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 daveangulo/twining-mcp --skill twining-handoffgit clone --depth 1 https://github.com/daveangulo/twining-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/daveangulo/twining-mcp/twining-handoff)<a href="https://agentmods.dev/skills/daveangulo/twining-mcp/twining-handoff"><img src="https://agentmods.dev/badge/skills/daveangulo/twining-mcp/twining-handoff.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 | $0.00041 | $0.00800 |
| Opus 5 | $0.00020 | $0.00400 |
| Sonnet 5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
twining-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 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twining Handoff — Agent and Session Handoff
You're transferring work to another agent, ending a session with incomplete work, or approaching context window limits. Create a handoff the next agent (or your next session) can actually continue from.
Pattern change (#33): the structured
twining_handoff/twining_acknowledgetools are deprecated and scheduled for removal in v3. Field data across real projects showed zero calls to them, while every project that handed off well did it with rich committed markdown docs. This skill now teaches that pattern: a committed doc + a blackboard pointer.
When to Invoke
- When completing partial work that another agent should continue
- When delegating a subtask to a specialized agent
- When approaching context window limits and need to continue in a new session
- When the user explicitly asks to hand off or pass work along
For a session that simply finished its work, twining_record (Gate 2) is the handoff — don't write a doc for completed work with nothing pending.
Workflow
1. Write the handoff document
Create a markdown file under the project's docs or planning area (follow the project's existing convention; docs/handoffs/YYYY-MM-DD-<topic>.md is a good default). Include:
- State of the work — what's done, what's in flight, what's untouched
- Next steps — concrete, ordered, with enough context to start cold
- Decisions and constraints — link Twining decision IDs; don't restate rationale the store already holds
- Gotchas — anything that will waste the next agent's first hour
- Verification — how to check the current state actually works (test commands, expected output)
twining_export (scope-limited) and twining_summarize are useful raw material for the doc — export gives full entries and decisions, summarize gives the compact overview. Both require tools.full_surface: true; on a default install, twining_assemble on the handoff scope gives you the same briefing the next agent will receive, which is the right thing to write the doc against anyway.
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 · 68 lines · 41 tokens per session scan A 7ca8099989f6
twining-handoff is a skill published in the GitHub repository daveangulo/twining-mcp (7 stars, last pushed 11d ago), licensed MIT. It adds 41 tokens to every session and 800 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
autograph
Schema-as-code enforcement for any Obsidian vault. Zero hardcoded domains. Use when creating vault cards, checking vault health, running schema compliance, deduplicating entities, generating MOC indexes, running decay cycles, bootstrapping a vault, fixing wikilinks, finding orphans or backlinks, extracting entities…
dbrain-processor
Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.
braindb-agent
Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.