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 sandsower/beislid --skill poke-holesgit clone --depth 1 https://github.com/sandsower/beislidWrote 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/sandsower/beislid/poke-holes)<a href="https://agentmods.dev/skills/sandsower/beislid/poke-holes"><img src="https://agentmods.dev/badge/skills/sandsower/beislid/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.
<a href="https://agentmods.dev/skills/sandsower/beislid/poke-holes"><img src="https://agentmods.dev/badge/skills/sandsower/beislid/poke-holes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00116 | $0.00715 |
| Opus 5 | $0.00058 | $0.00358 |
| Sonnet 5 | $0.00023 | $0.00143 |
| Haiku 4.5 | $0.00012 | $0.00072 |
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 9d 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.
What it actually says
Requires an existing plan, spec, or design to pressure-test. Not for extracting requirements from scratch — use spec for that.
Optional visual routing: only when repo-level beislid:visual_surfaces config exists and the effective poke-holes mode is active, load visual-surface-protocol.md; it mirrors canonical .beislid/visual-surface-protocol.md for copied installs. Use Lavish conservatively, only when a decision tree, branching tradeoff matrix, risk map, architecture/dependency diagram, or visual input control materially improves the stress test. Absent config or off must not mention or invoke Lavish.
Workflow signals
When workflow_signals is configured, use the best-effort CLI to expose semantic state:
- At start/resume of interrogation, emit
beislid workflow-signal emit working --skill poke-holes --phase interrogate. - If no existing plan/spec/design is available, emit
beislid workflow-signal emit blocked --skill poke-holes --phase missing-inputbefore asking the user to provide one or route tospec. - Before every interview question that needs the user's answer, emit
beislid workflow-signal emit waiting --skill poke-holes --phase question. - When exploring the codebase to answer a question from evidence, emit
beislid workflow-signal emit working --skill poke-holes --phase explore. - When shared understanding is reached and the stress-test is complete, emit
beislid workflow-signal emit done --skill poke-holes --phase complete.
The command is safe to call even when unconfigured, outside tmux, or without tmux-glance; it no-ops rather than blocking the interview.
Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
If a question can be answered by exploring the codebase, explore the codebase instead.
When active visual routing is useful, apply the protocol at a concrete branch/decision/revision boundary, not for every interview turn. Respect suggest/prompt/auto exactly; unattended prompt mode falls back to Markdown/chat unless the run envelope already grants permission. The supplemental surface should use comparison, diagram, and input playbook guidance and include one typed BEISLID_VISUAL_FEEDBACK_V1 gate for workflow: poke-holes, action resolve_revise_or_choose_poke_holes, and decisions resolved, revise, or choose (choose requires selected_option). Copy accepted visual resolutions, revisions, or branch choices into the canonical Markdown/chat stress-test record before marking the check complete or routing back to the owning planning skill; visual controls never approve implementation by themselves.
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.
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.
- 9d ago First seen · 27 lines · 116 tokens per session scan A 1f98890187ab
poke-holes is a skill published in the GitHub repository sandsower/beislid (10 stars, last pushed 10d ago), licensed MIT. It adds 116 tokens to every session and 715 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…