validation-plan

validation-plan is a skill for Claude Code, Codex from fzfclee/consulting-skills. It costs 51 tokens per session (735 once invoked), scanned A, original, Apache-2.0.

A planning method for checking whether a recommendation or hypothesis is supported by enough evidence. It defines tests, decision checkpoints, and rules for continuing, changing, or stopping.

In plain words
What is it for?
Use it to design experiments, set evidence standards, choose success thresholds, and decide what to do based on test results.
Why use it?
It prevents teams from treating an untested idea as a decision. It also makes missing evidence, assumptions, and risk visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design experiments, set evidence standards, choose success thresholds, and decide what to do based on test results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fzfclee/consulting-skills/validation-plan
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.

Any agent
npx skills add fzfclee/consulting-skills --skill validation-plan
Clone the repo
git clone --depth 1 https://github.com/fzfclee/consulting-skills

Made for: Claude Code, Codex.

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 validation-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/fzfclee/consulting-skills/validation-plan.svg)](https://agentmods.dev/skills/fzfclee/consulting-skills/validation-plan)
Your own site
<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/validation-plan"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/validation-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 735 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00051 $0.00735
Opus 5 $0.00026 $0.00367
Sonnet 5 $0.00010 $0.00147
Haiku 4.5 $0.00005 $0.00073

Measured 8d ago against content hash 33e0832f4eb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

validation-plan 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 8d 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.

skills/validation-plan/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validation Plan

Use this skill to turn a recommendation into a testable plan with evidence standards and decision gates.

Method Notes

  • Validation is not the same as implementation. It defines what evidence will increase or reduce confidence.
  • A good validation plan names the hypothesis, test, signal, threshold, owner, timing, and decision rule.
  • It should be proportional to risk: higher-risk decisions need stronger validation.

Required Inputs

Collect or infer these inputs before execution:

  • recommendation or hypothesis to validate
  • decision consequence and risk level
  • available evidence and current confidence
  • feasible tests or evidence sources
  • timeline, owner, and decision deadline

If an input is missing, mark it as missing, state the assumption used, and add a validation action.

When Not To Use

Do not use when the user has not yet formed a hypothesis or action option. Use evidence-map, issue-tree, or hypothesis-tree first.

Step-by-Step Execution

Step Required input How to execute Output
State the hypothesis Recommendation, expected outcome, current confidence. Write the claim to be validated in one testable sentence. Validation hypothesis.
Define decision consequence Risk, reversibility, cost of wrong action. Decide how strong the evidence must be before action. Evidence standard.
Select validation method Evidence sources, access, timeline. Choose interview, document check, commitment test, pilot, prototype, data analysis, stakeholder signal, or market test. Validation method.
Define success and failure signals Hypothesis, expected behavior, thresholds. Make pass, adjust, and stop criteria explicit. Decision criteria.
Plan execution Owner, timing, script or data need, dependencies. Specify who does what by when and with what artifact. Validation workplan.
Decide next gate Test result, action options. Define what decision will be made after evidence arrives. Continue / adjust / stop gate.

Read the full file on GitHub · 80 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. 8d ago First seen · 80 lines · 51 tokens per session scan A 33e0832f4eb3

Subscribe to this mod's changes

validation-plan is a skill published in the GitHub repository fzfclee/consulting-skills (4 stars, last pushed 20d ago), licensed Apache-2.0. It adds 51 tokens to every session and 735 once invoked, about $0.0003 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.