term 2027-01 → 2027-12 (source: <...>)   # on the new note
Step 4 — Reindex
bash
cd resources/local-brain-search && ./run_index.sh && ./run_daemon.sh restart   # :7437, RESTART not reload

(No BDG bootstrap — reference notes are BDG-excluded.)

Verification

  • Two notes now exist: the old one status: superseded with a resolving superseded_by:, the new one status: active.
  • /ref-query for the entity returns the new (active) fact by default and can surface the old on "what changed?".
  • Both notes carry a ## Change Log line describing the transition; the old body is intact as the snapshot.
  • /ref-audit reports no status/superseded_by integrity violation for the pair.

This skill must refuse to

  • Write without explicit approval of the specific transition (human-gated in every scope, including market/).
  • Delete or overwrite the old snapshot (supersede keeps it — that is the whole point).
  • Set any provenance but reference, or crystallize/lifecycle-classify/promote a record into a cognitive insight.

© 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/ref-supersede of Abilityai/cornelius.

Open the folder on GitHubat commit fd5e9a4

Compare with similar skills

Ref Supersede 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.

Ref Supersede compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ref Supersede this skillAbilityai/cornelius109—~1.2kAutomated safety check: NotesMIT
Twenty Syncable Entity Validationtwentyhq/twenty58k—~3.3kAutomated safety check: PassCustom licence
Error Handlingaffaan-m/ECC274k1 repos~2.7kAutomated safety check: PassMIT
Python Error Handlingwshobson/agents40k—~1.5kAutomated safety check: PassMIT
Form Validationthedaviddias/Front-End-Checklist74k—~633Automated safety check: PassMIT
Error Handlingthedaviddias/Front-End-Checklist74k—~416Automated safety check: PassMIT

Similar skills

  • Contributor guide for step three of adding a syncable entity to the Twenty server: write the validator, the migration action builder and the orchestrator wiring.

    58k GitHub stars~3.3k tokensUpdated today
    Backend & APIsAuto-check passed
  • Error Handling

    affaan-m/ECC

    Patterns for robust error handling across TypeScript, Python, and Go.

    274k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • Python Error Handling

    wshobson/agents

    Python error handling patterns including input validation, exception hierarchies, and partial failure handling.

    40k GitHub stars~1.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Form Validation

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Validate forms accessibly.

    74k GitHub stars~633 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Error Handling

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Implement proper error handling.

    74k GitHub stars~416 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Error Handling

    affaan-m/ECC

    TypeScript、Python、Goにわたる堅牢なエラー処理のパターン。型付きエラー、エラー境界、リトライ、サーキットブレーカー、ユーザー向けエラーメッセージをカバーします。

    274k GitHub stars~2.4k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

More from Abilityai/cornelius

All 56 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 15 days ago
    Auto-check: notes
  • Changelog Protocol

    Abilityai/cornelius

    Protocol for creating dated changelog files after significant agent sessions.

    109 GitHub stars~555 tokensUpdated 15 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 15 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 15 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 15 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 15 days ago
    Auto-check passed

Questions about Ref Supersede

What does Ref Supersede do?

Handle a validity transition on a reference entity — a contract renewal, role change, or re-termed price where a full prior snapshot matters. Ref Supersede is an agent skill from Abilityai/cornelius. Handle a validity transition on a reference entity — a contract renewal, role change, or re-termed price where a full prior snapshot matters.

How do I install Ref Supersede in Claude Code?

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

How do I install Ref Supersede in Codex?

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

Can I use Ref Supersede 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 ref-supersede -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ref-supersede, .gemini/skills/ref-supersede, .github/skills/ref-supersede and .opencode/skills/ref-supersede in your project.

What does Ref Supersede need to run?

SKILL.md names no scripts, command-line tools or credentials: Ref Supersede is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion.

Does Ref Supersede 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 Ref Supersede 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 Ref Supersede use?

Ref Supersede 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 Ref Supersede use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Ref Supersede?

Skills that share tags, products or a category with Ref Supersede: Twenty Syncable Entity Validation (twentyhq/twenty, 58k stars), Error Handling (affaan-m/ECC, 274k stars), Python Error Handling (wshobson/agents, 40k stars) and Form Validation (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ref Supersede?

Abilityai (a GitHub organization) maintains it in Abilityai/cornelius, which has 109 GitHub stars. The repository holds 56 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.