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 agentmods add skills/aendrix03/graft/graft-initnpx skills add AEndrix03/Graft --skill graft-initgit 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/graft-init)<a href="https://agentmods.dev/skills/aendrix03/graft/graft-init"><img src="https://agentmods.dev/badge/skills/aendrix03/graft/graft-init.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 | $0.00119 | $0.01533 |
| Opus 5 | $0.00060 | $0.00766 |
| Sonnet 5 | $0.00024 | $0.00307 |
| Haiku 4.5 | $0.00012 | $0.00153 |
Grade A, and why
graft-init 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 6d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
graft-init — Configure graft behavior in CLAUDE.md
This skill writes a short, opinionated instruction block into a CLAUDE.md so future sessions automatically use the graft skills (recall, memoryze, learn, memory-audit) according to the user's preferences. The block is fenced with HTML markers so re-running the skill cleanly replaces it.
Flow
Run the four AskUserQuestion calls in order. Stop immediately if the user picks exit on Q1. Pass multiSelect: false for all four. Defaults are marked (recommended) in the option labels — do not auto-pick, the user must choose.
Q1 — Scope
question: "Where should the graft configuration live?"
header: "Scope"
options:
- { label: "Global (recommended)", description: "Write to ~/.claude/CLAUDE.md — applies to every project on this machine." }
- { label: "Local", description: "Write to ./CLAUDE.md in the current repo — applies only here, takes precedence over global." }
- { label: "Exit", description: "Cancel without changing anything." }
If the user picks Exit, reply with one short line ("Cancelled, nothing changed.") and stop.
Q2 — Caching
question: "Enable cache-first lookups?"
header: "Caching"
options:
- { label: "Enable (recommended)", description: "Use `graft query` first (fast, exact-match cache) before escalating to retrieve. Cuts latency on repeat questions." }
- { label: "Disable", description: "Always go straight to retrieve. Slower but always semantic." }
Q3 — Retrieve strategy
question: "When should the agent search the graph during a conversation?"
header: "Retrieve"
options:
- { label: "Every interaction on cache miss (recommended)", description: "Run `/recall` on any non-trivial turn whenever the cache lookup misses. Maximum coverage." }
- { label: "Only at conversation start", description: "One opening recall to load context, then rely on conversation memory." }
- { label: "Never", description: "Do not retrieve automatically — only when the user explicitly 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.
- 6d ago First seen · 127 lines · 119 tokens per session scan A 271160d2878c
graft-init is a skill published in the GitHub repository AEndrix03/Graft (11 stars, last pushed 13d ago), licensed Apache-2.0. It adds 119 tokens to every session and 1,533 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
Context Doctor
Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.
memanto-companion
Inspect and manage the cross-session engineering memory that Memanto maintains for your Claude Code skills. Use when the user asks what Memanto remembers, wants to see their engineering profile, manually recall context for a skill, or store a decision. The automatic lifecycle hooks handle capture/injection on their…
system-monitor
Monitor system health: CPU, memory, disk, processes, and network. Alert on thresholds via any channel.
ov-experience-memory
Retrieve and apply OpenViking Experience memories through the Agent runtime's generic OpenViking search and read tools. Use before or during executable, multi-step, or tool-based work such as coding, file or data changes, configuration, deployment, workflow execution, and failure recovery when prior operational…
mnemon
Persistent memory CLI for LLM agents. 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.