Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sfrangulov/skill-graveyard --skill memory-graveyardgit clone --depth 1 https://github.com/sfrangulov/skill-graveyardWrote 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/sfrangulov/skill-graveyard/memory-graveyard)<a href="https://agentmods.dev/skills/sfrangulov/skill-graveyard/memory-graveyard"><img src="https://agentmods.dev/badge/skills/sfrangulov/skill-graveyard/memory-graveyard.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00103 | $0.00514 |
| Opus 5 | $0.00051 | $0.00257 |
| Sonnet 5 | $0.00021 | $0.00103 |
| Haiku 4.5 | $0.00010 | $0.00051 |
Grade A, and why
memory-graveyard 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 7d 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.
What it actually says
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 onMEMORY.mdand 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.--applyto 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 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.
- 7d ago First seen · 33 lines · 103 tokens per session scan A bfd9f8016c13
memory-graveyard is a skill published in the GitHub repository sfrangulov/skill-graveyard (10 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 514 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
check-docs-consistency
Cross-reference project docs for drift, stale references, and contradictions. Outputs timestamped report. Discovers Markdown wherever it lives in the repo.
maintaining-session-continuity
Judgment for using cc-reload — carrying a session's working thread across a context reset via .reload/session.md: snapshot, arm, rehydrate after /clear, /compact, or auto-compaction. Use when saving state before a reset, handing off mid-task, holding working state as context fills, or working with /snapshot, /reload…
brain-log
Show brain sync and evolution history.
memory
Persistent, token-efficient project memory. When ON, maintains a .shob/memory/ folder of structured .md files so the full context of the project is NEVER lost across responses, sessions, or context compaction. Uses progressive disclosure — routes through a lightweight INDEX and loads only the files a task needs…
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…