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 AEndrix03/Graft --skill memory-auditgit clone --depth 1 https://github.com/AEndrix03/GraftWrote 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/aendrix03/graft/memory-audit)<a href="https://agentmods.dev/skills/aendrix03/graft/memory-audit"><img src="https://agentmods.dev/badge/skills/aendrix03/graft/memory-audit/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/aendrix03/graft/memory-audit"><img src="https://agentmods.dev/badge/skills/aendrix03/graft/memory-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 52 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 | $0.00144 | $0.01740 |
| Opus 5.5 | $0.00058 | $0.00696 |
| Sonnet 5.5 | $0.00029 | $0.00348 |
| Haiku 4.5 | $0.00014 | $0.00174 |
Grade A, and why
memory-audit 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 14d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-audit — Keep the graph true, without bothering the user
The graph rots like any knowledge base: the code moves on and a note goes stale, the same fact gets saved twice, a newer decision replaces an older one. Graft finds these cases and hands them to you as candidates with their evidence; you decide each one against the repository as it is now, and apply the decision with one narrow command. The user installed Graft so they would not have to curate memories by hand: resolve on your own, and only surface what is irreversible or genuinely ambiguous.
Every action below is recorded in graft maintain log and is reversible with restore until the retention window ends (retire purges after maintenance.retention_days, default 30). Never use graft delete in this skill: it is immediate and permanent.
1. Is anything due?
graft maintain status
Cheap (no embedding). Read recommended:
apply-safe→ step 2.scanorresolve→ step 3.- empty → nothing to maintain; skip to the report (step 5) if the user asked for an audit, otherwise stop here.
When the user explicitly asked for an audit, run steps 2-3 anyway.
2. Mechanical cleanup
graft maintain apply-safe
Safe by construction: expired nodes, orphan rows, ANALYZE, retired nodes past retention, and exact duplicates (same title and body) collapsed onto the oldest copy. Nothing to decide; note the counts for the report.
3. Adjudicate candidates
Run it from the repository the memories describe, so changed / removed file sources are detected (or pass --root <repo>):
graft maintain scan --limit 20
Candidates come most urgent first. For each one:
- Read the nodes:
graft get <id_hex>(the candidate already shows titles, states and dates). - Read the evidence it names: the file in
signals.sources[].locator, the code or docs the note talks about, the other note of the pair. - Decide, then apply exactly one action:
graft maintain resolve <candidate-id> --action <action> [--by <id>] [--node <id>] --note "<one line: why>"
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.
- 14d ago Changed · -14 lines · +19 tokens per session c9d5a4bd0620
- 1mo ago First seen · 138 lines · 125 tokens per session scan A 73bedf4159ca
memory-audit is a skill published in the GitHub repository AEndrix03/Graft (37 stars, last pushed 11d ago), licensed Apache-2.0. It adds 144 tokens to every session and 1,740 once invoked, about $0.0006 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
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent graph-based memory. Recall context before responding, remember insights after. Each group has private memory; global memory is read-only.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for Hermes Agent. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.