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 daisuke-ai/write-goal-handoff-skill --skill write-goal-handoffgit clone --depth 1 https://github.com/daisuke-ai/write-goal-handoff-skillWrote 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/daisuke-ai/write-goal-handoff-skill/write-goal-handoff)<a href="https://agentmods.dev/skills/daisuke-ai/write-goal-handoff-skill/write-goal-handoff"><img src="https://agentmods.dev/badge/skills/daisuke-ai/write-goal-handoff-skill/write-goal-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/daisuke-ai/write-goal-handoff-skill/write-goal-handoff"><img src="https://agentmods.dev/badge/skills/daisuke-ai/write-goal-handoff-skill/write-goal-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 | $0.00089 | $0.01005 |
| Opus 5 | $0.00044 | $0.00502 |
| Sonnet 5 | $0.00018 | $0.00201 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
write-goal-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 10d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Goal Handoff
Overview
Create a handoff document that a fresh AI agent can execute through /goal without guessing architecture, scope, order, or completion criteria. Keep the /goal text short and put the detailed contract in Markdown.
Workflow
- Inspect the repo or source artifacts before writing. Read project instructions, existing handoff docs, relevant specs, current diffs/status, and named reference implementations.
- Separate the short
/goallauncher from the full handoff. The launcher should fit comfortably under 3500 characters and point to the Markdown file as the source of truth. - Write the handoff as an execution contract, not a brainstorming plan. Include objective, authority, exact scope, non-goals, phase order, hard rules, verification gates, completion criteria, and report format.
- Make every phase independently checkable. Each phase needs deliverables, expected files or modules, required tests, grep/file-existence checks when useful, and pass/fail criteria.
- Save the handoff to a Markdown file. Use an existing project handoff location if one exists; otherwise prefer
docs/handoffs/YYYY-MM-DD-<slug>.mdfor repo work ormktemp -t goal-handoff-XXXXXX.mdfor temporary cross-project handoffs. - Final response should include the handoff path and the exact short
/goallauncher to paste.
Goal Launcher Rules
Write a launcher block that names the outcome, references the handoff path or attachment, and states that completion requires the handoff's verification gates. Do not duplicate the whole handoff in /goal.
Use this shape:
/goal Execute <handoff title> from <handoff path>.
Treat that handoff as the source of truth. Complete phases in order, obey all hard rules, run every verification gate, update docs where required, and return the final implementation report requested in the handoff. The goal is complete only when all listed completion criteria pass or an explicit blocker is reported with evidence.
What ships with it
2 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.
- 10d ago First seen · 67 lines · 89 tokens per session scan A 300dc325ba5b
write-goal-handoff is a skill published in the GitHub repository daisuke-ai/write-goal-handoff-skill (2 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 1,005 once invoked, about $0.0004 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
handoff
Use when managing a two-session handoff — inspecting, picking up, or reviewing a committed handoff package produced by a session=two scope run. The operator interface over the cross-environment handoff lifecycle (plan in one session, build in another, review back in the first). Trigger with /hyperflow:handoff, "list…
design-import
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…
design-ship
One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…
silicon-steward
A planning guide for coordinating work between a person and a coding agent. It turns required information, resources, feedback, actions, and handoffs into explicit checklists and protocols.
summarize
A guide for turning conversations, logs, documents, or investigation notes into short, action-oriented summaries. It requires conclusions to be tied to available evidence and distinguishes confirmed facts from items still needing confirmation.
chatbot
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is building-agents), NOT a human answering one ticket…