agentsclimarketplace
Sign in

Memory graveyard

Skill sfrangulov/skill-graveyard/skills/memory-graveyard

Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entries, broken pointers in MEMORY.md, orphan memory files, or surface entries that fall below the system-prompt truncation cutoff. Triggers on "audit MEMORY.md", "dead memory entries", "broken memory pointers", "memory hygiene", "unused memory", "memory truncation". Runs locally; reads ~/.claude/projects session JSONL logs and memory directories. No network calls.From its SKILL.md

Install
npx -y skills add sfrangulov/skill-graveyard --skill memory-graveyard

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 6 commands, including `npx memory-graveyard@latest <subcommand> [flags]` and 5 more.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.9 KB, 379 tokens by cl100k_base, as published. Nobody here has run it

memory-graveyard

CLI that audits per-project file-based memory (MEMORY.md index + memory/*.md entries). Bucketed audit (ACTIVE / DEAD / MISSING / HALLUCINATED) plus a static linter that flags broken pointers, orphan files, truncation-budget overflow, index size, and stale dated entries.

How to invoke

Run via npx memory-graveyard@latest <subcommand> [flags] — no install needed.

Subcommands

  • audit (default) — 4-bucket per-project table. Flags: --days N, --only <bucket>, --json, --project <path>, --claude-dir <path>.
  • lint — static checks on MEMORY.md and the memory dir. Flags: --truncation-cutoff N (default 200), --stale-days N (default 30), --json. Exit 1 on findings.
  • prune — plan removal of dead entries and hallucinated pointers. --apply to execute (with snapshot backup in .graveyard-backup/<timestamp>/). --include orphans|broken-pointers, --exclude <basename>.
  • projects — cross-project sweep, surfaces cold memory dirs. --cold-days N (default 90).

Decision flow

  • "what entries in my MEMORY.md are dead?" → npx memory-graveyard@latest
  • "is anything in MEMORY.md broken?" → npx memory-graveyard@latest lint
  • "clean up MEMORY.md" → prune, then --apply
  • "which projects have stale memory dirs?" → projects

After running, print output verbatim. Do not summarize unless the user asks.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.