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 SerenecoTech/agent-skills --skill handoffgit clone --depth 1 https://github.com/SerenecoTech/agent-skillsWrote 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/serenecotech/agent-skills/handoff)<a href="https://agentmods.dev/skills/serenecotech/agent-skills/handoff"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/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/serenecotech/agent-skills/handoff"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/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 | $0.00041 | $0.02553 |
| Opus 5 | $0.00020 | $0.01277 |
| Sonnet 5 | $0.00008 | $0.00511 |
| Haiku 4.5 | $0.00004 | $0.00255 |
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 8d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Write HANDOFF.md so a fresh agent can pick up in-flight work without re-deriving context. Pulls from three context sources: built-in user memory, per-project memsearch recall, and non-boilerplate project docs. The ▶ Resume This Work block at the top is the entry point the handoff-resume skill acts on to continue without re-prompting.
When to Use
- User says "handoff", "wrap up", "summarize for next session", invokes /handoff
- About to /clear, compact context, or end a session mid-task
- Context window approaching limit and work is unfinished
- Switching between agents/sessions on the same task
Proactively offer (do not auto-write) when context is clearly running low and the task is incomplete: "Want me to write a handoff before we continue?" Never write one without confirmation outside an explicit request.
Do NOT use for:
- Completed tasks (the diff/PR/commit is the handoff)
- One-shot questions
- Tasks already fully captured by memory entries
Where It Goes
- Default:
HANDOFF.mdin current working directory - If
HANDOFF.mdalready exists: create.claude/handoff/if missing, move existing file to.claude/handoff/handoff-<YYYYMMDD-HHMM>.md, then write the new one. Never silent overwrite. - Unsafe cwd (
~,/, anywhere outside an actual project): stop and ask for a path
Process
- Gather git state (parallel):
git statusgit diff --statgit log --oneline -10
- Archive existing
HANDOFF.mdper the rule above - Discover context sources (parallel):
- Built-in agent memory (if the harness provides one): the session's own memory directory — for Claude Code,
~/.claude/projects/<project-slug>/memory/*.md(skim theMEMORY.mdindex first). Skip if your harness has no file-based memory. - Project memsearch (capability, not files; optional): if
.memsearch/exists, memsearch is active. Don't enumerate or link the daily logs; instead derive 2-5 recall seed queries from this session's work for the next agent to search (optionally sanity-check withmemsearch search "<topic>"). - Project context docs: glob
**/*.mdin cwd, exclude boilerplate and build dirs (see below), surface anything non-standard
- Built-in agent memory (if the harness provides one): the session's own memory directory — for Claude Code,
- Extract from conversation:
- Original goal
- Done vs. not done
- Failed approaches — highest-value section, mandatory if any exist
- Decisions and why
- User preferences expressed this session
- Errors hit and how they resolved
- Cross-link, don't duplicate:
- Memory entries →
[[memory-slug]] - Project docs → relative path and one-line relevance
- Memory entries →
- Write
HANDOFF.mdusing the template - Verify by re-reading as if you were a fresh agent. Gaps? Fix them before declaring done.
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.
- 8d ago First seen · 218 lines · 41 tokens per session scan A 7cbaba22f92a
handoff is a skill published in the GitHub repository SerenecoTech/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 2,553 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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.