agentleFS
cellrishi-codecellrishi-code/claude-skills-atlas/skills/coding/ledger-tasks-yylo/SKILL.md

ledger-tasks-yylo

Skill6 starsChanged 41 days agoMITView on GitHub

Track coding-agent work in a durable Git-backed task ledger (YYLO Ledger) so plans, status, and dependencies survive across sessions instead of living only in chat history.

  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run yy ledger --help first.

    line 23
  2. Very specific:

    Read before writing: yy ledger record search --projection summary --limit 20 -f json lists current tasks.

    line 24
  3. Very specific:

    Create tasks with yy ledger create "{{task description}}" --status todo --tags {{project-tags}}.

    line 25
  4. Distinctive:

    Before reporting work as done, re-read the task record and check its acceptance notes.

    line 27
  5. Distinctive:

    Prefer commands that return mutation receipts.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ledger Tasks (YYLO)

Purpose

Give a coding agent a persistent, queryable task store: planned work, status changes, dependencies, and history are recorded durably and read back on demand instead of being reconstructed from conversation memory.

When to use

  • Multi-session projects where task state must outlive a single conversation.
  • Planning work that needs explicit dependencies (start B only after A) and blocked states.
  • Any request for a kanban board, task list, or work ledger rather than a prose status update.
  • The YYLO CLI is available (npm install -g @yylo/cli) and the project is initialized (a .juno_task/ directory is present).

Instructions

  1. Run yy ledger --help first; the installed help is authoritative for the runtime.
  2. Read before writing: yy ledger record search --projection summary --limit 20 -f json lists current tasks. Never guess record IDs.
  3. Create tasks with yy ledger create "{{task description}}" --status todo --tags {{project-tags}}.
  4. Move work forward with explicit status transitions (backlog → todo → in_progress → done) and record blockers with --blocked-by {{task_id}}.
  5. Before reporting work as done, re-read the task record and check its acceptance notes. The ledger is the source of truth, not memory.
  6. Prefer commands that return mutation receipts. Never hand-edit ledger store files or bypass the CLI.

Inputs

  • Short task descriptions, optional tags, desired status, and dependency task IDs.
  • Record IDs (task_...) returned by earlier create or list calls.

Outputs

  • JSON task records containing IDs, status, tags, dependencies, and timestamps.
  • Board-style summaries from yy ledger list (statuses, counts, ordering) suitable for quoting in replies.

Example

yy ledger create "Add retry logic to uploader" --status todo --tags backend,reliability
# -> { "id": "{{task_id}}", "status": "todo", ... }

yy ledger update {{task_id}} --status in_progress
yy ledger update {{task_id}} --status done
yy ledger list --status todo,in_progress --limit 10

Limitations

  • Requires the YYLO CLI and an initialized project; without them, fall back to a plain checklist file the user nominates.
  • Cross-project access is opt-in via registry configuration; the default scope is the current project only.
  • Models tasks, dependencies, and typed records deliberately — not a replacement for issue trackers with rich UIs or permissions.

Attribution

Adapted from the ledger-tasks-yylo skill in yylo-dev/yylo-skills (MIT).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.