poke-holes

poke-holes is a skill for Claude Code from danweinerdev/claude-sdd-planner. It costs 42 tokens per session (1,882 once invoked), scanned A, original, MIT.

An adversarial review skill that challenges plans, specifications, and designs by looking for missing details, weak assumptions, and ways they could fail.

In plain words
What is it for?
Use it to stress-test a project plan, product specification, or technical design and ask what could go wrong.
Why use it?
It gives you a deliberate critical review before implementation, when overlooked problems are cheaper to fix.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the sdd-planner plugin — 34 skills, 8 agents shipped together

Good fit Use it to stress-test a project plan, product specification, or technical design and ask what could go wrong.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danweinerdev/claude-sdd-planner/poke-holes
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 danweinerdev/claude-sdd-planner --skill poke-holes
Clone the repo
git clone --depth 1 https://github.com/danweinerdev/claude-sdd-planner

Made for: Claude Code.

Or install sdd-planner, the plugin that ships this one along with the rest of its 34 skills, 8 agents.

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 poke-holes

README.md
[![agentmods](https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/poke-holes/github.svg)](https://agentmods.dev/skills/danweinerdev/claude-sdd-planner/poke-holes)
Your own site
<a href="https://agentmods.dev/skills/danweinerdev/claude-sdd-planner/poke-holes"><img src="https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/poke-holes/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 poke-holes

Your own site · 80×15
<a href="https://agentmods.dev/skills/danweinerdev/claude-sdd-planner/poke-holes"><img src="https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/poke-holes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,882 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 $0.00042 $0.01882
Opus 5 $0.00021 $0.00941
Sonnet 5 $0.00008 $0.00376
Haiku 4.5 $0.00004 $0.00188

Measured 10d ago against content hash b7e3713627b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

poke-holes 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.

commands/poke-holes/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/poke-holes — Adversarial Critical Analysis

Path Resolution

The plugin directory contains commands/, agents/, and shared/ as siblings. Find it by globbing for **/commands/research/SKILL.md in both the current directory and ~/.claude/plugins/cache/; if multiple versions match, sort them as semantic versions (like sort -V) and use the highest, then strip commands/research/SKILL.md from the match. Resolve the planning root (artifacts) and target repository per shared/path-resolution.md in the plugin directory.

When to Use

When you need an adversarial critical review of a planning artifact before committing to it. Good for stress-testing plans before approval, finding gaps in specs, and challenging design assumptions. This is not a structural review (sdd-planner:plan-reviewer and sdd-planner:spec-reviewer handle that). This skill actively tries to break the thinking.

Think of it as the planning-artifact counterpart to sdd-planner:blind-spot-finder (which does the same thing against code diffs): fresh eyes, hostile framing, deliberately looking for what the author didn't think about.

Process

  1. Identify Target

    • Ask which artifact to analyze (plan, spec, design, or brainstorm)
    • Confirm the artifact path before proceeding
  2. Gather Context Read the full target artifact yourself in the primary context (a single-artifact read is lightweight and the raw wording is the attack surface). Dispatch sdd-planner:researcher only for the related-context sweep:

    • Read all documents referenced in the target's related frontmatter
    • Search for any specs, designs, or plans that reference this artifact (by filename or title)
    • Return a structured summary containing:
      • Related context that informs analysis (from related docs and reverse references)
      • Cross-references, dependencies, and any conflicts between documents
  3. Adversarial Analysis Apply the lenses below to the full artifact text you read, informed by the researcher's related-context summary. The posture is adversarial — you are not checking whether the artifact is well-structured, you are trying to find the thing that will blow up in six weeks. For every finding, produce a concrete scenario: a sequence of events, inputs, or conditions that exposes the flaw. "This is risky" is not a finding. "If the downstream service returns a 503 during step 3, the transaction is orphaned and the plan has no cleanup story" is a finding.

Read the full file on GitHub · 117 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 · 117 lines · 42 tokens per session scan A b7e3713627b1

Subscribe to this mod's changes

poke-holes is a skill published in the GitHub repository danweinerdev/claude-sdd-planner (2 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,882 once invoked, about $0.0002 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

moai-workflow-thinking

Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.

modu-ai/moai-adk · 43 tokens

moai-platform-chrome-extension

Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome. APIs, side panel, declarativeNetRequest, and Chrome Web Store publishing. Use when building browser extensions.

modu-ai/moai-adk · 48 tokens

moai-framework-electron

Electron 33+ desktop app development specialist covering Main/Renderer process architecture, IPC communication, auto-update, and packaging with Electron Forge. Use when building cross-platform desktop applications.

modu-ai/moai-adk · 41 tokens

moai-foundation-context

Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.

modu-ai/moai-adk · 41 tokens

moai-domain-uiux

UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.

modu-ai/moai-adk · 49 tokens

moai-platform-database-cloud

Cloud database platform specialist covering Neon (serverless PostgreSQL), Supabase (PostgreSQL 16 with real-time), and Firebase Firestore (NoSQL with offline sync). Use when choosing or setting up cloud databases.

modu-ai/moai-adk · 51 tokens