validate-output

validate-output is a command for Claude Code from khanh-vu/claude-force. It costs 7 tokens per session (401 once invoked), scanned A, original, MIT.

A command that checks .claude/work.md against a project’s quality rules. It runs checks for scorecard items, allowed write areas, secrets, focused changes, formatting, and agent scope.

In plain words
What is it for?
Use it before handing off work from a Claude Code project. It validates the work file, reports pass or fail results, and suggests fixes for problems such as exposed keys or invalid formatting.
Why use it?
It gathers several final checks in one place and shows which requirement failed, instead of relying on a manual review of the output file.

Command 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 commands/khanh-vu/claude-force/validate-output
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

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 validate-output

README.md
[![agentmods](https://agentmods.dev/badge/commands/khanh-vu/claude-force/validate-output.svg)](https://agentmods.dev/commands/khanh-vu/claude-force/validate-output)
Your own site
<a href="https://agentmods.dev/commands/khanh-vu/claude-force/validate-output"><img src="https://agentmods.dev/badge/commands/khanh-vu/claude-force/validate-output.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 401 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 5.1 $0.00007 $0.00401
Opus 5 $0.00003 $0.00200
Sonnet 5 $0.00001 $0.00080
Haiku 4.5 $0.00001 $0.00040

Measured 5d ago against content hash 41e84b9eb94f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

validate-output 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.

.claude/commands/validate-output.md · 71 lines

What it actually says

Validate Output Command

Run all validators on the current .claude/work.md to ensure it meets quality standards.

Validators to Run

  1. Scorecard Validator - Check all scorecard items marked PASS/FAIL
  2. Write Zone Guard - Verify Write Zone updated correctly
  3. Secret Scan - Ensure no secrets in output
  4. Diff Discipline - Verify minimal, focused changes
  5. Format Lint - Validate output structure and formatting
  6. Hierarchy Governance - Ensure agent stayed within scope

Process

  1. Read .claude/work.md
  2. Read all validators from .claude/hooks/validators/
  3. Run each validator in sequence
  4. Report PASS/FAIL for each
  5. Provide summary of issues
  6. Suggest remediation steps for failures

Output Format

## Validation Results

### Scorecard Validator: ✅ PASS
- All items marked PASS or justified FAIL

### Write Zone Guard: ✅ PASS
- Write Zone updated with 5 lines
- Last updated: 2025-11-13 10:30

### Secret Scan: ❌ FAIL
- Found API key on line 245
- Remediation: Replace with placeholder

### Diff Discipline: ✅ PASS
- Changes focused and minimal

### Format Lint: ✅ PASS
- All sections present
- Markdown valid

### Hierarchy Governance: ✅ PASS
- Agent stayed within contract scope

## Summary
- **Total**: 6 validators
- **Passed**: 5
- **Failed**: 1
- **Status**: ❌ VALIDATION FAILED

## Next Steps
1. Fix secret leak on line 245
2. Re-run validation
3. Proceed when all validators pass

Example

/validate-output
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 First seen · 71 lines · 7 tokens per session scan A 41e84b9eb94f

Subscribe to this mod's changes

validate-output is a command published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It adds 7 tokens to every session and 401 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 2026-08-31.