Kernel Organization
sgl-project/sglang
Apply the SGLang kernels RFC when adding, moving, splitting, or reviewing kernel APIs, registry metadata, kernel tests, benchmarks, and model-specific implementations.
Egregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage.
MITAuto-check passed
Install Egregore
$ npx skills add egregore-labs/egregore --skill egregore -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install egregore-labs/egregore egregore --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/egregore-labs/egregore.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.prime/agent/skills/egregore .claude/skills/egregore && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "egregore" agent skill from https://github.com/egregore-labs/egregore/tree/main/.prime/agent/skills/egregore into .claude/skills/egregore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "egregore", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/egregore-labs/egregore/tree/main/.prime/agent/skills/egregoreType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add egregore-labs/egregore --skill egregore -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install egregore-labs/egregore egregore --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/egregore-labs/egregore.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.prime/agent/skills/egregore .agents/skills/egregore && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "egregore" agent skill from https://github.com/egregore-labs/egregore/tree/main/.prime/agent/skills/egregore into .agents/skills/egregore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "egregore", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add egregore-labs/egregore --skill egregore -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install egregore-labs/egregore egregore --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/egregore-labs/egregore.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.prime/agent/skills/egregore .cursor/skills/egregore && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "egregore" agent skill from https://github.com/egregore-labs/egregore/tree/main/.prime/agent/skills/egregore into .cursor/skills/egregore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "egregore", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/egregore-labs/egregore.git --path .prime/agent/skills/egregore--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add egregore-labs/egregore --skill egregore -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install egregore-labs/egregore egregore --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/egregore-labs/egregore.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.prime/agent/skills/egregore .gemini/skills/egregore && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "egregore" agent skill from https://github.com/egregore-labs/egregore/tree/main/.prime/agent/skills/egregore into .gemini/skills/egregore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "egregore", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install egregore-labs/egregore egregoreInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add egregore-labs/egregore --skill egregore -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/egregore-labs/egregore.git skills-src && mkdir -p .github/skills && cp -r skills-src/.prime/agent/skills/egregore .github/skills/egregore && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "egregore" agent skill from https://github.com/egregore-labs/egregore/tree/main/.prime/agent/skills/egregore into .github/skills/egregore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "egregore", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add egregore-labs/egregore --skill egregore -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install egregore-labs/egregore egregore --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/egregore-labs/egregore.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.prime/agent/skills/egregore .opencode/skills/egregore && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "egregore" agent skill from https://github.com/egregore-labs/egregore/tree/main/.prime/agent/skills/egregore into .opencode/skills/egregore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "egregore", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
egregore- GitHub stars
- 291
- Token cost
- ~540 tokens
- SKILL.md length
- 202 words
- Files
- 3
- Skills in repo
- 43
- Repo updated
- First seen
- Licence
- MIT
At a glance
Egregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage.
- Runs Python scripts from its folder
What it does
Egregore is an agent skill from egregore-labs/egregore. Egregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage. Import and call directly; every function wraps the same runtime-neutral bin/ scripts the other harnesses use.
Its SKILL.md is about 540 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `src/egregore/__init__.py`).
The repository describes itself as: Shared intelligence layer for organizations. The licence is MIT.
Example prompts
- “/egregore”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 05b8672. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
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
Egregore loads about 540 tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 202 words of instructions outside code blocks.
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
Auto-check passed
The automated check found no risky patterns in SKILL.md.
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 egregore-labs/egregore at commit 05b8672, republished under its MIT licence (© egregore-labs). 202 words, ~540 tokens.
Download SKILL.mdSave it as
.claude/skills/egregore/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- egregore
- description
- Egregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage. Import and call directly; every function wraps the same runtime-neutral bin/ scripts the other harnesses use.
egregore — kernel bridge to Egregore mechanics
Python-backed skill. The module is installed into the kernel venv; call the
functions directly instead of grepping bin/ scripts to reconstruct CLI usage:
import egregore
egregore.search("pricing decision") # ranked shared-memory recall
egregore.activity() # team activity JSON
egregore.handoff(to="renc", topic="...", body="...")
egregore.save(message="fix(runtime): correct behavior", topic="topic", draft=True)
egregore.branch("new topic") # task branch + worktree
egregore.notify_plan(recipient="renc", message="...") # proposal ONLYUse draft=True while
implementation or review continues. After local QA and review pass, use
draft=False to push the final changes and mark the PR ready for CI. Omit
draft for normal non-coding auto-merge; omitting it on an existing PR
preserves that PR's readiness. These choices follow the work's state and do
not require a separate permission checkpoint.
Ground rules:
- Every function shells out to the corresponding
bin/script with a generous internal timeout and returns its text output.bin/stays the single mechanics layer — this module contains no logic of its own. notify_planonly CREATES a notification plan. Approval and dispatch remain subject to the explicit human Send / Edit / Cancel checkpoint: show the plan, get the user's approval, then runbin/notify.sh approve/dispatchwith the plan's one-use approval token. Never call approve or dispatch without a fresh human yes in this conversation.- Functions raise
RuntimeErrorwith the script's stderr on failure — report the single relevant line, do not debug the plumbing mid-workflow. help()on the module or any function shows signatures and semantics.
© egregore-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in .prime/agent/skills/egregore of egregore-labs/egregore.
- SKILL.md
- pyproject.toml
- src/egregore/__init__.py
Open the folder on GitHubat commit 05b8672
Compare with similar skills
Egregore next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Egregore this skillegregore-labs/egregore | 291 | — | ~540 | Automated safety check: Pass | MIT | |
| Kernel Organizationsgl-project/sglang | 37k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Metal Kernelpytorch/pytorch | 104k | — | ~4.9k | Automated safety check: Pass | Custom licence | |
| Azure Functionsdavila7/claude-code-templates | 33k | 2 repos | ~344 | Automated safety check: Pass | MIT | |
| Mechanical Refactor Verifysgl-project/sglang | 37k | 2 repos | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Neon Functionssickn33/agentic-awesome-skills | 47k | 1 repos | ~8.6k | Automated safety check: Notes | Apache-2.0 |
Similar skills
Metal Kernel
pytorch/pytorch
Write Metal/MPS kernels for PyTorch operators. An agent skill from pytorch/pytorch.
Azure Functions
davila7/claude-code-templates
Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns.
Mechanical Refactor Verify
sgl-project/sglang
Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of eyeballed.
Neon Functions
sickn33/agentic-awesome-skills
Long-running, serverless Node.js HTTP functions deployed onto your Neon branch, with DATABASEURL injected automatically and compute that runs next to your data.
GCP Cloud Functions
sickn33/agentic-awesome-skills
Deploy serverless functions on Google Cloud Functions. An agent skill from sickn33/agentic-awesome-skills.
More from egregore-labs/egregore
All 43 skills in this repoIngest User Interview
egregore-labs/egregore
Analyze a user interview from Granola, pasted text, or a file into an evidence-backed briefing, journey insights, product findings, patterns, and actions.
Meeting
egregore-labs/egregore
Analyze a Granola meeting into an evidence-backed briefing, decisions, findings, patterns, actions, and continuity.
View
egregore-labs/egregore
Generate a branded HTML artifact from Egregore data (quest, handoff, activity, board, network, or any document) and open it in the browser.
Activity
egregore-labs/egregore
Explicit Activity card only. An agent skill from egregore-labs/egregore.
Checkup
egregore-labs/egregore
Run diagnostics on an Egregore environment and render a health report, repairing safe local Runtime problems when possible.
Dashboard
egregore-labs/egregore
Explicit personal-status surface for /dashboard or a direct request for the whole personal overview.
Questions about Egregore
What does Egregore do?
Egregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage. Egregore is an agent skill from egregore-labs/egregore. Egregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage.
How do I install Egregore in Claude Code?
Run `npx skills add egregore-labs/egregore --skill egregore -a claude-code`. Or copy the skill folder (.prime/agent/skills/egregore in egregore-labs/egregore) into .claude/skills/egregore in your project. Claude Code loads it when a task matches its description.
How do I install Egregore in Codex?
Run `npx skills add egregore-labs/egregore --skill egregore -a codex`. Or copy the skill folder (.prime/agent/skills/egregore in egregore-labs/egregore) into .agents/skills/egregore in your project. Codex loads it when a task matches its description.
Can I use Egregore in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add egregore-labs/egregore --skill egregore -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/egregore, .gemini/skills/egregore, .github/skills/egregore and .opencode/skills/egregore in your project.
What does Egregore need to run?
Going by SKILL.md and its folder, Egregore needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Egregore access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Egregore safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Egregore use?
Egregore is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Egregore use?
About 540 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Egregore?
Skills that share tags, products or a category with Egregore: Kernel Organization (sgl-project/sglang, 37k stars), Metal Kernel (pytorch/pytorch, 104k stars), Azure Functions (davila7/claude-code-templates, 33k stars) and Mechanical Refactor Verify (sgl-project/sglang, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Egregore?
egregore-labs (a GitHub organization) maintains it in egregore-labs/egregore, which has 291 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on October 1, 2026.
Source: egregore-labs/egregore on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.