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 JinPLu/Teamwork --skill teamwork-initgit clone --depth 1 https://github.com/JinPLu/TeamworkWrote 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/jinplu/teamwork/teamwork-init)<a href="https://agentmods.dev/skills/jinplu/teamwork/teamwork-init"><img src="https://agentmods.dev/badge/skills/jinplu/teamwork/teamwork-init/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/jinplu/teamwork/teamwork-init"><img src="https://agentmods.dev/badge/skills/jinplu/teamwork/teamwork-init.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 | $0.00036 | $0.00494 |
| Opus 5.5 | $0.00014 | $0.00198 |
| Sonnet 5.5 | $0.00007 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
teamwork-init 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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teamwork Init
Init adds one small managed block to the project's agent instruction file, plus the small import bridge a host needs to read that block. It creates no document database, schema, case directory, runtime state, or migration path.
Method
- Resolve a trustworthy Teamwork package source: read
~/.teamwork/install.jsonroot; use that path if it containsVERSION,skills/, andinstall.sh. If the pointer is missing or invalid, ask the user for the repository path. Do not search the home directory. Then resolve the authorized project root and read its instruction hierarchy. - Preserve all user-owned content outside the Teamwork managed markers.
- Run
./install.sh --project-root <root> init-projectfrom that resolved package source. - Re-read the resulting project instruction surfaces and report each exact changed surface or the observed no-op.
The command is idempotent: an existing Teamwork block is refreshed in place, and an instruction file that already reaches the block is left unchanged. Ambiguous duplicate markers or an unreadable target are real file-ownership conflicts; version, schema, readiness, and agent availability are not Init preconditions.
Init never creates an empty docs/teamwork tree. Document directories appear only
when a Skill checkpoint asks Writer to write a file there. When Init observes
no change, report the observed no-op. Create or update a durable report only
when that result is reusable or the user explicitly requests it.
Persistence
Persistence is optional. Write a report only when the observed result is reusable
across sessions or the user explicitly requests it. When that optional
checkpoint fires, write the document in the same response cycle from
references/report.md at
docs/teamwork/reports/<slug>.md (reuse the existing path for the
same project-operation identity). Optional triggers: Init completes with an
observed AGENTS.md change worth reusing; Init stops on a real file-ownership
conflict worth reusing; or a no-op result is reusable or explicitly requested.
Init never blocks on a report.
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.
- 1mo ago First seen · 47 lines · 36 tokens per session scan A 51265c5d415c
teamwork-init is a skill published in the GitHub repository JinPLu/Teamwork (12 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 494 once invoked, about $0.0001 per session on Opus 5.5. 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
oma-scholar
Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…