Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/XMihura/Kanvasnpx agentmods add skills/xmihura/kanvas/skillWrote 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/xmihura/kanvas/skill)<a href="https://agentmods.dev/skills/xmihura/kanvas/skill"><img src="https://agentmods.dev/badge/skills/xmihura/kanvas/skill/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/xmihura/kanvas/skill"><img src="https://agentmods.dev/badge/skills/xmihura/kanvas/skill.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 | $0.00060 | $0.02497 |
| Opus 5.5 | $0.00024 | $0.00999 |
| Sonnet 5.5 | $0.00012 | $0.00499 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
kanvas 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 today.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kanvas
The board is kanvas.json at the project root. Change it only through the CLI in .agents/skills/kanvas/; the CLI enforces the workflow and keeps the file valid:
python .agents/skills/kanvas/kanvas.py <command>
Use python3 where python is missing. Never edit kanvas.json by hand. The human watches the board in a browser, where your changes appear within a second. It opens with kanvas serve when Kanvas is installed, or python .agents/skills/kanvas/kanvas.py serve. When Kanvas already runs for another project, this opens the board there and returns at once; otherwise it keeps running until stopped.
Workflow
proposed -> todo -> doing -> review -> done
| State | Moved there by | Meaning |
|---|---|---|
| proposed | you (propose, batch) |
An idea waiting for human approval |
| todo | the human | Approved. Shown as blocked while a dependency is unfinished |
| doing | you (start) |
In progress |
| review | you (finish, with a summary) |
Waiting for the human to check it |
| done | the human | Accepted |
You may propose tasks and groups, start ready tasks, finish or pause tasks in progress, add notes and add dependencies. Until the human approves a proposal, you may also revise it (edit), withdraw it (withdraw) or remove its dependencies (undepend), so rework proposals freely while you discuss a plan. Approving proposals, changing approved tasks and marking tasks done belong to the human; ask for them in the conversation.
The human can also ask for changes to a proposal in the board. status then marks it (changes requested: ...), and show ID has the request in its notes. Revise the proposal with edit ID, passing -m with what you changed; that note answers the request, and the mark goes.
YOLO
The human can put a task under YOLO in the board. That covers the task and everything it depends on, directly or indirectly; the CLI marks covered tasks (YOLO). For covered tasks:
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.
- today First seen · 133 lines · 60 tokens per session scan A 0331a65e03f0
kanvas is a skill published in the GitHub repository XMihura/Kanvas (297 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 2,497 once invoked, about $0.0002 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 2026-10-28.
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.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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,"…
remove
Remove a deployed framework or addon from the current workspace.