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/jinplu/teamwork/teamwork-researchnpx skills add JinPLu/Teamwork --skill teamwork-researchgit 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-research)<a href="https://agentmods.dev/skills/jinplu/teamwork/teamwork-research"><img src="https://agentmods.dev/badge/skills/jinplu/teamwork/teamwork-research.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 | $0.00039 | $0.00469 |
| Opus 5 | $0.00019 | $0.00234 |
| Sonnet 5 | $0.00008 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
teamwork-research 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teamwork Research
Keep narrow lookups native. When Research is activated, investigate the complete question rather than creating a lightweight ritual around a few searches.
Method
- Name the decision this investigation serves, then define intended use, scope, freshness cutoff, privacy boundary, and material claims.
- Search the strongest primary and current sources first, then add independent source classes where they can change confidence.
- Connect each material claim to direct support, counterevidence, inference, confidence, date, and nearby citation.
- Investigate contradictions and explain rejected sources or unresolved gaps.
- Stop when the evidence distinguishes the served direction, the scope is answered, or further retrieval is unlikely to change the conclusion; state which condition applies. Results feed the matching discussion or plan section; they do not rewrite the whole case. Supplied sources are seeds, not automatic proof or a search boundary. Split work only across independent evidence areas and keep one synthesis owner.
Maintain an early provisional conclusion as evidence develops, clearly marked as provisional. The research synthesis must preserve the decision use, a question tree, a claim-to-evidence table, contradictions and unknowns, coverage and stop conditions, and notes for every source that actually participated in the reasoning; source notes are embedded in the document rather than delegated to a separate index.
Return the supported conclusion, contradictions, residual uncertainty, coverage result, and the explicit stop basis.
Persistence
When a listed checkpoint fires, write in the same response cycle. If separate stable identities each cross a checkpoint, write each to its own path.
Cross-chat memory lives in one Markdown document from references/research.md
at docs/teamwork/research/<slug>.md. Same identity means the same
research question; reuse that path and name the document you read. A different
subject gets a new path.
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.
- 4d ago First seen · 50 lines · 39 tokens per session scan A 0e9f97a02947
teamwork-research is a skill published in the GitHub repository JinPLu/Teamwork (11 stars, last pushed 8d ago), licensed MIT. It adds 39 tokens to every session and 469 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
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
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 brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…