egregore: Skill for Claude Code

.claude/skills/save/SKILL.md

save is a skill for Claude Code from egregore-labs/egregore. It costs 51 tokens per session (6,367 once invoked), scanned A, original, MIT.

A save workflow for committing your code changes, pushing the working branch, and opening a pull request to the project's configured base branch.

In plain words
What is it for?
Use it when you want to commit and push changes, sync your branch, or create a pull request for the current work.
Why use it?
It removes the repeated Git steps needed to publish work for review. It also distinguishes saving work from handing off or ending a session.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; names the AskUserQuestion tool; positional $N argument.

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 node bin/capability-distribution.mjs validate --root ..

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/save/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 save

README.md
[![agentmods](https://agentmods.dev/badge/skills/egregore-labs/egregore/save.svg)](https://agentmods.dev/skills/egregore-labs/egregore/save)
Your own site
<a href="https://agentmods.dev/skills/egregore-labs/egregore/save"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/save.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,367 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: 2 findings, up to medium

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 →

  • medium Agent Snooping · line 426
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Excessive Agency · line 511
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00051 $0.06367
Opus 5 $0.00026 $0.03184
Sonnet 5 $0.00010 $0.01273
Haiku 4.5 $0.00005 $0.00637

Measured 4d ago against content hash 64988d5f63a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

save 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 4d 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/save/SKILL.md · 526 lines

How it starts

The opening of the file, as written. The whole thing — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Save your contributions to Egregore. Pushes working branch, creates PR to develop.

Worktree note: Git operations (commit, push, gh pr create) work normally from within a worktree — no special handling needed. After save completes, work continues in the worktree. Worktree cleanup happens automatically when the session ends (WorktreeRemove hook), never during an active session.

When to invoke

User says: "push my work", "sync changes", "commit and push", "save everything", "push this up" Not this: user is leaving/done → /handoff (which auto-saves)

Base branch

Every develop in this skill — branch points, rebase targets, gh pr create --base, git diff bases — means the instance's base branch, not the literal string. Resolve it once at the start and substitute it everywhere below:

BASE=$(bash -c 'SCRIPT_DIR="$PWD"; CONFIG="$PWD/egregore.json"; . "$PWD/bin/lib/config.sh" && _get_base_branch') ||
  { echo "Could not resolve the configured base branch; stopping before Git changes." >&2; exit 1; }

It is develop unless egregore.json sets base_branch. Instances running single-branch mode set it to main; opening a PR against a develop that does not exist there will fail.

Mode detection

MODE=$(jq -r '.mode // "connected"' egregore.json 2>/dev/null)

Local mode (mode === "local"): Skip the "Sync to Neo4j" step entirely. Skip bin/sync-graph.sh and the graph enrichment section. Skip the bash bin/graph-op.sh create-pr ... fire-and-forget calls. Do NOT show any graph-related messaging ("[sync] Checking Neo4j...", "Synced N to graph", "tracked PR in graph", etc.). Git operations (commit, push, gh pr create) work identically in both modes — only the graph reporting layer is skipped.

Execution rules

CRITICAL: Suppress raw output. Never show raw JSON to the user. All bin/graph.sh calls MUST capture output in a variable and only show formatted status lines (e.g. "Synced 2 sessions, 1 artifact to graph").

Read the full file on GitHub · 526 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. 4d ago Changed 64988d5f63a4
  2. 8d ago First seen · 526 lines · 51 tokens per session scan A 390c51c3459e

Subscribe to this mod's changes

save is a skill published in the GitHub repository egregore-labs/egregore (282 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 6,367 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

release-expert

Multi-repo release coordination: version alignment, RC lifecycle, release waves, rollback planning. Use when saying "release", "version alignment", or "cut an RC".

anton-abyzov/specweave · 0 tokens

release

Prepare code for release (version bumps, changelog, README updates) and create an annotated tag to trigger the GoReleaser workflow.

jrswab/axe · 30 tokens

agentplane-release-and-packaging-operator

Use when preparing, validating, publishing, auditing, or recovering an Agentplane release, especially package build ordering, version parity, npm/GitHub/GHCR/external distribution publication, public install smoke tests, hosted publish evidence, or release CI failures.

basilisk-labs/agentplane · 60 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

pypi-release

This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.

alchemiststudiosDOTai/tunacode · 52 tokens

ship

Ship phase. Runs isolated integration test in a fresh worktree, creates a PR with full spec + audit report in the body, watches CI, and auto-fixes failures.

epicsagas/epic-harness · 37 tokens