task-scope-validator

task-scope-validator is an agent for Claude Code from ivegamsft/basecoat. It costs 85 tokens per session (505 once invoked), scanned A, original, MIT.

A checker that reviews a task before it is sent to another coding agent. It looks for one clear outcome, an understood path, measurable success criteria, and a reasonable time limit.

In plain words
What is it for?
Use it to classify exploration, execution, design, or research prompts; identify missing scope; assess dispatch risks; and suggest a suitable agent or remediation.
Why use it?
It helps prevent agents from receiving tasks that are too broad, unclear, risky, or difficult to verify. It can recommend refining the task or treating it as information gathering instead.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents.

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/ivegamsft/basecoat/basecoat-60-workflow-task-scope-validator
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

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 task-scope-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-task-scope-validator.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-task-scope-validator)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-task-scope-validator"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-task-scope-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 505 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 $0.00085 $0.00505
Opus 5 $0.00043 $0.00253
Sonnet 5 $0.00017 $0.00101
Haiku 4.5 $0.00009 $0.00051

Measured 2d ago against content hash 3655ccc87a40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

task-scope-validator 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.

agents/basecoat-60-workflow-task-scope-validator.agent.md · 49 lines

What it actually says

Task Scope Validator Agent

Analyzes task descriptions before dispatch to detect overscope, ambiguity, and risk, returning a classification decision and remediation guidance.

Inputs

  • Task description or prompt; task type (exploration, execution, design, research)
  • Optional: existing task context, constraints, user role, or authority level

Workflow

  1. Extract task summary, objectives, success criteria, and intended agent type.
  2. Check 1 - Single issue/outcome: task targets one artifact with one identifiable outcome.
  3. Check 2 - Deterministic path: steps to completion are known or strongly inferrable.
  4. Check 3 - Success measurability: success is objectively verifiable with explicit criteria.
  5. Check 4 - Time-bounded: <5 min for explore agents, <60 min for task/general-purpose agents.
  6. Classify as automatable, gather-findings-only, or defer based on check results.
  7. Return structured JSON with check results, recommended agent, risks, and remediation suggestions.

Decision Rules

  • Approve (approved_for_dispatch: true) if automatable with confidence >= 0.8.
  • Approve with caution if confidence 0.6-0.79.
  • Require refinement if defer or confidence <0.6.
  • Manual override: --force flag bypasses checks and logs the override.

Output

Structured JSON: task_id, classification, confidence, check results (pass/fail with evidence), recommended agent, risks, remediation suggestions, approved_for_dispatch flag, and notes.

References

Classification check criteria, output JSON schema, good and bad task prompt examples, integration points: agents/references/task-scope-validator-detail.md

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 · 49 lines · 85 tokens per session scan A 3655ccc87a40

Subscribe to this mod's changes

task-scope-validator is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 505 once invoked, about $0.0004 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 2026-09-03.