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 lttr/claude-marketplace --skill handoffgit clone --depth 1 https://github.com/lttr/claude-marketplaceWrote 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/lttr/claude-marketplace/handoff)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/handoff"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/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/lttr/claude-marketplace/handoff"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/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 | $0.00020 | $0.00770 |
| Opus 5 | $0.00010 | $0.00385 |
| Sonnet 5 | $0.00004 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
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 11d 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.
Write ~/.claude/custom-handoff.md (resolve ~ to the user's home directory) summarizing current work so the next Claude session can pick up where this one left off.
Focus argument
$ARGUMENTS, when present, is the user's steer for what the handoff should emphasize. Let it bias every section — GOAL, RECENT CONCLUSIONS, and NEXT especially — toward that thread of the work. Trim or drop details unrelated to the focus, and let NEXT lead with the focused action. Still keep # ORIGINAL PROMPT verbatim; the focus reshapes emphasis, not the recorded intent. When $ARGUMENTS is empty, weight sections as the rules below describe.
Steps
- Run
trash-put ~/.claude/custom-handoff.md 2>/dev/null || trueto remove any prior handoff (ignore error if file absent). - Write fresh content per template. No merge, no preserve.
Template
# ORIGINAL PROMPT
<the user's opening prompt from this conversation, verbatim if short; otherwise a one-to-two-sentence summary that preserves the ask>
# GOAL
<one line: what we're doing now>
# DONE
- <thing done>
- <thing done>
# RECENT CONCLUSIONS
- <decision, agreement, or insight from last few turns — what shifted the plan>
- <open question raised at end, still unanswered>
# NEXT
<concrete next action — derived from RECENT CONCLUSIONS, not stale earlier intent>
# WATCH OUT
<gotchas; omit section if none>
# SUGGESTED SKILLS
- `/plugin:skill` — <why the next session should invoke it>
Rules
- Terse, scannable, under 250 words total.
# ORIGINAL PROMPTanchors intent across sessions — do not drop it even if the work has drifted.- Weight the final turns heaviest. Conclusions, decisions, course corrections, and open questions from the last few messages drive
NEXT. Early-conversation context is backdrop, not the lead. # RECENT CONCLUSIONScaptures what was just decided or learned — not a re-summary of DONE. If the last turns only restated earlier work, leave it empty rather than padding.- If user and assistant disagreed or pivoted near the end, record the resolution (or that it's unresolved).
- Use file paths, not descriptions (e.g.
src/auth.ts:42, not "the auth file"). - No prose narration ("we decided to...").
- Redact secrets. API keys, tokens, passwords, connection strings, and personal data never land in the file. Name where a value lives (
.env:DATABASE_URL) instead of the value itself. - Point, don't copy. Anything already captured in a spec, ticket, ADR, commit, or diff gets referenced by path or id — never re-summarized here.
# SUGGESTED SKILLSnames the skills the next session should invoke for this work, with a few words on why each. Omit the section when nothing specific applies.- Omit
# WATCH OUTwhen there are no gotchas.
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.
- 11d ago First seen · 68 lines · 20 tokens per session scan A 6b6c39cc4027
handoff is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 770 once invoked, about $0.0001 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
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
ima-skill
A unified IMA skill for managing personal notes and knowledge bases through the platform's APIs.
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.
config-evals
Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…
qqexmail
An email skill for Tencent Enterprise Email, a business email service, using the standard IMAP and SMTP protocols to read and send messages.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.