egregore: Skill for Claude Code

.claude/skills/contribute/SKILL.md

contribute is a skill for Claude Code from egregore-labs/egregore. It costs 50 tokens per session (2,787 once invoked), scanned A, original, MIT.

A guide for sending improvements to the upstream Egregore framework as a cross-fork pull request. A pull request is a proposed code change submitted for review.

In plain words
What is it for?
Checking contribution settings, choosing interactive or submission mode, preparing an upstream change, and tracking its contribution status.
Why use it?
It directs contributions through the repository's required checks and distinguishes upstream contributions from saving local work or filing a bug.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md; 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 UPSTREAM_REPO=$(bash bin/contribute-guard.sh) || exit $?.

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/contribute/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 contribute

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/egregore-labs/egregore/contribute"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/contribute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,787 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 175
    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 $0.00050 $0.02787
Opus 5 $0.00025 $0.01393
Sonnet 5 $0.00010 $0.00557
Haiku 4.5 $0.00005 $0.00279

Measured 10d ago against content hash 8a17f3be1cf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

contribute 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/contribute/SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contribute an improvement back to the upstream Egregore framework.

Arguments: $ARGUMENTS

When to invoke

User says: "I want to improve this command", "submit a fix upstream", "contribute back", "send this to egregore", "contribute to the framework", "upstream PR", "fix in upstream" Not this: saving work to org repo → /save · filing a bug → /issue · syncing from upstream → /update

Argument routing

Parse $ARGUMENTS:

  • Empty → Interactive mode (ask what they want to improve)
  • submit → Submit mode (push changes + create cross-fork PR)
  • status → Show current contribution state
  • Anything else → Interactive mode with topic pre-seeded from arguments

Step 0: Gate check

Resolve the contribution target through the shared executable guard. This is mandatory for every mode, including status, and replaces any hand-written interpretation of upstream_url:

UPSTREAM_REPO=$(bash bin/contribute-guard.sh) || exit $?

If the guard refuses because upstream_url is "none", tell the user:

This is the framework source repository. Use /save to push changes to its configured integration branch.

Stop.

For malformed configuration, unsupported URLs, or any other guard failure, show its error and stop. Never substitute a public target after a guard error.

Step 1: Check auth + get username

GH_USER=$(gh api user --jq '.login' 2>/dev/null)

If empty: "Run bash bin/github-auth.sh first — you need GitHub access to contribute." Stop.


Interactive mode (default / topic provided)

Step 2: Understand intent

If $ARGUMENTS is non-empty (and not submit/status), use as the topic description.

If empty, use AskUserQuestion:

header: "Contribute"
question: "What do you want to improve in the Egregore framework?"
options:
  - label: "A command"
    description: "Improve or fix a slash command"
  - label: "A script"
    description: "Improve or fix a bin/ script"
  - label: "CLAUDE.md"
    description: "Update framework behavior"
  - label: "Something else"
    description: "I'll describe what I want to change"

Read the full file on GitHub · 344 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 · 344 lines · 50 tokens per session scan A 8a17f3be1cf1

Subscribe to this mod's changes

contribute is a skill published in the GitHub repository egregore-labs/egregore (289 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 2,787 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

gwm

Manage git worktrees across any repository with the gwm Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (gwm exec) or reclaim build artifacts (gwm clean), materialise a PR into a worktree (gwm review), drive a…

kbrdn1/gwm-cli · 0 tokens

agentplane

Use when a repository uses AgentPlane or the user wants a governed git-native workflow for planning, task execution, verification, and closure.

basilisk-labs/agentplane · 30 tokens

aigon-next

Suggest the most likely next workflow action based on current context.

jayvee/aigon · 15 tokens

dos-verify-done-claims

Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.

anthony-chaudhary/dos-kernel · 61 tokens

take-task

A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.

restarter/lets-workflow · 76 tokens

release

Release Aigon — push to origin, cut a version+tag, or publish to npm. Wraps scripts/ship.js with CHANGELOG draft + dry-run preview. Triggers when the user types "/release", "/push", "/ship", or says "ship a release", "publish a beta", "cut a version", "push to origin", "release X to npm".

jayvee/aigon · 79 tokens