Ref Refresh

What it does

When your agent uses it

• Sales & Support work in your project

Example prompts

• “/ref-refresh”

Requirements

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

Workflow steps

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

1. 1Sweep as_of vs SLA
2. 2Split the queue by scope
3. 3Refresh market/ (autonomous, batched)
4. 4Report

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
  • Bash
  • Glob
  • Grep
  • Skill

  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 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 Refresh loads about 1.3k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 527 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~102

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

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

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

  allowed-tools: Read, Write, Bash, Glob, Grep, Skill

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). 527 words, ~1,335 tokens.

name

ref-refresh

description

Mechanical staleness sweep over a reference scope. Scans every note's as_of age against the per-type Freshness SLA, builds an overdue-sorted refresh queue, then splits by scope — market/ stale items are handed to ref-ingest (the gate-free overwrite branch) for autonomous re-verification; CRM stale items are report-only (never auto-written). Safe to run unattended. Company is the default scope.

allowed-tools

Read, Write, Bash, Glob, Grep, Skill

automation

autonomous

user-invocable

true

argument-hint

[scope=Company] [--market-only]

metadata.version

1.0

metadata.created

2026-07-08

metadata.author

Cornelius

metadata.changelog

1.0: Initial version — as_of-vs-SLA staleness sweep → refresh queue; market→ref-ingest (ungated overwrite), CRM→report-only; single batch reindex

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

cd resources/local-brain-search && ./run_index.sh && ./run_daemon.sh restart

© 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-refresh of Abilityai/cornelius.

Open the folder on GitHubat commit fd5e9a4