egregore: Skill for Claude Code

.claude/skills/update/SKILL.md

update is a skill for Claude Code from egregore-labs/egregore. It costs 37 tokens per session (2,981 once invoked), scanned A, original, MIT.

An environment-update command for Egregore, a framework that manages shared project memory and repositories. It synchronises the framework, runs required migrations, and pulls repository and memory changes.

In plain words
What is it for?
Use it to update the framework, apply post-update changes, synchronise the base branch, and pull the latest managed repositories and memory.
Why use it?
It brings a local Egregore setup up to date when it is missing changes or behaving incorrectly.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

This is egregore-labs/egregore's own configuration. It tells Claude Code how to work on egregore itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything egregore configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is [ -f "$MAIN_DIR/bin/codex-sync-skills.sh" ] && (cd "$MAIN_DIR" && bash bin/codex-sync-skills.sh) >/dev/null 2>&1 || true.

Reuse

Borrowing it

Nothing to install: this file belongs to egregore-labs/egregore. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/egregore-labs/egregore/main/.claude/skills/update/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/egregore-labs/egregore

Made for: Claude Code.

Wrote 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.

agentmods badge for update

README.md
[![agentmods](https://agentmods.dev/badge/skills/egregore-labs/egregore/update.svg)](https://agentmods.dev/skills/egregore-labs/egregore/update)
Your own site
<a href="https://agentmods.dev/skills/egregore-labs/egregore/update"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/update.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,981 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 110
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.02981
Opus 5 $0.00018 $0.01491
Sonnet 5 $0.00007 $0.00596
Haiku 4.5 $0.00004 $0.00298

Measured 8d ago against content hash 398e8ca50801, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

update 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 8d 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.

.claude/skills/update/SKILL.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update local Egregore environment — sync framework from upstream and pull repos.

When to invoke

User says: "/update", "update Egregore", "sync the framework", "get the latest framework" — or framework behavior seems broken or missing (the first thing to try). Not this: syncing managed repos + memory only, no framework sync → /pull

What to do

  1. Sync framework from upstream (egregore-labs/egregore)
  2. Run post-update migrations (bin/post-update.sh)
  3. Run /pull (sync base branch + memory)
  4. Show what changed

Step 1: Detect environment

Detect the base branch and whether we're in a worktree. Framework updates MUST land on the base branch, never on working branches.

# Detect base branch: develop if it exists, otherwise main
BASE_BRANCH="main"
git show-ref --verify --quiet refs/heads/develop 2>/dev/null && BASE_BRANCH="develop"

CURRENT_BRANCH=$(git branch --show-current)

# Detect worktree: .git is a file (not a directory) in worktrees
IN_WORKTREE="false"
if [ -f .git ]; then
  IN_WORKTREE="true"
  WT_GITDIR=$(sed 's/^gitdir: //' .git)
  MAIN_DIR=$(cd "$WT_GITDIR/../../.." && pwd)
fi

Step 2: Sync framework to base branch

Egregore is a framework — updates come from upstream, not from your own repo's history.

Freeze lever — check FIRST, before touching any remote:

UPSTREAM_URL=$(jq -r '.upstream_url // empty' egregore.json 2>/dev/null)

If UPSTREAM_URL is "none", this instance does not pull framework from upstream — it is either the framework source of truth (framework changes are authored here and flow OUT via /sync-public) or deliberately frozen. Skip Step 2 entirely — do NOT add an upstream remote, do NOT checkout any path. Tell the user: ⛔ upstream_url is "none" — this instance never pulls framework from upstream. Skipping framework sync; running migrations + /pull only. Then continue with Step 3. A wholesale upstream checkout on a source-of-truth instance reverts downstream work (the 578deee incident: 23 files, −1131 lines).

Read the full file on GitHub · 264 lines

Changes

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.

  1. 8d ago First seen · 264 lines · 37 tokens per session scan A 398e8ca50801

Subscribe to this mod's changes

update is a skill published in the GitHub repository egregore-labs/egregore (282 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 2,981 once invoked, about $0.0002 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 2026-08-30.