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.
npx skills add Abilityai/cornelius --skill ref-supersedegit clone --depth 1 https://github.com/Abilityai/corneliusWrote 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.
[](https://agentmods.dev/skills/abilityai/cornelius/ref-supersede)<a href="https://agentmods.dev/skills/abilityai/cornelius/ref-supersede"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/ref-supersede.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.01222 |
| Opus 5 | $0.00056 | $0.00611 |
| Sonnet 5 | $0.00023 | $0.00244 |
| Haiku 4.5 | $0.00011 | $0.00122 |
Grade A, and why
ref-supersede 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.changelogabove — 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
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Company family | Brain/Company/*/*.md |
✓ | ✓ (gated) | Old + new entity notes |
| LBS index | resources/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, withvalid_from:(andvalid_until:if it has a term), freshas_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): addsuperseded_by: "[[<New note title>]]"; leave its body as the historical snapshot; re-stampupdatedonly.
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.
- 3d ago First seen · 73 lines · 113 tokens per session scan A cdc927fc6d7a
ref-supersede is a skill published in the GitHub repository Abilityai/cornelius (106 stars, last pushed 14d ago), licensed MIT. It adds 113 tokens to every session and 1,222 once invoked, about $0.0006 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 2026-09-03.
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.
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.…
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…
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.
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…
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.