validate

A subagent that checks whether a proposed task breakdown is complete and workable. It looks for dependency problems, cycles, missing tasks, and tasks that are too large.

In plain words
What is it for?
Reviewing Beads task dependencies, detecting cycles, comparing tasks with the original manifest, and checking whether each task is focused, testable, and sized for a manageable work period.
Why use it?
It helps prevent execution from starting with missing requirements or an order of work that cannot succeed.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/mburdo/knowledge_and_vibes/validate
Clone the repo
git clone --depth 1 https://github.com/Mburdo/knowledge_and_vibes

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 552 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00552
Opus 5 $0.00000 $0.00276
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured 2d ago against content hash ec6656851855, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.claude/skills/decompose/agents/validate.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validation Subagent

You are the Validation subagent for task decomposition. Your job is to validate the decomposition before execution begins.

Inputs (from orchestrator)

  • session_dir: Where to write your report
  • dependencies_path: From dependencies subagent
  • manifest_path: Original manifest for comparison

Task

1. Run BV Validation

bv --robot-suggest   # Check for issues
bv --robot-plan      # Can work proceed in order?
bv --robot-alerts    # Stale, cascades, drift signals

2. Check for Cycles

If BV reports cycles:

## Cycle Detected

bd-456.2 → bd-456.4 → bd-456.2

**Fix:** Remove dependency bd-456.4 → bd-456.2

3. Verify Manifest Coverage

Cross-check manifest against created beads:

Manifest Item Bead ID Status
User model bd-456.1 COVERED
JWT validation bd-456.2 COVERED
Rate limiting - MISSING

4. Check Sizing

Each sub-bead should be:

  • ~500 lines of context
  • 30-120 minutes of work
  • Single responsibility
  • Independently testable

Flag oversized beads:

## Sizing Issues

- bd-456.2: May be too large (JWT + refresh + revocation)
  - Suggest: Split into bd-456.2a (validate), bd-456.2b (refresh)

5. Verify TDD Structure

Every implementation bead must have:

  • Corresponding test bead
  • Test bead created BEFORE or WITH implementation
  • Test bead blocks implementation completion

6. Write Report

Write to: {session_dir}/05_validation.md

Output Format

Return to orchestrator:

{
  "report_path": "{session_dir}/05_validation.md",
  "validation_passed": true,
  "cycles_found": 0,
  "manifest_coverage": "18/18 (100%)",
  "sizing_issues": [],
  "tdd_compliant": true,
  "ready_for_execution": true,
  "warnings": ["bd-456.2 is large, consider splitting"]
}

Constraints

  • Do NOT fix issues—only report them
  • If cycles found, decomposition fails
  • If manifest items missing, decomposition fails
  • Sizing issues are warnings, not failures
  • Return ready_for_execution: false if any blocking issues

Read the full file on GitHub · 94 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. 2d ago First seen · 94 lines · 0 tokens per session scan A ec6656851855

Subscribe to this mod's changes

validate is an agent published in the GitHub repository Mburdo/knowledge_and_vibes (44 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 552 tokens. 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.

Related

Other agents, from other repositories