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 agentmods add skills/flurdy/agent-skills/handoffsnpx skills add flurdy/agent-skills --skill handoffsgit clone --depth 1 https://github.com/flurdy/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/flurdy/agent-skills/handoffs)<a href="https://agentmods.dev/skills/flurdy/agent-skills/handoffs"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/handoffs.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 | $0.00055 | $0.07607 |
| Opus 5 | $0.00028 | $0.03803 |
| Sonnet 5 | $0.00011 | $0.01521 |
| Haiku 4.5 | $0.00006 | $0.00761 |
Grade B, and why
handoffs scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
_⚠️ {unresolved} handoff(s) could not be matched to any repo or directory (recorded path is invalid or gone). Run `grep -L "Repo root:" ~/.claude/handoffs/*.md` to find them._ How it starts
The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoffs — Pick a saved session to resume
Browse handoff files written by /wrap-up (in ~/.claude/handoffs/) and pick one to resume. Companion to /wrap-up (the writer) and /landscape (the morning orienter).
When to use
- Starting a session and wanting to pick up a thread from a previous one.
- After
/landscapeflagged that recent handoffs exist for this repo. - Searching for an older thread —
ls ~/.claude/handoffs/is grep-friendly, but this skill renders the metadata table.
Not sure whether to resume a handoff or start fresh work? That's a morning orientation call, not a handoffs call — run
/landscapefirst. Its**Next:**line arbitrates resume-a-handoff vs/next safefrom the full picture (Jira, PRs, beads, working copy). Come here once you've decided to resume a thread.
What it does
- List handoffs across all repos, with per-repo counts.
- Fully detail handoffs in the current repo as a pickable table, flagging which are superseded by a newer handoff, done (PR merged, all beads closed, or Jira ticket Done), or stale (branch gone / PR closed).
- Summarise handoffs in other repos (count per repo, not full listing).
- Optionally archive confirmed superseded, done, stale, or assisted-review handoffs to keep the picker focused, including safe workspace-member rows through separate per-repo confirmation.
- Prompt you to pick one — only handoffs for the current repo and workspace members are pickable.
- On pick, render the resume block inline and surface the
cdif the recorded worktree differs from pwd.
Important — what this skill cannot do
- It cannot resume for you. It surfaces the resume block; you read it and act on the next step.
- It cannot rename the session for you. On load it prints the active client's paste-ready command (§5):
/name {slug}in Pi and/rename {slug}in Claude Code. Only you typing it triggers a rename. - It cannot pick handoffs from unrelated repos. That is a deliberate guard — running commands against the wrong repo is the failure mode it prevents. To resume a handoff in an unrelated repo,
cdthere and run/handoffsagain. Exception: repos in the same multi-repo workspace are listed and pickable (§2b/§4b), because from a workspace root they'd otherwise be invisible; picking one requires an explicitcdbefore any repo-scoped command runs. - It never deletes handoff files. The opt-in archive steps (§3b–§3e) only move explicitly confirmed candidates into
~/.claude/handoffs/archive/— they stay on disk and greppable.
What ships with it
4 files 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.
- 5d ago First seen · 455 lines · 55 tokens per session scan B e04c46b97706
handoffs is a skill published in the GitHub repository flurdy/agent-skills (8 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 7,607 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…