validate-change-plan

validate-change-plan is a skill for Claude Code, Codex from cdeust/ai-architect-mcp-codebase. It costs 53 tokens per session (387 once invoked), scanned A, original, MIT.

A workflow for checking whether an implementation plan matches the current structure of a codebase.

In plain words
What is it for?
Use it to review plans that name files, functions, dependencies, boundaries, or expected effects, and to compare a real code change with the plan.
Why use it?
It catches missing files or symbols, incorrect dependency assumptions, and an underestimated scope of impact before coding begins.

Skill for Claude CodeCodex

Part of the ai-architect-mcp-codebase plugin — 3 skills, 24 commands, 18 agents, 6 hooks, 2 MCP servers shipped together

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 skills/cdeust/ai-architect-mcp-codebase/validate-change-plan
Any agent
npx skills add cdeust/ai-architect-mcp-codebase --skill validate-change-plan
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code, Codex.

Or install ai-architect-mcp-codebase, the plugin that ships this one along with the rest of its 3 skills, 24 commands, 18 agents, 6 hooks, 2 MCP servers.

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-change-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp-codebase/validate-change-plan.svg)](https://agentmods.dev/skills/cdeust/ai-architect-mcp-codebase/validate-change-plan)
Your own site
<a href="https://agentmods.dev/skills/cdeust/ai-architect-mcp-codebase/validate-change-plan"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp-codebase/validate-change-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 387 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 $0.00053 $0.00387
Opus 5 $0.00026 $0.00193
Sonnet 5 $0.00011 $0.00077
Haiku 4.5 $0.00005 $0.00039

Measured 5d ago against content hash be3417813b75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-change-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 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.

plugins/ai-architect-mcp-codebase/skills/validate-change-plan/SKILL.md · 24 lines

What it actually says

Validate Change Plan

Use only the eight tools in the core profile. Do not present this workflow as equivalent to the full profile's PRD validator, security gates, or semantic-diff verifier.

Workflow

  1. Break the plan into falsifiable claims: files exist, symbols exist, dependency directions are correct, named boundaries match communities or processes, and the stated blast radius is plausible.
  2. Call health_check, then build or refresh the graph with analyze_codebase. Reuse the returned graph_path.
  3. Resolve each named symbol with search_codebase, then verify it with get_symbol or get_context. Mark ambiguous or missing names as unverified instead of choosing a convenient match.
  4. Call get_impact for every symbol the plan changes. Compare callers, importers, users, implementors, communities, and processes with the plan's scope claims.
  5. If a real diff exists, call detect_changes and compare its affected symbols and risk scores with the plan. Skip this step for a plan-only review.
  6. Call query_graph with graph="missed". Inspect flagged files or ranges before accepting any absence-based claim.
  7. Use read-only query_graph queries for remaining structural assertions, adding ORDER BY when paging.

Verdict

Return one row per plan claim with the evidence, a verdict of supported, contradicted, or unverified, and the smallest correction needed. End with coverage gaps, unresolved questions, likely tests, and the plan steps that require deeper semantic or runtime validation.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 24 lines · 53 tokens per session scan A be3417813b75

Subscribe to this mod's changes

validate-change-plan is a skill published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 387 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.

Related

Other skills, from other repositories

new-skill

Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…

hyhmrright/brooks-lint · 145 tokens

release

Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…

hyhmrright/brooks-lint · 135 tokens

brooks-audit

Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized…

hyhmrright/brooks-lint · 143 tokens

brooks-test

Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…

hyhmrright/brooks-lint · 161 tokens

architecture-refiner

Facilitate a structured conversation to define architecture principles for a repository. Supports multiple architecture styles: clean architecture (default), hexagonal / ports & adapters, modular monolith, or custom. Produces a formal architecture document that the corresponding atom will use. Use when setting up a…

techygarg/lattice · 114 tokens

review

Perform a structured code review by composing validation checklists from relevant atoms based on what code changed. Loads atoms conditionally -- clean-code always, architecture/DDD/security/tests only when the delta touches their domain. Produces a severity-ordered report with specific locations and fixes. Use when…

techygarg/lattice · 95 tokens