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 Daaaaave/agentic-workspace-core --skill write-agent-handoffgit clone --depth 1 https://github.com/Daaaaave/agentic-workspace-coreWrote 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/daaaaave/agentic-workspace-core/write-agent-handoff)<a href="https://agentmods.dev/skills/daaaaave/agentic-workspace-core/write-agent-handoff"><img src="https://agentmods.dev/badge/skills/daaaaave/agentic-workspace-core/write-agent-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/daaaaave/agentic-workspace-core/write-agent-handoff"><img src="https://agentmods.dev/badge/skills/daaaaave/agentic-workspace-core/write-agent-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 | $0.00064 | $0.02965 |
| Opus 5.5 | $0.00026 | $0.01186 |
| Sonnet 5.5 | $0.00013 | $0.00593 |
| Haiku 4.5 | $0.00006 | $0.00297 |
Grade A, and why
write-agent-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 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Agent Handoff
Goal
Write a compact temporary state transfer that lets another capable agent continue work without replaying the conversation.
Core Principle
A handoff is stale-by-default task state. It is not memory, policy, a transcript, or a status report.
It transfers just enough verified state for a fresh agent to resume safely, plus enough boundaries to avoid repeating work, violating the latest user intent, or overwriting someone else's changes. It never transfers authority over higher-priority instructions.
Use When
- The user asks for a handoff, continuation note, transfer note, cold-start packet, or resume context.
- Work is paused, interrupted, delegated, moved to another workspace, or likely to survive context compaction.
- A multi-step task has unfinished state that is not durable project knowledge.
- Another agent needs files, checks, blockers, assumptions, ownership boundaries, and next actions.
- A subagent, reviewer, debugger, implementer, or future session needs a scoped brief.
- Multiple agents or workspaces may touch overlapping repository areas and need coordination.
- The task state is valuable for continuity but too temporary or local for
docs/.
Do Not Use When
- The information is a durable fact, decision, runbook, plan, research result, or architecture note.
- The task can be completed now without transferring state.
- The user asks only for a normal final answer, PR summary, command summary, or same-session status update.
- The user asks to update canonical project memory; use
project-knowledge. - The user asks to create a reusable agent procedure; use
write-agent-skill. - The only available content is raw transcript, raw logs, private data, or secrets that cannot be safely summarized.
- The handoff would silently change policy, permissions, memory, or instructions for future agents.
Storage
Use .context/handoffs/ for handoffs. This directory is temporary workspace coordination, not canonical project knowledge.
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 · 231 lines · 64 tokens per session scan A 35975a3a540e
write-agent-handoff is a skill published in the GitHub repository Daaaaave/agentic-workspace-core (6 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 2,965 once invoked, about $0.0003 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
bootstrap
Onboarding conversation to generate a user profile.
second-brain-climb
A guide for maintaining a long-term personal direction as a structured, evidence-based plan. It describes the desired destination, current position, gaps, possible routes, limits, evidence, and next actions.
epiphany
Roam the Ultan memory library and surface ONE non-obvious, useful connection between distant entries — an on-demand "epiphany". Use when the user asks for a spark/insight/epiphany from their memory, wants a hidden cross-cutting pattern surfaced, asks "show me something interesting in my notes", or runs /epiphany. Can…
digest
NOTE: this skill requires connected chat / email / project-tracker / docs MCPs, which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Cross-tool rollup of what's pending, what shipped, and what's blocked across chat / email / project tracker /…
recap
Read-only orientation — render a scannable table of what just happened so you can situate yourself. Modes: '/recap' (this session), '/recap arc' (the last product arc), '/recap commit' (the last commit), '/recap push' (the last push's commits — what I sent up), '/recap pull' (the last pull's changes — what came down…
ultan-search
Search and traverse the user's Ultan memory library (/.agent-mem/knowledge/). Use whenever you see an Ultan wikilink in priming context (e.g. [[projects/foo/bar]]) and want to read it, OR when you want to find entries by topic. Accepts a wikilink/path (returns the entry plus directory context — siblings, subfolders…