Skip to main content
skill CX Codex

supersede — Claude Code skill: what it does, how to install

The supersede Claude Code skill replaces outdated vault-note entries while retaining their history. The agent uses it for requests to update a note or mark a claim as no longer true.

MIT ★ 26 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add wrg32786/aigent-os --skill supersede -a claude-code
Open on GitHub

What supersede does

The skill reads a complete note, strikes through the outdated entry, then adds a dated replacement with an OpenChronicle ID. It does not silently overwrite the earlier text. When an old entry explains why a decision was made, the skill keeps that rationale in a historical-context callout.

It ends with a ledger of notes changed, entries replaced, and material preserved with reasons. The editing tools are Read, Write, Edit, Grep, and Glob. Partial context is not enough: the agent must read the full note before editing.

What it helps with

  • replace a stale claim while retaining its earlier wording
  • add a dated replacement with an OpenChronicle ID
  • keep the reasoning behind an earlier decision
  • report which entries were replaced or preserved

Example prompts for the agent

  • Replace the outdated claim in this note and retain its history.
  • Update this note by striking the old entry and adding a dated replacement.
  • Mark this statement as outdated, but preserve the reasoning behind the decision.

How to install supersede

1Skills CLI (Vercel)

npx skills add wrg32786/aigent-os --skill supersede -a claude-code

2Manually: put the files in place

~/.claude/skills/supersede/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/supersede/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about supersede

How do I install supersede in Claude Code?

Run npx skills add wrg32786/aigent-os --skill supersede -a claude-code. The skill file is at ~/.claude/skills/supersede/SKILL.md.

What does supersede do?

It strikes through an outdated note entry and adds a dated replacement with an OpenChronicle ID. It can retain decision rationale in a historical-context callout and finishes with a ledger of changes.

How does supersede preserve a note’s history?

It keeps the former wording with strikethrough instead of deleting it. If that entry explains a decision, the skill preserves the reasoning in a callout.

Source text

SKILL.md · MIT
---
name: supersede
agent: mnemosyne
description: "Apply OpenChronicle supersede semantics to vault notes, preserving history. Use when striking outdated entries, adding dated replacements, or updating the record."
allowed-tools: Read, Write, Edit, Grep, Glob
user-invocable: true
triggers:
  - supersede this entry
  - supersede
  - update this note
  - mark as superseded
  - replace outdated entry
  - this is no longer true
  - update the record
  - strike and replace
---

# Supersede

You are Mnemosyne applying OpenChronicle supersede semantics. You strike outdated entries and add new ones. You never silently overwrite.

## What this skill does

Mark an outdated vault entry as superseded using strikethrough, add the replacement entry below it with an OpenChronicle ID timestamp, and explain what was preserved and why. The history of reasoning matters — never delete, always layer.

## Protocol

### Step 1: Read the full note

Read the entire target note before touching anything. Understand what's current, what's stale, and what's load-bearing. Never edit from partial context.

### Step 2: Identify the supersede target

From the user's prompt, identify:
- The specific entry, section, or claim being superseded
- The replacement content
- The date of the new entry

### Step 3: Apply supersede semantics

Format for superseded entry:
```
~~<old entry text>~~ *(superseded YYYY-MM-DD)*
<new entry text> — `YYYYMMDD-HHMM-xxxx`
```

Where `xxxx` is a 4-char identifier (use first 4 chars of a relevant keyword, or `gnrc` for generic).

### Step 4: Preserve what's load-bearing

Before striking anything, ask: is this entry referenced elsewhere? Does it explain *why* a decision was made? If the rationale matters, preserve it in a `> [!info] Historical context` callout rather than striking it completely.

### Step 5: Return honesty ledger

```
## Honesty Ledger

**Notes touched:** <list>
**Entries superseded:** <count and list of what was struck>
**Entries preserved:** <what was kept and why>
**Compaction ratio:** N/A (supersede-only pass)
**Residual uncertainty:** <any entries that were ambiguous to classify>
```

## OpenChronicle ID format

`YYYYMMDD-HHMM-xxxx — event description`

Examples:
- `20260427-1430-echo — Agent definition created`
- `20260501-0900-fixd — Sprint 3 gate merged`

## Constraints

- Read the full note before any edit. No partial-context edits.
- Never silently overwrite. Always use strikethrough + replacement pattern.
- Preserve load-bearing rationale — compacting reasoning is a separate `/compact-note` operation.
- Flag preservation decisions explicitly. "I kept X because Y" is required output.

© wrg32786 · MIT · wrg32786/aigent-os

Similar skills

All skills for Notes, tasks and projects →

From the same set58

The whole set →
frontend-slides The frontend-slides Claude Code skill creates animated HTML presentations and converts PowerPoint files into browser-ready slides. It activates for slide decks, talks, pitches, and PPT/PPTX web conversions. CX Codex +1 ★ 26repo stars sweep-links The sweep-links skill for Claude Code finds wikilinks that point to missing notes. Run it to scan a vault or locate dead links. CX Codex +1 ★ 26repo stars sweep-heat The sweep-heat Claude Code skill marks cold notes in the bottom 20 of HEAT_INDEX.md as dormant. Run it to inspect the heat index or change note statuses. CX Codex +1 ★ 26repo stars Stuck The Stuck Claude Code skill guides an agent through possible next steps before it calls a task blocked. It activates when the agent runs out of ideas or is about to ask for help. CX Codex +1 ★ 26repo stars status The status Claude Code skill reports the current operating state of aigent-OS. Ask for a snapshot of its mode, objective, next action, or blockers. CX Codex +1 ★ 26repo stars start start — a Claude Code skill that opens a home screen on first launch or when work resumes. It guides setup or gives a brief status update with an action menu. CX Codex +1 ★ 26repo stars sprite-spec This Claude Code skill turns pixel-art character ideas into sprite specifications. It activates for character or sprite-sheet design, covering palettes, proportions, and animation states. CX Codex +1 ★ 26repo stars solution-hunt The solution-hunt Claude Code skill finds legitimate alternatives when a task hits a blocker. It searches local notes and skills, then looks through GitHub and documentation. CX Codex +1 ★ 26repo stars

Project sponsors

Companies that keep this analytics open