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/recallnpx skills add AEndrix03/Graft --skill recallgit 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/recall)<a href="https://agentmods.dev/skills/aendrix03/graft/recall"><img src="https://agentmods.dev/badge/skills/aendrix03/graft/recall.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 | $0.00097 | $0.01190 |
| Opus 5 | $0.00048 | $0.00595 |
| Sonnet 5 | $0.00019 | $0.00238 |
| Haiku 4.5 | $0.00010 | $0.00119 |
Grade A, and why
recall 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 4d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
recall — Smart, escalating search of the memory graph
graft exposes three search modes and they have different sweet spots:
| Mode | Best when |
|---|---|
query |
The user is asking for the answer to a specific problem. Cache-style gating: STRONG / WEAK / MISS. |
retrieve |
The user is exploring; they want top-K hybrid (lexical + semantic) ranked results. |
explore |
The user names a topic + keywords; they want to walk the graph from there. |
This skill orchestrates them. Do not ask the user which mode — pick based on the question.
Argument shape
The user invokes you with a free-form question or topic.
| Pattern | Strategy |
|---|---|
| "how do I X" / specific problem statement | query → escalate to retrieve if MISS. |
| "what do we know about X" / open-ended topic | retrieve --top-k 10. |
| "X with Y" / topic with keyword anchors | explore "X" --keyword Y. |
| "find related to " | explore from that node's keywords (read via get). |
| "recent stuff about X" | retrieve and re-rank by node created_at if shown. |
If the user provides a --keyword style flag, respect it.
Cascade flow
┌─── STRONG → done; cite + use ───┐
graft query <Q> ──────────────┤ │
├─── WEAK → graft get <id> │── present
│ then continue │
└─── MISS → graft retrieve <Q>│
if 0 useful results: │
graft explore <Q>│
--keyword <inferred>│
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.
- 4d ago First seen · 115 lines · 97 tokens per session scan A 2b1eb6272fea
recall is a skill published in the GitHub repository AEndrix03/Graft (11 stars, last pushed 12d ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,190 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 2026-08-30.
Other skills, from other repositories
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…
memory-recall
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this…
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.
prep
Session wrap-up. Update memories, check plans, review git state, check inbox, flag loose ends. Use before closing a session or compacting context.