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-updatenpx skills add JinPLu/Teamwork --skill teamwork-updategit clone --depth 1 https://github.com/JinPLu/TeamworkWhat 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 | $0.00037 | $0.00546 |
| Opus 5 | $0.00018 | $0.00273 |
| Sonnet 5 | $0.00007 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
teamwork-update 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 2d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teamwork Update
Update is a small install and refresh operation. It is never an automatic detour from another task.
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. - For a check-only request, run
./scripts/check-update.sh --readiness. Treat the output as diagnostic information, not permission to continue other work. - For an authorized refresh, update only the requested host. The default
updatetarget refreshes Codex; Cursor or Claude adapters require explicit targets. When refreshing an intentionally revised Agent profile, keepperformance-firstandcost-firstdistinct and compare task success, elapsed time, and cost together instead of maximizing model or effort. For a Codex profile refresh, update both the role profiles and the top-level main-thread default while preserving other user configuration:performance-firstuses Terra/xhigh andcost-firstuses Luna/high. - Preserve unknown and user-owned files. Replace only recognizable Teamwork-owned surfaces.
- Re-run the same focused check and report what changed or the observed no-op, and any manual restart still needed.
Do not inspect or migrate project documents, compare project schemas, fetch release state, modify unrelated plugins or credentials, or require any agent to perform a readiness check. A missing specialized agent never makes Update a precondition for native work. When Update 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 operation identity). Optional triggers: an authorized refresh completes
with observed surface changes worth reusing; Update stops on a real blocker
worth reusing; or a no-op result is reusable or explicitly requested.
Update 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.
- 2d ago First seen · 51 lines · 37 tokens per session scan A c3352cc23f8d
teamwork-update is a skill published in the GitHub repository JinPLu/Teamwork (11 stars, last pushed 6d ago), licensed MIT. It adds 37 tokens to every session and 546 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
etsy-category-listing
Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…
human-approval
Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…
firebase-analytics
Use when logging analytics events, setting user properties, configuring default event parameters, building funnels, or adding screen-view tracking.
firebase-remote-config
Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.
git-master
MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git…
prismer-evolve-record
Record the outcome of applying an evolution strategy. Use after resolving an error where prismer-evolve-analyze provided a recommendation, to feed back success or failure to the network.