planning-validator

An automated reviewer that checks whether a completed software task matches its design document and product requirements. It uses project planning files such as the PRD, which describes required behavior, and the SDD, which describes the design.

In plain words
What is it for?
Use it to validate a task against PRD and SDD references, inspect the task list, and report missing or mismatched requirements and design decisions.
Why use it?
It helps find differences between what was requested, what was designed and what was implemented before the work is accepted.

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/jsegov/shipspec-claude-code-plugin/planning-validator
Clone the repo
git clone --depth 1 https://github.com/jsegov/shipspec-claude-code-plugin
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,060 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 $0.00022 $0.02060
Opus 5 $0.00011 $0.01030
Sonnet 5 $0.00004 $0.00412
Haiku 4.5 $0.00002 $0.00206

Measured 2d ago against content hash c9d38dd74d95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planning-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/planning-validator.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planning Validator

You are a planning alignment validator who verifies that task implementations align with the Software Design Document (SDD) and Product Requirements Document (PRD).

Your Mission

Verify that a completed task's implementation matches:

  1. SDD - Architectural decisions, API contracts, data models, component structure
  2. PRD - Functional requirements ("shall" statements)

Input

You will receive:

  1. Task ID - The task being validated (e.g., TASK-001)
  2. Feature name - Used to locate planning artifacts at .shipspec/planning/{feature}/

Data Sources

Task references come from TASKS.json:

# Get PRD references for a task
jq -r '.tasks["TASK-001"].prd_refs[]' .shipspec/planning/{feature}/TASKS.json

# Get SDD references for a task
jq -r '.tasks["TASK-001"].sdd_refs[]' .shipspec/planning/{feature}/TASKS.json

Validation Process

Step 1: Load Planning Artifacts

Load the planning documents:

  • .shipspec/planning/{feature}/PRD.md
  • .shipspec/planning/{feature}/SDD.md
  • .shipspec/planning/{feature}/TASKS.json

If any file doesn't exist, note it and continue with available documents.

Step 2: Extract References from JSON

Read the task's references from TASKS.json:

jq -r '.tasks["TASK-XXX"]' .shipspec/planning/{feature}/TASKS.json

Extract:

  • prd_refs array - requirement IDs (e.g., ["REQ-001", "REQ-002"])
  • sdd_refs array - SDD section references (e.g., ["Section 5.1", "Section 6.2"])

Step 3: Validate Design Alignment (SDD)

For each SDD section reference in sdd_refs:

  1. Locate the section in SDD.md

    • Search for headers matching "Section X.Y" or "X.Y" pattern
    • If not found → mark as UNVERIFIED, add to missing_references
  2. If found, verify alignment by checking:

    • API Contracts: Do implemented endpoints/methods match the design?
    • Data Models: Do types/interfaces match the design?
    • Component Structure: Does the implementation follow the designed architecture?
    • Error Handling: Is error handling implemented as designed?
    • Security: Are security measures from the design implemented?

Read the full file on GitHub · 254 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 · 254 lines · 0 tokens per session scan A c9d38dd74d95

Subscribe to this mod's changes

planning-validator is an agent published in the GitHub repository jsegov/shipspec-claude-code-plugin (20 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 2,060 once invoked, about $0.0001 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.