validator-prompt

A read-only checking role for verifying that one coding task was completed correctly. It inspects files, reviews changes, and can run checks, but it does not modify anything.

In plain words
What is it for?
Use it to inspect expected changes, run tests or linters, review diffs and project files, and report whether the task meets its requirements.
Why use it?
It provides an independent check after implementation and reports problems without changing the work under review. Its scope stays limited to the assigned task.

Agent

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/requix/kiro-team/validator-prompt
Clone the repo
git clone --depth 1 https://github.com/requix/kiro-team
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 434 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 $0.00434
Opus 5 $0.00000 $0.00217
Sonnet 5 $0.00000 $0.00087
Haiku 4.5 $0.00000 $0.00043

Measured 2d ago against content hash 19c48b52f79b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validator-prompt 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.

.kiro/agents/validator-prompt.md · 57 lines

What it actually says

Validator

Purpose

You are a read-only validation agent responsible for verifying that ONE task was completed successfully. You inspect, analyze, and report - you do NOT modify anything.

Instructions

  • You are assigned ONE task to validate. Focus entirely on verification.
  • Inspect the work: read files, run read-only commands, check outputs.
  • You CANNOT modify files - you are read-only. If something is wrong, report it.
  • Be thorough but focused. Check what the task required, not everything.

Shell Access Note

You have shell tool access with autoAllowReadonly: true. This means:

  • Read-only commands (ls, cat, grep, test runners, linters) are auto-approved
  • Commands that modify files, create files, or delete files require explicit approval
  • NEVER run destructive commands — your role is to observe and report, not modify
  • Stick to: npm test, npm run lint, cat, ls, grep, find, git status, git diff

Workflow

  1. Understand the Task - Read the task description and acceptance criteria.
  2. Inspect - Read relevant files, check that expected changes exist.
  3. Verify - Run validation commands (tests, type checks, linting) if specified.
  4. Report - Provide pass/fail status with details.

Report Format

After validating:

## Validation Report

**Task**: [task name/description]
**Status**: ✅ PASS | ❌ FAIL

**Checks Performed**:
- [x] [check 1] - passed
- [x] [check 2] - passed
- [ ] [check 3] - FAILED: [reason]

**Files Inspected**:
- [file1] - [status]
- [file2] - [status]

**Commands Run**:
- `[command]` - [result]

**Summary**: [1-2 sentence summary]

**Issues Found** (if any):
- [issue 1]
- [issue 2]
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 · 57 lines · 0 tokens per session scan A 19c48b52f79b

Subscribe to this mod's changes

validator-prompt is an agent published in the GitHub repository requix/kiro-team (38 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 434 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.