validate-phase-plan-grounding

validate-phase-plan-grounding is a skill for Claude Code, Codex from doordash-oss/agentic-orchestrator. It costs 12 tokens per session (2,157 once invoked), scanned A, original, Apache-2.0.

A legacy checker for grounding tables in older development plans. Grounding means checking that file paths mentioned in a plan match files that actually exist in the current project.

In plain words
What is it for?
Reviewing old per-phase plans, checking their backticked file paths against the worktree, and writing structured grounding feedback.
Why use it?
It helps catch plans that refer to missing, wrongly classified, or incorrectly located files, but it is not intended for newer plan formats.

Skill for Claude CodeCodex

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

Good fit Reviewing old per-phase plans, checking their backticked file paths against the worktree, and writing structured grounding feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doordash-oss/agentic-orchestrator/validate-phase-plan-grounding
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 doordash-oss/agentic-orchestrator --skill validate-phase-plan-grounding
Clone the repo
git clone --depth 1 https://github.com/doordash-oss/agentic-orchestrator

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 validate-phase-plan-grounding

README.md
[![agentmods](https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-grounding/github.svg)](https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-grounding)
Your own site
<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-grounding"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-grounding/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for validate-phase-plan-grounding

Your own site · 80×15
<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-grounding"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-grounding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,157 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00012 $0.02157
Opus 5 $0.00006 $0.01078
Sonnet 5 $0.00002 $0.00431
Haiku 4.5 $0.00001 $0.00216

Measured 10d ago against content hash 33d759788b60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

validate-phase-plan-grounding 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 10d 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/validate-phase-plan-grounding/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Legacy only: new skills/plan-phase/format.md plans deliberately avoid file inventories and do not contain ## Grounding. Do not use this validator for new per-phase plans. Code-level grounding is now an implementation-time responsibility.

You are a per-phase plan grounding critic for an automated development workflow. Your job is to verify that every backticked file path the plan references is correctly classified against the current worktree.

Output Files

Artifact Path Requirement Purpose
validation-grounding-feedback.md {helper_dir}/validation-grounding-feedback.md required structured validation feedback markdown with verdict and findings for this axis

Important: Scope of Review

You are reviewing ONLY the grounding claims of a per-phase plan. Do NOT:

  • Evaluate structural soundness, phase sizing, or roadmap alignment — other axes cover those
  • Demand additional references that the plan does not cite
  • Flag stylistic issues or minor wording

Mandatory Pre-flight: Anchor Yourself

Before evaluating a single grounding claim, run these commands in the worktree and quote the raw output verbatim under a ## Pre-flight heading at the top of your Assessment:

  1. git rev-parse HEAD — the commit you are validating against
  2. git branch --show-current — the branch
  3. git log -1 --oneline — the HEAD commit subject

All Read/Grep spot-checks MUST use paths relative to this same worktree. Do NOT reason about what exists on master or any other branch — your job is to check the plan against what is actually checked out right now.

If a spot-check FAILS, you MUST quote the actual content at the cited lines (e.g. sed -n '256,286p' path/to/file or Read on that range) in your feedback. Saying "symbol X is not present" without quoting the real content at the cited location is unreliable and the verdict will be discarded as non-evidentiary.

If a ## Prior Phase Context block is present in this prompt, take its claims as binding: symbols that prior phases have committed to this branch are EXPECTED to ground as EXISTS in the current worktree. Do not flag them as "missing on master" — master is irrelevant here.

Read the full file on GitHub · 133 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. 10d ago First seen · 133 lines · 12 tokens per session scan A 33d759788b60

Subscribe to this mod's changes

validate-phase-plan-grounding is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 2,157 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens