agentleFS
dtiger1889-opsdtiger1889-ops/claude-harness-toolbox/skills/necromancy/SKILL.md

necromancy

Skill31 starsChanged 32 days agoMITView on GitHub

Recovers a Claude Code session that ended before its checkpoint was saved, using a deterministic digest of the local session store. Use for /necromancy, "recover the dead session", "resurrect that session", or a crash before checkpointing. Does not recover other agents' stores, editor autosaves, or git artifacts.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use the bundled necromancy.ps1 with PowerShell.

    line 8
  2. Distinctive:

    Do not load a full raw JSONL transcript into model context.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Recover a dead session

Use the bundled necromancy.ps1 with PowerShell. Resolve <skill-dir> to the directory containing this loaded SKILL.md, including plugin installs. The script reads the current user's ~/.claude/projects store; it needs access to the actual host store, not an unrelated sandbox home.

  1. List candidates for the requested project, defaulting to the project under discussion:

    & "<skill-dir>/necromancy.ps1" -Project "<project path>"
  2. Select by topic, timeframe, and checkpoint state. The newest transcript may be the current live session; do not select it merely for being newest. Ask if multiple candidates fit.
  3. Digest the selected session:

    & "<skill-dir>/necromancy.ps1" -Project "<project path>" -Session "<UUID prefix>"
  4. Synthesize from the digest: request, user decisions, completed work, interrupted work, and next action. Verify completion claims against current artifacts; transcript statements alone do not prove writes or releases completed.
  5. Persist recovered state through checkpoint when the user authorizes resuming or recording it. If the checkpoint already reflects the session, use it rather than repeating recovery.

Do not load a full raw JSONL transcript into model context. The digest caps each category and uses regex anchors; errors and commits are leads. If required detail is omitted, search only the selected transcript for specific anchors. Report uncertainty instead of reconstructing missing events.

Project slugs replace non-alphanumeric path characters with hyphens; the script also checks case variants. A missing store or unsupported runtime is a limitation, not evidence that the session never existed.

Credit: digest pattern adapted from herderp.

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.