yylo: Skill for Claude Code

.agents/skills/kanban-workflow/SKILL.md

kanban-workflow is a skill for Claude Code from yylo-dev/yylo. It costs 65 tokens per session (2,352 once invoked), scanned A, original, MIT.

A guide for managing tasks on a YYLO Ledger kanban board. Kanban is a board-based way to track work as it moves through stages such as queued, active, and complete.

In plain words
What is it for?
Use it to create, find, inspect, update, archive, order, merge, and mark tasks, and to check which tasks are ready to start.
Why use it?
It explains the board’s commands and working patterns, so tasks, dependencies, and ordering can be handled consistently.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is yylo-dev/yylo's own configuration. It tells Claude Code how to work on yylo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yylo configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is yy ledger merge ./sub1/.juno_task ./sub2/.juno_task --into ./.juno_task.

Reuse

Borrowing it

Nothing to install: this file belongs to yylo-dev/yylo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yylo-dev/yylo/main/.agents/skills/kanban-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yylo-dev/yylo

Made for: Claude Code.

Wrote 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.

agentmods badge for kanban-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/yylo-dev/yylo/kanban-workflow/github.svg)](https://agentmods.dev/skills/yylo-dev/yylo/kanban-workflow)
Your own site
<a href="https://agentmods.dev/skills/yylo-dev/yylo/kanban-workflow"><img src="https://agentmods.dev/badge/skills/yylo-dev/yylo/kanban-workflow/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.

agentmods 80×15 button for kanban-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/yylo-dev/yylo/kanban-workflow"><img src="https://agentmods.dev/badge/skills/yylo-dev/yylo/kanban-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,352 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.02352
Opus 5 $0.00032 $0.01176
Sonnet 5 $0.00013 $0.00470
Haiku 4.5 $0.00006 $0.00235

Measured 5d ago against content hash a486d10a1447, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kanban-workflow 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.

.agents/skills/kanban-workflow/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YYLO Ledger CLI Reference

Use yy ledger for all commands. It delegates to the canonical controller wrapper and the exact yylo-ledger 0.2.1rc2 Python distribution. yy kanban is a labelled legacy Task alias.

Native Record contract

  • Records use one envelope with immutable ID, kind/profile, revision, lifecycle/tier, relations, provenance, system/custom metadata, and typed payload.
  • Use yy ledger task|wiki|workflow|artifact|record; do not simulate Documents, Workflows, or Artifacts with task bodies.
  • Read the current Record first and pass the required expected revision, preimage, or record/payload digest shown by nested update --help. A stale compare-and-replace must fail; never retry as an unconditional overwrite.
  • Capture Artifact bytes explicitly as inline, content-addressed local, or declared external evidence. Preserve the returned ID, revision, and SHA-256 digest in references.
  • Normal search is bounded, projected, cursor-based, and hot-only unless an explicit archive command is used.
  • Copy legacy files with yy migrate ledger inventory|plan|apply|status|verify. Keep immutable plans/status outside the source tree, apply explicit Record IDs one at a time, verify bytes/history/search, and never delete a legacy source without separate owner approval.

Examples:

yy ledger wiki create --title Guide --file guide.md
yy ledger workflow create --title Build --file workflow.yaml
yy ledger artifact create --title Report --profile report --mode local --file report.bin
yy ledger record search --scope all --projection summary --limit 20 --format json
yy migrate ledger status --source-root /project --plan /external/plan.json --status /external/status.json

Opt-in cross-project routing

Cross-project access is disabled by default. The source .juno_task/config.json must set kanbanRegistry.enabled: true and explicitly list allowedProjects; environment overrides are JUNO_KANBAN_REGISTRY_ENABLED and JUNO_KANBAN_REGISTRY_ALLOWED_PROJECTS. Register with yy ledger project add ALIAS --path /absolute/project, then route any command with --project ALIAS. The destination wrapper/runtime remains authoritative, and routing failures never fall back to the source board.

Read the full file on GitHub · 193 lines

Changes

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.

  1. 5d ago Changed · +19 lines a486d10a1447
  2. 9d ago First seen · 174 lines · 65 tokens per session scan A 7a546a11424e

Subscribe to this mod's changes

kanban-workflow is a skill published in the GitHub repository yylo-dev/yylo (57 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 2,352 once invoked, about $0.0003 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.