Conductor-Beads: Command for Claude Code

.claude/commands/conductor-validate.md

conductor-validate is a command for Claude Code from NguyenSiTrung/Conductor-Beads. It costs 5 tokens per session (681 once invoked), scanned A, original, Apache-2.0.

A command that checks whether a Conductor project is complete and internally consistent. It examines required files, work-track folders, task statuses, and planning markers.

In plain words
What is it for?
Use it to audit Conductor setup, verify tracks and plans, detect inconsistencies, and check annotations used for parallel work.
Why use it?
It finds missing files, orphaned folders, mismatched statuses, invalid task states, and other problems that can make the project plan unreliable.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is NguyenSiTrung/Conductor-Beads's own configuration. It tells Claude Code how to work on Conductor-Beads 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 Conductor-Beads configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NguyenSiTrung/Conductor-Beads. 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/NguyenSiTrung/Conductor-Beads/main/.claude/commands/conductor-validate.md
Clone the repo
git clone --depth 1 https://github.com/NguyenSiTrung/Conductor-Beads

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 conductor-validate

README.md
[![agentmods](https://agentmods.dev/badge/commands/nguyensitrung/conductor-beads/conductor-validate/github.svg)](https://agentmods.dev/commands/nguyensitrung/conductor-beads/conductor-validate)
Your own site
<a href="https://agentmods.dev/commands/nguyensitrung/conductor-beads/conductor-validate"><img src="https://agentmods.dev/badge/commands/nguyensitrung/conductor-beads/conductor-validate/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 conductor-validate

Your own site · 80×15
<a href="https://agentmods.dev/commands/nguyensitrung/conductor-beads/conductor-validate"><img src="https://agentmods.dev/badge/commands/nguyensitrung/conductor-beads/conductor-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 681 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.
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 $0.00005 $0.00681
Opus 5 $0.00003 $0.00341
Sonnet 5 $0.00001 $0.00136
Haiku 4.5 $0.00001 $0.00068

Measured 9d ago against content hash 8f82e9ee9ba0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

conductor-validate 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • validate — 92% identical, 4 lines differ
.claude/commands/conductor-validate.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conductor Validate

Validate the integrity of this Conductor project.

1. Core Files Check

Verify these files exist in conductor/:

  • product.md
  • tech-stack.md
  • workflow.md
  • tracks.md

2. Tracks Consistency

For each track in tracks.md:

  • Verify directory exists: conductor/tracks/<track_id>/
  • Verify files: metadata.json, spec.md, plan.md
  • Validate metadata.json has: track_id, type, status, created_at

3. Orphan Detection

  • List all directories in conductor/tracks/
  • Report any not referenced in tracks.md

4. Status Consistency

  • Compare status markers in tracks.md with metadata.json status field
  • Report mismatches

5. Plan Integrity

For each plan.md:

  • Must have at least one phase and task
  • Valid markers only: [ ], [~], [x], [!]
  • Completed tracks should have all tasks completed
  • Validate parallel execution annotations if present

5a. Parallel Execution Validation

For tracks with parallel execution annotations:

  • Check <!-- execution: parallel --> is after valid phase heading
  • Verify all tasks in parallel phases have <!-- files: ... --> annotation
  • Detect file conflicts (same file in multiple tasks)
  • Verify <!-- depends: ... --> references valid task IDs
  • If parallel_state.json exists, check for stale/orphan workers

6. Report

Present summary with:

  • ✅ Valid items
  • ⚠️ Warnings
  • ❌ Errors
  • Recommendations for fixes

7. Auto-Fix Option

Offer to fix auto-fixable issues:

  • Missing metadata fields
  • Status mismatches
  • Orphan cleanup

8. BEADS VALIDATION

PROTOCOL: Include Beads consistency checks.

  1. Check for Beads CLI:

    • Run which bd
    • If NOT found:

      "⚠️ Beads CLI (bd) is not installed. Beads provides persistent task memory across sessions." "A) Continue validation without Beads checks" "B) Stop - I'll install Beads first"

      • If A: Skip this section
      • If B: HALT and wait for user
  2. Verify Beads Integration:

    • Task status sync between Beads and plan.md
    • No orphan epics/tasks
    • Epic links valid in metadata.json
    • If any bd command fails:

      "⚠️ Beads command failed: " "A) Continue validation without Beads checks" "B) Retry the failed command" "C) Stop - I'll fix the issue first"

      • If A: Skip remaining Beads steps
      • If B: Retry the command
      • If C: HALT and wait for user

Read the full file on GitHub · 97 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. 9d ago First seen · 97 lines · 5 tokens per session scan A 8f82e9ee9ba0

Subscribe to this mod's changes

conductor-validate is a command published in the GitHub repository NguyenSiTrung/Conductor-Beads (24 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 5 tokens to every session and 681 once invoked, about $0.0000 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.