agentleFS
egregore-labsegregore-labs/egregore/.claude/skills/save/SKILL.md

save

Skill293 starsChanged 10 days agoMITView on GitHub

Save current Egregore work: validate distribution, commit the task branch, push it, and create or reuse a PR against the configured integration branch.

37 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use load, query and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TheLatentSpaceLabSkill

    load

    Load a document into memory for RAG

    Also in 4 projects that use this

  • ArtemXTechSkill

    query

    Query data from this vault. USE WHEN user asks about projects, clients, tasks, daily notes. Use grep to extract frontmatter - do NOT read full files.

    Also in 4 projects that use this

  • szweibelSkill

    idea

    Generate a wide field of options when the user is brainstorming, exploring, expanding, or pressure-testing — not recommending or implementing

    Also in 3 projects that use this

  • Microsoft AzureSkill

    lint

    Run all linting and spell checking for TypeScript and Rust code. Run this before committing to catch style issues, clippy warnings, and misspellings.

    Also in 5 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 6 projects that use this

  • HK-hubSkill

    defuddle

    Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 10 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use for “save”, “commit and push”, “push this work”, or $save.

    line 10
  2. Distinctive:

    Do not scan or mutate the graph before/after saving.

    line 20
  3. Distinctive:

    Do not repeat canonical artifact writeback.

    line 22
  4. Distinctive:

    Stop before mutation if it cannot be resolved.

    line 40
  5. Distinctive:

    Ask one placement question only for a genuinely new/unclassified component or an explicit placement change.

    line 54
  6. Distinctive:

    If unrelated changes make the save scope ambiguous, show one Save all / Narrow scope checkpoint.

    line 79
  7. Very specific:

    When the requested work is complete and local QA/review has passed, use --ready.

    line 87
  8. Very specific:

    Use {message}, {topic}, and {pr_body} for the commit subject/body, topic, and PR body derived in Step 4.

    line 104
  9. Distinctive:

    Never push directly to a protected integration/stable branch.

    line 121
  10. Distinctive:

    Never use destructive Git commands.

    line 122
  11. Distinctive:

    Never auto-close handoffs or todos during save.

    line 123
  12. Distinctive:

    Never publish or notify as an implied side effect.

    line 124
  13. Distinctive:

    Do not spend a Loom/model-routing turn on deterministic save mechanics.

    line 125

“Common” is measured: kept by at least 6 in 10 of the 31 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 save is the one runtime-neutral Git transaction for Claude, Codex, Pi, and Prime.
  • Resolve the integration branch from egregore.json; never hardcode develop or main.
  • 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

  1. 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.
  2. 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.

  1. The shared bin/agent.sh save preflight 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=0 only to explicitly disable this advisory receipt.

Ask one placement question only for a genuinely new/unclassified component or an explicit placement change. Ordinary edits to an existing component do not prompt.

For that question, show artifacts/capability-pipeline.html and offer:

  1. OSS + Connect — part of the open runtime; Connect inherits it.
  2. Connect only — delivered only to authenticated Connect users.
  3. Curve Labs / Egregore — used only in this development instance.

Record each new component as queued under the selected placement with all its governed source paths. Availability changes separately after review. Group components in one checkpoint only when they share a placement. Apply the decision to capability-distribution.json, regenerate skill-distribution.json and both artifacts, then validate again. Rebuild runtime packs when an available runtime component changes placement. Reuse an explicit placement decision from the current work; do not ask twice.

  1. Derive:
  • a short topic;
  • a commit subject/body under .claude/context/commit-format.md;
  • a PR body under .claude/context/pr-format.md, including honest verification for non-Markdown changes.

If unrelated changes make the save scope ambiguous, show one Save all / Narrow scope checkpoint. Otherwise continue without ritual confirmation.

  1. Choose readiness from the work's actual state, without a permission ritual:
  • While implementation or review continues, use --draft. New code PRs are drafts by default; passing --draft also converts an existing ready PR before pushing, avoiding paid checks on unfinished iterations.
  • When the requested work is complete and local QA/review has passed, use --ready. In the Egregore source repository (not an installed instance) the bridge first runs the checks CI would select for the branch on this machine, which can take as long as a CI run; run the save in the background where the harness allows. If a check fails, the work is still pushed, the PR stays a draft, and the bridge exits non-zero naming the check and its log: fix it, then save with --ready again. For an existing draft, the bridge pushes the final head before marking it ready, so CI checks the saved version. If CI fails or another edit is needed, use --draft for the next in-progress save.
  • Non-coding saves keep their existing ready/auto-merge behavior. Omit the readiness flag unless the work should deliberately remain a draft.
  • Without a flag, existing PRs retain their current readiness. --draft and --ready are mutually exclusive and cannot be combined with --no-pr.
  1. Execute exactly once:

Use {message}, {topic}, and {pr_body} for the commit subject/body, topic, and PR body derived in Step 4; single-quote each value, writing an embedded single quote as '\''. Append --draft or --ready as selected above; omit both for the normal non-coding path.

bin/agent.sh save \
  --message '{message}' \
  --topic '{topic}' \
  --pr-body '{pr_body}'

The bridge owns branch safety, exact commits, push, PR create/reuse, and memory sync. Do not run manual Git commands around it or trigger a graph scan.

  1. Report only the branch, commit/push outcome, PR URL/reuse and draft/ready state, memory sync, and any failed step. Local commits remain safe if transport fails.

Rules

  • Never push directly to a protected integration/stable branch.
  • Never use destructive Git commands.
  • Never auto-close handoffs or todos during save.
  • Never publish or notify as an implied side effect.
  • Do not spend a Loom/model-routing turn on deterministic save mechanics.

Emit content-free command telemetry after the bridge returns:

bash bin/telemetry.sh emit "command" '{"command":"save"}' 2>/dev/null &

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.