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-goalnpx skills add JinPLu/Teamwork --skill teamwork-goalgit 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-goal)<a href="https://agentmods.dev/skills/jinplu/teamwork/teamwork-goal"><img src="https://agentmods.dev/badge/skills/jinplu/teamwork/teamwork-goal.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 | $0.00041 | $0.00600 |
| Opus 5 | $0.00020 | $0.00300 |
| Sonnet 5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
teamwork-goal 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teamwork Goal
Goal adds persistence to the underlying task; it does not add a second workflow.
Method
- State the concrete objective, success signal, applicable scope, and any user budget. A success signal is the directly observable result that shows the requested outcome is achieved. Example: the authorized command or user-stated completion condition is observed on the real path.
- Perform the next useful action and observe the result.
- Continue until the success signal is directly observed, the user interrupts, or a genuine external blocker prevents further progress.
- Change approach when evidence invalidates the current one. Do not repeat a failed action without a new reason.
- Report success with the observed evidence, or report the exact blocker and what would unblock it.
Carry compact Invariants through every retry: the original objective, protected constraints, and stop or budget state. After each attempt, keep an Attempt Record with the previous result, the new reason to continue or stop, and the current stop or budget state. These records live in the working context and, when a checkpoint fires, in the report; they are not a workflow database.
Tests support the goal but do not replace the real success signal when that signal is available.
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/report.md
at docs/teamwork/reports/<slug>.md. Same identity means the same
continuing objective; reuse that path and name the document you read. A
different subject gets a new path.
Experiment checkpoints write from references/experiment-record.md at
docs/teamwork/experiments/<slug>.md. Same identity means the same
falsifiable claim; reuse that path and name the document you read. A
different claim gets a new path. Probe declarations need only a claim draft,
kill criterion, and budget. The full declaration is for main-table or
appendix-hygiene eligibility, not a run gate. Slot criteria are in
../teamwork-collaborate/references/experiment.md. Post-run HARKing is the
diff between the frozen declared claim and a post-hoc claim; Reviewer or
Challenger is the right role for that adjudication, and it is not a
mandatory ceremony.
What ships with it
3 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 · 58 lines · 41 tokens per session scan A 01671d5d7a22
teamwork-goal is a skill published in the GitHub repository JinPLu/Teamwork (11 stars, last pushed 9d ago), licensed MIT. It adds 41 tokens to every session and 600 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
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.
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.
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…