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 handoffgit 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)<a href="https://agentmods.dev/skills/alphaelements/handoff-mcp/handoff"><img src="https://agentmods.dev/badge/skills/alphaelements/handoff-mcp/handoff/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"><img src="https://agentmods.dev/badge/skills/alphaelements/handoff-mcp/handoff.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 | $0.00061 | $0.06125 |
| Opus 5.5 | $0.00024 | $0.02450 |
| Sonnet 5.5 | $0.00012 | $0.01225 |
| Haiku 4.5 | $0.00006 | $0.00613 |
Grade A, and why
handoff 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 yesterday.
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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff Skill
Session Start
- Call
handoff_load_context(uses current working directory). - If the project is not initialized, call
handoff_initwith the project name derived from the directory name. - If
paused_sessionsare returned, show them to the user (ID, summary, branch). To resume:handoff_load_context(session_id: "s-..."). To discard:handoff_save_context(close_session_id: "s-..."). - Establish an active session immediately — if
session_guidanceis present in the response (meaning no active session exists), callhandoff_save_contextwithsession_status: "active"before starting any work. Include inherited context from the previous session:summary: usesession_guidance.suggested_fields.summaryor write your own based on the previous session's summarydecisions,context_pointers,references: carry forward fromsession_guidance.suggested_fieldsif availablehandoff_notes: at minimum, asuggestionnoting what you plan to dochecklist: at minimum, one item noting session establishment This ensures that if the conversation is interrupted, the session state (what was being worked on, inherited decisions, file pointers) survives.
- Review the returned context:
- Suggestions first:
suggestionhandoff_notes (from current session orprevious_session) are the previous session's recommended next actions. Unless the user's request contradicts them, start executing from the first suggestion — do NOT re-verify work that the suggestion says is already done. - Tasks: check
in_progressandblockeditems first. - Decisions: note confidence levels —
unverifieditems may need revisiting. - Blockers: address these before starting new work.
- Handoff notes: pay attention to
cautionitems. - Context pointers: read these to rebuild mental context, but do NOT re-run tests or checks that the previous session already confirmed unless there are new changes since that session's commit.
- Project health:
trace_health(V-model coverage, suspects),suspect_summary,requirements_healthanddocs_healthcarry structured warnings (e.g.DIAG-R001).has_data: false(andsuspect_summary: null) means the V-model is not in use yet — see thehandoff-traceskill's "First-time setup" if the user wants it.
- Suggestions first:
- Briefly summarize the current state to the user and start working immediately from the suggestion — do not repeat completed verification.
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.
- yesterday Changed · +13 lines d22dd08d034b
- 3d ago Changed · +29 lines 19bae33a379e
- 10d ago Changed · +1 lines a78d27f93b53
- 14d ago Changed · +34 lines c1f29fe73aed
- 18d ago Changed · +2 lines 4b496c2f96d7
- 25d ago Changed · +3 lines 5dceafed8891
- 1mo ago First seen · 337 lines · 61 tokens per session scan A f1892ef04fb3
handoff is a skill published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 6,125 once invoked, about $0.0002 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.