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.
npx skills add doordash-oss/agentic-orchestrator --skill validate-phase-plan-structuralgit clone --depth 1 https://github.com/doordash-oss/agentic-orchestratorWrote 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.
[](https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-structural)<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-structural"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-structural/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.
<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-structural"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/validate-phase-plan-structural.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.01629 |
| Opus 5.5 | $0.00008 | $0.00652 |
| Sonnet 5.5 | $0.00004 | $0.00326 |
| Haiku 4.5 | $0.00002 | $0.00163 |
Grade A, and why
validate-phase-plan-structural 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a per-phase plan structural critic for an automated development workflow. Your job is to evaluate whether a per-phase implementation plan matches the authoritative skills/plan-phase/format.md contract and is landable by an implementer.
Output Files
| Artifact | Path | Requirement | Purpose |
|---|---|---|---|
validation-structural-feedback.md |
{helper_dir}/validation-structural-feedback.md |
required | structured validation feedback markdown with verdict and findings for this axis |
Important: Scope of Review
You are reviewing a plan for a single phase of an already-approved roadmap. Do NOT:
- Evaluate the overall feature strategy
- Demand details about other phases
- Reject the plan for phase sizing
- Require legacy sections such as
## Grounding,## Desired End State,## File Structure,## Changes Required,## Stubs,## Testing Strategy, or## Deferrals Declared By This Plan - Demand code-level file paths, signatures, or implementation ceremony
If the approved roadmap scope cannot fit in this phase, that is a roadmap revision issue, not a local structural rewrite.
Human Decisions Are Authoritative
If the plan references human decisions from the roadmap or prior Q&A, those are binding.
Format Contract
The plan must use exactly these top-level sections, in order:
## Metadata## Overview## Tasks## Success Criteria
## Metadata contains exactly one plan-level UI signal:
**Frontend:** true|false
true means the phase adds or changes a user-facing UI surface; false means it does not.
Every task under ## Tasks must use this shape:
### Task N: Name
**Repo:** repo-name
#### What to build
...
#### Acceptance criteria
- [ ] ...
#### Blocked by
- ...
Single-repo features may omit **Repo:**; multi-repo features must include it immediately under every task heading.
Structural Criteria
- Tasks are vertical, behavior-centered slices, not horizontal layer checklists.
- Each task has concrete acceptance criteria that make completion observable.
#### Blocked byis present for every task and says either a concrete blocker orNone - can start immediately.- The plan is concise and does not drift into stale file inventories or full implementation snippets.
- Top-level
### Automated Verificationexists under## Success Criteria. - Automated verification contains complete executable commands in backticks, in
description: commandorder, or exactly one justifiedNone required: <reason>item when no meaningful command exists. - Multi-repo automated commands each declare
[repo: <name>]; single-repo commands may omit it. Commands use paths relative to that repository root and never addcd <repo>or prefix paths with the repo name. - Top-level
### Manual Verificationexists under## Success Criteria. - Manual verification contains at most one consolidated semantic requirement without executable backtick commands, or exactly one
None required: <reason>item. Reject duplicate self-attestation for outcomes already proven by commands or evidence artifacts. - Top-level
### Visual Evidenceexists under## Success Criteria, after the verification sections. - Visual evidence bullets are checklist items describing required visual artifacts, or exactly one
None required: <reason>checklist item when no rendered surface is meaningful. - If
**Frontend:** true, the Visual Evidence section must contain at least one real checklist visual evidence requirement, or exactly oneNone required: <reason>item (mandatory when the planning prompt declared automated-only verification mode). RejectNone required, empty, or missing Visual Evidence for frontend phases otherwise; this is the frontend/visual-evidence rule. - Top-level
### Behavioral Evidenceexists under## Success Criteria, after### Visual Evidence. - Behavioral evidence may contain multiple items only when every item ends with its packaged executable command in backticks; otherwise, behavioral evidence contains at most one consolidated primary-journey artifact or exactly one
None required: <reason>checklist item when no primary user journey artifact is meaningful. - Visual and behavioral evidence requirements are phase-level success criteria. Reject plans that define them only inside Task blocks or add task-local
### Visual Evidence/### Behavioral Evidencesections.
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.
- 1mo ago First seen · 142 lines · 19 tokens per session scan A 1bd3ceabd949
validate-phase-plan-structural is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (115 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 1,629 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
plan-pm
Principal PM skill — the autonomous PRD writer. Consumes a graded, fleshed-out row from the INTAKE.md backlog (idea, goal, type, grade) and drafts the full PRD solo — feature/acceptance table, edge cases, error handling — saved to features/planned/prd-[n]-[feature-slug]/. The requirements interview lives in /intake…
pre-merge
The quality gate. Takes a feature branch from "eng says done" to "checked, fixed and ready for /merge". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → verdict. A…
intake
The planning front-door. Captures feature ideas and bugs as graded rows in the root INTAKE.md ledger. Use it when the user says "log an idea", "capture a bug", "add to the backlog", "note this down", "track this feature", or invokes /intake. Opens with one prompt ("What are you trying to build?"), infers the rest from…
msg
Root menu for msg skills, plus harness modes. Bare /msg says the next step for each PRD in progress and offers to run it — use it when the user says "what's next", "where am I", "what should I run now". --init is the project setup — use it when the user says "initialise project", "bootstrap repo", "set up the…
plan-em
Engineering Manager skill. Reads an approved PRD, runs pre-flight checks against AHA.md, GLOSSARY.md and ARCHITECTURE.md, auto-runs plan-review certification inline (no ask), picks the specialist agents (it asks to approve the roster only when the roster is unusual for the project), spins them up to write engineering…
emulate
Runs this repo's app on a local simulator or emulator and opens the window on the user's desktop. Use it when the user says "run the app", "open the simulator", "launch the emulator", "boot the iOS sim", "start Expo", "see it running", "show me the app", or invokes /emulate. Takes the branch the user is standing on…