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-refreshgit 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-refresh)<a href="https://agentmods.dev/skills/abilityai/cornelius/ref-refresh"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/ref-refresh.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 | $0.00087 | $0.01386 |
| Opus 5 | $0.00044 | $0.00693 |
| Sonnet 5 | $0.00017 | $0.00277 |
| Haiku 4.5 | $0.00009 | $0.00139 |
Grade A, and why
ref-refresh 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ref Refresh
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-refresh v1.0 — recent: initial version. Then proceed.
The temporal maintenance loop: which records have gone stale, and which can be autonomously refreshed. Reference facts have a freshness half-life; this skill enforces the per-type SLA and routes the stale ones. It is the reference analog of a scheduled coherence job — mechanical, no judgment.
Read first: resources/layered-brains/COMPANY-BRAIN-SCHEMA.md → "The temporal model" → the per-type Freshness SLA and "Automation boundary — split by scope".
Composes
/ref-ingest— formarket/stale items only, invoked with--no-reindex(batch); this skill reindexes once at the end. Because it only ever takesref-ingest's gate-free, overwrite-only market branch, the whole path is autonomous-safe.
State Dependencies
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Company family | Brain/Company/*/*.md |
✓ | ✓ (market, via ref-ingest) | Entity notes swept |
| Refresh report | resources/company-brain/reports/ |
✓ | ref-refresh-YYYY-MM-DD.md (the queue + what was done) |
|
| LBS index | resources/local-brain-search/data/ |
✓ | ✓ (one batch reindex) | Rebuilt once after market writes |
The Freshness SLA (drives the sweep)
| Type / relationship | Stale after |
|---|---|
market/ competitor product/pricing |
~14 days |
engagement (active deal) |
~30 days |
organization (client) |
~90 days |
person (bio/role) |
~180 days |
product (own) |
on-change (no age SLA — skip) |
Process
Step 1 — Sweep as_of vs SLA
For every Brain/Company/*/*.md, read type/relationship/status/as_of, compute today − as_of in days, and compare to the SLA for that type. Collect the overdue notes; sort by how far over SLA they are. Skip status: superseded and own-product (on-change).
cd $PROJECT_ROOT/Brain/Company
# example: market notes older than 14 days (compute days-since in the agent; illustrative)
for f in market/*.md; do a=$(grep -m1 '^as_of:' "$f" | cut -d' ' -f2); echo "$a $f"; done | sort
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 · 89 lines · 87 tokens per session scan A b26665b0d832
ref-refresh is a skill published in the GitHub repository Abilityai/cornelius (106 stars, last pushed 14d ago), licensed MIT. It adds 87 tokens to every session and 1,386 once invoked, about $0.0004 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.