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.
curl -O https://raw.githubusercontent.com/egregore-labs/egregore/main/.claude/skills/save/SKILL.mdgit clone --depth 1 https://github.com/egregore-labs/egregoreWrote 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.
[](https://agentmods.dev/skills/egregore-labs/egregore/save)<a href="https://agentmods.dev/skills/egregore-labs/egregore/save"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/save/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.
<a href="https://agentmods.dev/skills/egregore-labs/egregore/save"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/save.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.01249 |
| Opus 5.5 | $0.00013 | $0.00500 |
| Sonnet 5.5 | $0.00006 | $0.00250 |
| Haiku 4.5 | $0.00003 | $0.00125 |
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 24d 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save work without asking the user to manage Git mechanics.
When to invoke
Use for “save”, “commit and push”, “push this work”, or $save. When the user
is ending a session and needs a durable continuation record, use handoff or
wrap first; their canonical writes are already independently durable.
Contract
bin/agent.sh saveis the one runtime-neutral Git transaction for Claude, Codex, Pi, and Prime.- Resolve the integration branch from
egregore.json; never hardcodedevelopormain. - Do not scan or mutate the graph before/after saving. Canonical lifecycle and projection repair are separate Runtime operations.
- Do not repeat canonical artifact writeback. Save only outstanding repository changes and already-created memory records.
- The current Git/GitHub transport remains valid but is behind the sync boundary; GitHub identity is not ActorIdentity.
Flow
- Inspect branch, working-tree changes, memory changes, ahead count, and an existing PR. A clean tree can still need a push/PR when the branch is ahead.
- Resolve the configured integration branch first:
bash bin/base-branch.sh
It prints the branch name; for a managed repo run bash bin/base-branch.sh <repo-name>.
A non-zero exit means the configuration could not be resolved: stop before any
Git change. Use the printed name wherever {base} appears below.
Stop before mutation if it cannot be resolved.
-
The shared
bin/agent.sh savepreflight runs distribution validation, the change report, and the strict Runtime-skill audit before any memory or project mutation. Both engine and registry must exist; installed public instances intentionally omit the development engine.It also prints an advisory affected-skill receipt from the branch diff, staged/unstaged edits, and relevant untracked files. Read the named instructions for drift and include material findings in PR verification; ordinary edits require no new approval. A missing base is reported as an unavailable review, never as zero affected skills. Set
EGREGORE_SKILL_REVIEW=0only to explicitly disable this advisory receipt.
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.
- 24d ago Changed · -400 lines · -19 tokens per session 9d7c711c2e4b
- 1mo ago Changed 64988d5f63a4
- 1mo ago First seen · 526 lines · 51 tokens per session scan A 390c51c3459e
save is a skill published in the GitHub repository egregore-labs/egregore (293 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 1,249 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
git-workflow
Git branching, commit conventions, rebase vs merge, conflict resolution, and release tagging. Use when setting up a git workflow, writing commits, resolving conflicts, or preparing a release.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
release
Skill "release" from Hmbown/Codewhale, covering release, invocation, non-goals and workflow.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
skillshare-changelog
Generate CHANGELOG.md entry from recent commits in conventional format. Also syncs the website changelog page. Use this skill whenever the user asks to: generate a changelog, document what changed between tags, or create a new CHANGELOG entry. If you see requests like "write the changelog for v0.17", "what changed…
commit-pr
Mandatory Codex/Copilot publication adapter for opencode-swarm. Use for every GitHub issue assignment that results in code changes, commits, pushes, draft PRs, PR body edits, PR readying, release notes, or CI closeout. Must be loaded before git push, gh pr create, gh pr edit, or gh pr ready. Routes to the single…