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 kaisa-kucherenko/claude-code-flow --skill handoffgit clone --depth 1 https://github.com/kaisa-kucherenko/claude-code-flowWrote 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/kaisa-kucherenko/claude-code-flow/handoff)<a href="https://agentmods.dev/skills/kaisa-kucherenko/claude-code-flow/handoff"><img src="https://agentmods.dev/badge/skills/kaisa-kucherenko/claude-code-flow/handoff.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00130 | $0.01169 |
| Opus 5 | $0.00065 | $0.00584 |
| Sonnet 5 | $0.00026 | $0.00234 |
| Haiku 4.5 | $0.00013 | $0.00117 |
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff
Writes the state of the current work thread into a file the next session can start from — because answer quality degrades well before the context window is full, and a deliberate, writer-controlled handoff beats automatic summarization.
A handoff is the state of the task + instructions for the next executor — never a chronology of this session.
Files
- Name:
HANDOFF_<slug>.mdin the project root. Slug = issue number + short topic (HANDOFF_237_deploy.md) or topic alone (HANDOFF_pricing_banner.md) — readable at a glance, since several handoffs may coexist for parallel work threads. - One live handoff per work thread, updated in place. No date-stamped copies.
- Git hygiene: immediately add the filename to
.git/info/exclude(never.gitignore, never stage, never commit). Before any staging of adjacent files,git check-ignore -vthe handoff. Not a git repo → skip this step. - Delete the file when its task is fully closed (confirm with the user first).
Invocation
/handoff— no args: if exactly one handoff matches the session's current work thread, update it; none → create; several plausible → ask which one./handoff <slug|issue|topic>— explicit target.- Mid-session "add X to the handoff" — add X to the relevant section now, verbatim in meaning. Items the user explicitly names ("make sure X is in") MUST land in the file.
- "Is the handoff current?" — reread the file, diff it against the real session state, fix every stale point, then confirm.
Structure
# Handoff: <issue #N / topic> — <last updated>
Branch: <branch> @ <short-hash> | Source session: <session id, best effort>
## NEXT
<the new session's concrete first step; then a numbered plan, WHAT-level>
## State / Result
<result first, with numbers where they exist; then git: commits with hashes,
pushed/NOT pushed, what to commit / what NOT, how to restore anything deleted>
## Done
<one terse block per closed stage: hash, essence, who reviewed,
what was consciously deferred (follow-up, not pre-merge)>
## Ruled out — do not reopen
<dead ends and dropped hypotheses WITH THE REASON they are dead ends>
## Don't forget
<env gotchas, sharp details, runnable commands with checkpoints
to verify the environment is alive>
## Artifacts
<issue/PR/ADR URLs, key files with their role; durable knowledge — as a link
to a reference doc or memory, never as a copy>
## Open questions
<decision points AS QUESTIONS — or an explicit "None">
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 · 106 lines · 130 tokens per session scan A 17747f17444f
handoff is a skill published in the GitHub repository kaisa-kucherenko/claude-code-flow (19 stars, last pushed 12d ago), licensed MIT. It adds 130 tokens to every session and 1,169 once invoked, about $0.0006 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 2026-08-30.
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.