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 langwatch/kanban-code --skill openclawgit clone --depth 1 https://github.com/langwatch/kanban-codeWrote 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/langwatch/kanban-code/openclaw)<a href="https://agentmods.dev/skills/langwatch/kanban-code/openclaw"><img src="https://agentmods.dev/badge/skills/langwatch/kanban-code/openclaw/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/langwatch/kanban-code/openclaw"><img src="https://agentmods.dev/badge/skills/langwatch/kanban-code/openclaw.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 | $0.00076 | $0.01230 |
| Opus 5.5 | $0.00030 | $0.00492 |
| Sonnet 5.5 | $0.00015 | $0.00246 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
kanban-remote 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 20d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kanban remote
Coding work runs inside Kanban Code. Each task is a card on the board with its own Claude Code (or Codex) session. Kanban Code has two masters that share one board: this machine (kanban-code-server, always on) and the user's Mac (the app, only while it is awake). The kanban remote CLI talks to the master it is logged into, and tasks run there unless you pick another machine.
When to use
- The user asks for a change, a fix, a review or an investigation in one of their code projects.
- The user asks what is running, or how a task went.
- A task you started needs another instruction, a correction or a stop.
Setup, once
Pair with the master on this machine and log in to it:
kanban-code-server pair openclaw --scope agent # prints a token
kanban remote login http://127.0.0.1:7780 --token kc_...
kanban remote whoami
kanban remote machines
The login is saved in ~/.kanban-code/remote-client.json. KANBAN_REMOTE_URL and KANBAN_REMOTE_TOKEN override it.
Machines
kanban remote machines
Lists where a task can run: this master (marked default), the Mac with its online state, and any ssh machines. Tasks run on this machine by default. Send one to the Mac with --machine mac (or its name from machines) only when the user asks for the Mac, or the work needs it (macOS or iOS builds, Xcode, the Mac app itself, files only the Mac has). The Mac must be online.
Start a task
kanban remote projects # names accepted by --project
kanban remote task --project langwatch --worktree --name "Fix flaky login test" \
"The test 'login redirects after sign-in' in langwatch/app fails about 1 run in 5 on CI. Find the cause, fix it, run the test 20 times to confirm, and open a PR."
kanban remote task --project kanban --machine mac --worktree "Fix the toolbar layout on macOS."
- The output names the card and the machine it runs on:
Created card_... "..." in langwatch on rchaves-platform (In Progress).Keep the card id for the next steps. - Use
--worktreefor every task that changes code, so it runs on its own branch and does not touch the checkout.--worktree <name>picks the branch name. - Long prompts: pipe them in with
-:cat prompt.md | kanban remote task --project langwatch --worktree -. - A task for the Mac is handed to it: it finds the project by its git origin, or clones it.
--no-launchonly creates the card in the backlog, on this machine.
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.
- 20d ago Changed · +1 lines e0b59acbd443
- 22d ago Changed · +15 lines · +2 tokens per session 17c8454c0297
- 28d ago First seen · 78 lines · 74 tokens per session scan A 3c5d42b9efd3
kanban-remote is a skill published in the GitHub repository langwatch/kanban-code (333 stars, last pushed 5d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,230 once invoked, about $0.0003 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 2026-09-27.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…