egregore: Skill for Claude Code

.claude/skills/announce/SKILL.md

announce is a skill for Claude Code from egregore-labs/egregore. It costs 44 tokens per session (1,243 once invoked), scanned A, original, MIT.

A tool that drafts an announcement and sends it to a Telegram group after you approve the draft.

In plain words
What is it for?
Use it to notify a team about a feature, fix, decision, merge, or required action. It is for group announcements, not one-to-one messages or structured handoffs.
Why use it?
It helps communicate a change to everyone in one place while letting you review the wording before sending.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the AskUserQuestion tool.

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 ARTIFACT_URL=$(bash bin/publish-artifact.sh document "$FILE_PATH" \.

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/announce/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 announce

README.md
[![agentmods](https://agentmods.dev/badge/skills/egregore-labs/egregore/announce/github.svg)](https://agentmods.dev/skills/egregore-labs/egregore/announce)
Your own site
<a href="https://agentmods.dev/skills/egregore-labs/egregore/announce"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/announce/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for announce

Your own site · 80×15
<a href="https://agentmods.dev/skills/egregore-labs/egregore/announce"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/announce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,243 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 pass 7 Sept 2026
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 $0.00044 $0.01243
Opus 5 $0.00022 $0.00622
Sonnet 5 $0.00009 $0.00249
Haiku 4.5 $0.00004 $0.00124

Measured 10d ago against content hash ae8dd9531c3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

announce 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 10d 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/announce/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Send an announcement to the Telegram group. Drafts a message, shows a preview for approval, then sends.

When to invoke

User says: "announce", "tell the team", "send to the group", "notify everyone", "let everyone know" Not this: notify one person → prepare a direct notification proposal · handoff → /handoff

Topic: $ARGUMENTS

What to do

Step 1: Draft the message

If $ARGUMENTS is provided, use it as the topic and draft a concise announcement (2-5 lines). Pull context from the conversation — what just happened, what changed, what the team should do.

If no arguments, ask: "What should I announce?"

Message guidelines:

  • Lead with what changed (feature, fix, decision, merge)
  • Include the PR number or branch if relevant
  • End with an action if needed ("Run /update to get it", "Review PR #N", etc.)
  • Keep it under 500 chars (chat readability)
  • No emojis unless the user's draft uses them

Step 2: Publish artifact (if relevant)

If the announcement references a document, handoff, quest, or knowledge artifact from memory/, publish it now so the final message includes a clickable link with OG preview.

Detect: Check if the conversation produced or references a specific file in memory/ (handoffs, knowledge, quests). If so, publish it:

ARTIFACT_URL=$(bash bin/publish-artifact.sh document "$FILE_PATH" \
  --title "$TITLE" \
  --author "$AUTHOR" \
  --description "$ONE_LINE_DESCRIPTION" 2>/dev/null)

Use the appropriate type: handoff, quest, or document (for knowledge files).

  • If publish succeeds: insert the returned live URL into the message draft.
  • If publish fails: send the message without a link. Do NOT make up a URL.

Never fabricate artifact URLs. Only use URLs returned by publish-artifact.sh.

Step 3: Plan, preview, and confirm

Follow .claude/context/notification-consent.md. Create the group plan only after the artifact URL and message are final:

PLAN_JSON=$(bash bin/notify.sh plan group "$MESSAGE")

Read the full file on GitHub · 160 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. 10d ago First seen · 160 lines · 44 tokens per session scan A ae8dd9531c3b

Subscribe to this mod's changes

announce is a skill published in the GitHub repository egregore-labs/egregore (289 stars, last pushed 6d ago), licensed MIT. It adds 44 tokens to every session and 1,243 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.