Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add aiocean/claude-plugins/plugin install aio-kanbanWrote 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/aiocean/claude-plugins/aio-kanban)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-kanban"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-kanban/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/aiocean/claude-plugins/aio-kanban"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-kanban.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 | $0.00078 | $0.01425 |
| Opus 5.5 | $0.00031 | $0.00570 |
| Sonnet 5.5 | $0.00016 | $0.00285 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
aio-kanban scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
!bash "${CLAUDE_PLUGIN_ROOT}/skills/aio-kanban/scripts/kanban-status.sh" 2>/dev/null
Kanban Protocol (v3 — index + per-task files)
Board is a flat index at .kanban/board.md. Each line points to a task file.
Tasks live at .kanban/tasks/T-NNN-slug.md with full body (description, criteria, notes).
Follow this protocol exactly. Do NOT adapt or invent your own format.
Init
If auto-status above shows "not initialized":
mkdir -p .kanban/archive .kanban/tasks
cat > .kanban/board.md << 'BOARD'
# Kanban Board
<!-- Updated: YYYY-MM-DD -->
## Backlog
## Todo
## Doing
## Done
## Blocked
BOARD
Then inject the kanban guide into CLAUDE.md:
bash "${CLAUDE_PLUGIN_ROOT}/skills/aio-kanban/scripts/kanban-inject.sh"
Formats — MUST use verbatim
Board line (one per task)
- [T-NNN](tasks/T-NNN-slug.md) Title — priority/effort
Example:
- [T-052](tasks/T-052-rate-limit.md) Rate limit per endpoint — high/S
Task file (.kanban/tasks/T-NNN-slug.md)
# T-NNN: Title
> One-line description
- **priority**: critical | high | medium | low
- **effort**: XS | S | M | L
## Criteria
- [ ] Acceptance criterion 1
- [ ] Acceptance criterion 2
## Notes
(free-form section — design sketches, links, discussion)
Optional fields (add below - **effort**):
- **depends**: T-NNN- **branch**: feat/branch-name- **completed**: YYYY-MM-DD(added when moved to Done)- **blocked-by**: reason(added when moved to Blocked)
ID rule: T-NNN, zero-padded, monotonic. NEVER reuse.
Slug rule: kebab-case from title, lowercase, alphanumeric+hyphen only, max 40 chars.
Workflow Rules
- Add a task:
- Pick next ID: highest existing T-NNN + 1.
- Generate slug from title (kebab-case, ≤40 chars).
- Create file
.kanban/tasks/T-NNN-slug.mdwith format above. - Insert board line under ## Backlog in
.kanban/board.md.
- Refine: move the board line to ## Todo when criteria are defined.
- Start: move the board line to ## Doing, add
- **branch**: ...to the task file. NEVER exceed 2 in Doing. - Complete: ALL criteria checkboxes checked → move board line to ## Done, add
- **completed**: YYYY-MM-DDto task file. - Block: move to ## Blocked, add
- **blocked-by**: ...to task file. Review daily. - Archive: monthly, cut Done lines AND their task files to
.kanban/archive/YYYY-MM/(board lines intoarchive/YYYY-MM/board.md, task files intoarchive/YYYY-MM/tasks/). - Update timestamp: every board write updates
<!-- Updated: YYYY-MM-DD -->.
What ships with it
13 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.
- scripts/kanban-inject.sh 2.1 KB runs code
- scripts/kanban-status.sh 1.4 KB runs code
- tui/.gitignore 28 B
- tui/aiokan_test.go 14 KB
- tui/go.mod 1.5 KB
- tui/go.sum 6.3 KB
- tui/kanban.go 8.7 KB
- tui/keys.go 484 B
- tui/main.go 2.3 KB
- tui/model.go 14 KB
- tui/README.md 3.1 KB
- tui/theme.go 3.3 KB
- tui/view.go 9.3 KB
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.
- 1mo ago First seen · 143 lines · 78 tokens per session scan A 777b42495a8e
aio-kanban is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 28d ago), licensed MIT. It adds 78 tokens to every session and 1,425 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 2026-09-03.
Other skills, from other repositories
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
plan-pipeline
Orchestrates the complete planning pipeline: product direction (ceo-review) -> architecture (eng-review) -> implementation plan (start) -> validation (validate) -> execution (execute). Run stages individually or let the orchestrator coordinate the full flow.
routines-discover
Analyzes the current project to surface high-value Routines use cases across the three trigger types (schedule, API, GitHub events). Usage: /routines-discover.
incremental-shipping
Use when implementing a non-trivial feature, migration, or refactor that would otherwise be a single large change. Activate for keywords like "feature flag", "incremental", "vertical slice", "migration", "rollout", "behind a flag", "ship small". Enforces vertical slicing, feature-flagged rollout, and refactor-with…
linear-app-setup
Create and configure a Linear agent app so the assistant can manage issues, projects, and workflows under its own identity.
product-brief
Extract a product idea through guided questions and generate a PRD. Use when the user says 'write a PRD', 'spec this feature', 'turn this idea into a brief'. Not for a non-product initiative like hiring or partnerships (use initiative-kickoff once shipped); not for checking existing projects' status (use…