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/randynorthrup/teamwork-skill/teamwork-handoffnpx skills add RandyNorthrup/teamwork-skill --skill teamwork-handoffgit clone --depth 1 https://github.com/RandyNorthrup/teamwork-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/randynorthrup/teamwork-skill/teamwork-handoff)<a href="https://agentmods.dev/skills/randynorthrup/teamwork-skill/teamwork-handoff"><img src="https://agentmods.dev/badge/skills/randynorthrup/teamwork-skill/teamwork-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 5.1 | $0.00091 | $0.00897 |
| Opus 5 | $0.00046 | $0.00449 |
| Sonnet 5 | $0.00018 | $0.00179 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
teamwork-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 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.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teamwork handoff
Create or update the canonical .teamwork/ payload. Keep filenames stable. Treat live repository evidence as authoritative and memory as potentially stale.
Workflow
- Resolve repository root and read all applicable project instructions before changing files.
- Identify current agent and harness. Use explicit, honest names; use
unknownwhen unavailable. - Define
<skill-dir>as the directory containing thisSKILL.md. Select a Python 3.11+ executable (python3,py -3.11, or an absolute interpreter path). Run the bundled script from any working directory and request structured output:
<python-3.11+> "<skill-dir>/scripts/teamwork_payload.py" prepare --repo "<repo-root>" --agent "<agent>" --harness "<harness>" --json
- Read
.teamwork/SOURCES.md. Inspect only candidates relevant to this project. Also inspect live code, repository docs, VCS status, and test artifacts needed to establish current truth. - Update existing payload documents in place:
STATUS.md: exact outcome, completed/in-progress work, blockers, and one concrete safe resume action.PROJECT.md: purpose, boundaries, architecture, important paths, and proven commands.NEXT_STEPS.md: ordered actions and observable done criteria.DECISIONS.md: stable decision IDs, reasons, and evidence.VALIDATION.md: narrow claims, exact commands/artifacts, results, times, and gaps.CONTEXT.md: project-relevant synthesis from instructions and memory with source IDs and freshness caveats.ENVIRONMENT.md: dependencies, services, permissions, and approval boundaries. Preserve generated markers.
- Never add session-numbered duplicates. Preserve useful existing content and revise stale facts. Let preparation regenerate
WORKTREE.md,SOURCES.md,context-index.json,teamwork-manifest.schema.json, generated Markdown blocks, and manifest facts. - Exclude credentials,
creds.md, secrets, tokens, private keys, unrelated personal data, raw conversations, binaries, build output, and large logs. Never stage or commit.teamwork/. - Seal only after replacing every required placeholder:
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 · 52 lines · 91 tokens per session scan A cd2c9185dabf
teamwork-handoff is a skill published in the GitHub repository RandyNorthrup/teamwork-skill (1 stars, last pushed 13d ago), licensed MIT. It adds 91 tokens to every session and 897 once invoked, about $0.0005 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
kanwas-cli
Sync local files with a Kanwas workspace using the kanwas CLI. Use when the user wants to pull workspace content into the repo, push local edits back, or bulk-import markdown files from disk. Workspaces are trees of markdown notes organized into canvases (directories).
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.
create-coordclaw-team
A Skill for creating a CoordClaw multi-agent collaborative team. Through an 8-step standardized process, from requirement gathering to team validation, rapidly build a complete AI team.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.