agentleFS
davidmatousekdavidmatousek/tachi/.claude/skills/~aod-status/SKILL.md

~aod-status

Skill95 starsChanged 37 days agoApache-2.0View on GitHub

On-demand backlog snapshot and lifecycle stage summary. Regenerates BACKLOG.md from GitHub Issues and displays item counts per stage. Use this skill when you need to check backlog status, view stage counts, regenerate BACKLOG.md, or get a lifecycle overview.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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. Distinctive:

    No governance gates — this is a read-only utility command.

    line 12
  2. Distinctive:

    Run board reconciliation to fix any label↔board column drift before generating the snapshot:

    line 18
  3. Distinctive:

    Run the backlog regeneration script with JSON output mode:

    line 28
  4. Very specific:

    If the current git branch matches a feature pattern (NNN-*), display the active feature context:

    line 64
  5. Very specific:

    Check for specs/{NNN}-*/ directory

    line 68
  6. Very specific:

    If found, read spec.md/plan.md/tasks.md frontmatter to show approval status:

    line 69
  7. Distinctive:

    If not on a feature branch, skip this section.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

AOD Status Skill

Purpose

Utility skill for the AOD Lifecycle. Provides an on-demand snapshot of the project backlog by regenerating BACKLOG.md from GitHub Issues and displaying a summary of items per lifecycle stage.

No governance gates — this is a read-only utility command.

How It Works

Step 1: Reconcile Board

Run board reconciliation to fix any label↔board column drift before generating the snapshot:

source .aod/scripts/bash/github-lifecycle.sh && aod_gh_reconcile_board

This compares each open issue's stage:* label to its board column and fixes mismatches. If the board or gh is unavailable, it skips silently.

Step 2: Regenerate BACKLOG.md

Run the backlog regeneration script with JSON output mode:

bash .aod/scripts/bash/backlog-regenerate.sh --json

Parse the JSON output to extract:

  • file: path to regenerated BACKLOG.md
  • total: total number of GitHub Issues
  • stages: object with counts per stage (discover, define, plan, build, deliver, untracked)

If the script fails or gh is unavailable: Display a warning and attempt to read the existing BACKLOG.md file instead. If no BACKLOG.md exists either, report that no backlog data is available.

Step 3: Display Stage Summary

Present a formatted summary table:

AOD LIFECYCLE STATUS

| Stage    | Count |
|----------|-------|
| Discover | {n}   |
| Define   | {n}   |
| Plan     | {n}   |
| Build    | {n}   |
| Deliver  | {n}   |
| Untracked| {n}   |
|----------|-------|
| Total    | {n}   |

BACKLOG.md regenerated at {file_path}.

Step 4: Show Active Feature Context (Optional)

If the current git branch matches a feature pattern (NNN-*), display the active feature context:

  1. Get branch: git branch --show-current
  2. Extract NNN prefix
  3. Check for specs/{NNN}-*/ directory
  4. If found, read spec.md/plan.md/tasks.md frontmatter to show approval status:
Active Feature: {NNN}-{name}
  spec.md:  {PM approved / not approved / missing}
  plan.md:  {dual approved / not approved / missing}
  tasks.md: {triple approved / not approved / missing}

If not on a feature branch, skip this section.

Edge Cases

  • gh CLI unavailable: Warn and fall back to reading existing BACKLOG.md (may be stale)
  • No GitHub remote: Same as above — graceful degradation
  • Empty backlog: Display the table with all zeros
  • Script not found: Warn: "backlog-regenerate.sh not found at expected path"
  • Not on a feature branch: Skip active feature context section

Integration

Reads

  • .aod/scripts/bash/github-lifecycle.sh — reconciliation functions
  • .aod/scripts/bash/backlog-regenerate.sh — regeneration script (JSON mode)
  • docs/product/_backlog/BACKLOG.md — fallback if script fails
  • specs/{NNN}-*/spec.md, plan.md, tasks.md — active feature context

Invokes

  • aod_gh_reconcile_board — fixes label↔board drift before snapshot

Updates

  • docs/product/_backlog/BACKLOG.md — regenerated from GitHub Issues
  • GitHub Projects board — reconciles mismatched columns

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.