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 alphaelements/handoff-mcp --skill handoff-memorygit clone --depth 1 https://github.com/alphaelements/handoff-mcpWrote 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/alphaelements/handoff-mcp/handoff-memory)<a href="https://agentmods.dev/skills/alphaelements/handoff-mcp/handoff-memory"><img src="https://agentmods.dev/badge/skills/alphaelements/handoff-mcp/handoff-memory/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/alphaelements/handoff-mcp/handoff-memory"><img src="https://agentmods.dev/badge/skills/alphaelements/handoff-mcp/handoff-memory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00096 | $0.02062 |
| Opus 5.5 | $0.00038 | $0.00825 |
| Sonnet 5.5 | $0.00019 | $0.00412 |
| Haiku 4.5 | $0.00010 | $0.00206 |
Grade A, and why
handoff-memory 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 1mo 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff Memory Skill
When to use
- The user says "メモリ保存", "これ覚えて", "知見を残して", "remember this", "save this as a memory"
- The user asks "過去の知見を確認", "recall", "what do we know about X"
- You discover a reusable lesson, recurring NG pattern, or project-specific convention worth persisting across sessions
- Post-incident feedback or investigation results should be captured
- Existing memories need merging, updating, or pruning
- Session start — run cleanup to keep the memory store healthy
Granularity Rule
One memory = one piece of knowledge. Do not bundle multiple unrelated lessons into a single memory. Each memory should be independently searchable and independently deletable. If two ideas always travel together, save them together; if they could be relevant in different contexts, split them.
Saving a Memory
Call handoff_memory_save with:
| Param | Required | Description |
|---|---|---|
text |
yes | The memory content. Be specific and actionable — "always use X because Y", not "X is important" |
kind |
no (default: lesson) |
One of: lesson (something learned), rule (a mandated practice), convention (an agreed pattern), gotcha (a non-obvious trap) |
scope_paths |
no | Path prefixes this memory applies to (e.g. ["src/storage/", "src/mcp/handlers/"]). Memories with matching scope_paths get a relevance boost when the user edits files under those paths |
tags |
no | Free-form tags for searchability (e.g. ["atomic-write", "config"]). Tags are included in the similarity index |
force |
no | true to skip near-duplicate detection and save unconditionally |
merge_into |
no | ID of an existing memory to overwrite with merged content (see Merging below) |
absorb_ids |
no | IDs of memories to delete after merging into the target |
scope_paths Best Practices
- Use directory-level substrings, not full file paths:
"src/storage/"not"src/storage/config.rs". The matching is substring-based (file_path.contains(scope)), so"storage/"will match any file whose path contains that segment - Scope broadly enough to catch related files, narrowly enough to avoid noise
- A memory with no scope_paths relies purely on text similarity for injection — fine for project-wide rules, but file-specific gotchas benefit from scoping
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 160 lines · 96 tokens per session scan A 7d24917111c4
handoff-memory is a skill published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 2,062 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.