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/raulvidis/openclaw-multi-agent-kit/coding-handoffnpx skills add raulvidis/openclaw-multi-agent-kit --skill coding-handoffgit clone --depth 1 https://github.com/raulvidis/openclaw-multi-agent-kitWrote 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/raulvidis/openclaw-multi-agent-kit/coding-handoff)<a href="https://agentmods.dev/skills/raulvidis/openclaw-multi-agent-kit/coding-handoff"><img src="https://agentmods.dev/badge/skills/raulvidis/openclaw-multi-agent-kit/coding-handoff.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 | $0.00046 | $0.00522 |
| Opus 5 | $0.00023 | $0.00261 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
coding-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 4d 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.
What it actually says
Install
Copy to agents/<coder>/skills/coding-handoff/SKILL.md. Requires agents configured with sessions_send for inter-agent handoffs.
Coding Handoff Skill
Required Handoff Envelope
Always send handoff messages using:
fromtotask_idpriority(P1/P2/P3)summarycontext(branch, commit, environment)done_when(checklist)deliver_to(topic/channel target)
Lifecycle
- Post
ACKquickly with ownership and ETA. - Execute scoped checks.
- Post
DONEwith evidence (tests, logs, diff summary) orBLOCKEDwith explicit unblock requirements.
PR Readiness Gate
Before DONE, verify:
- lint/type/test status
- regression risk notes
- rollback note
- unresolved TODOs list
If any gate fails, return BLOCKED, not DONE.
Branch Naming
Branches created during a coding handoff should encode origin and task for traceability:
<agent-id>/<task_id>-<short-slug>
Examples: coder/build-142-coupon-rounding, coder/auth-jwt-001-refresh-token.
This pattern makes it easy to grep history for an agent's work, link branches back to task IDs in topic messages, and reason about cleanup. Avoid bare slugs (fix-bug) or timestamp-only branches — they don't carry provenance.
Do not commit or push unless the task explicitly asks for it. The DONE message references the local branch; pushing/PR-opening is a separate explicit step.
Scope Discipline
A handoff is bounded by done_when. Anything outside that scope:
- Unrelated bug spotted while working: mention it in the DONE message under
Risks/Notes. Do not fix it in the same change. - Adjacent refactor that "would be nice": skip. File a follow-up task instead.
- Test that fails for unrelated reasons: flag it, route around it, don't paper over it.
Scope creep turns a 1-hour handoff into a 6-hour mystery. The handoff format exists to keep work bounded — respect it.
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.
- 4d ago First seen · 66 lines · 46 tokens per session scan A 41cd443e3118
coding-handoff is a skill published in the GitHub repository raulvidis/openclaw-multi-agent-kit (395 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 522 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 2026-08-30.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
sap-transport-overview
System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
finn-spec
Interview the user about a raw idea until confident, then file a build-ready issue in Linear. Use when asked to run Finn-loop's spec interview, draft a queue-ready issue, or plan a feature. Interactive — requires the user present; never run unattended.