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 askarzh/epistemator --skill doorsgit clone --depth 1 https://github.com/askarzh/epistematorWrote 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/askarzh/epistemator/doors)<a href="https://agentmods.dev/skills/askarzh/epistemator/doors"><img src="https://agentmods.dev/badge/skills/askarzh/epistemator/doors.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.02364 |
| Opus 5 | $0.00043 | $0.01182 |
| Sonnet 5 | $0.00017 | $0.00473 |
| Haiku 4.5 | $0.00009 | $0.00236 |
Grade A, and why
doors 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 7d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One-Way / Two-Way Door Decision Triage
Overview
Apply the One-Way / Two-Way Door decision framework (Type 1 / Type 2 decisions), articulated by Jeff Bezos in his 2015 and 2016 Amazon shareholder letters. This is a meta-analytical triage tool designed for velocity. Its primary purpose is to prevent decision paralysis by determining how much thinking is actually required before acting.
This is not a deep analytical framework like the other four in this toolkit. It is a pre-analytical classifier: it answers "how should I decide?" before you decide "what should I decide?" Highly analytical thinkers often make the mistake of treating all decisions as One-Way doors, deploying heavy cognitive machinery on reversible problems. This framework categorizes the decision, sets the required information threshold, and most importantly, attempts to structurally transform One-Way doors into Two-Way doors to maintain momentum.
The framework is a practitioner tool from business leadership, not academic theory. However, its core insight — that irreversibility under uncertainty creates option value — is rigorously grounded in real options theory (Dixit & Pindyck, Investment under Uncertainty, 1994). The vocabulary is Bezos's; the economics are sound.
Core Methodology
-
Classify the Door — Determine whether the decision is reversible (Two-Way Door / Type 2) or irreversible (One-Way Door / Type 1). Reversibility is a spectrum, not a binary. Evaluate along three dimensions:
- Reversal cost: How expensive is it to undo? ($100 vs. $1M are both "reversible" but very different decisions.)
- Reversal speed: How long does it take to walk back? A feature flag takes seconds; a public announcement takes months of reputation repair.
- Blast radius: How many people, systems, or commitments are affected? A team experiment vs. a company-wide reorganization.
If the decision is clearly a Two-Way door, apply the 70% rule and act. If it is clearly a One-Way door, proceed to step 2. If ambiguous, treat it as a One-Way door and proceed to step 3 (transformation).
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.
- 7d ago First seen · 122 lines · 86 tokens per session scan A f2f89618226b
doors is a skill published in the GitHub repository askarzh/epistemator (3 stars, last pushed 6mo ago), licensed MIT. It adds 86 tokens to every session and 2,364 once invoked, about $0.0004 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
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
add-cloud-flow
Integrates Power Automate cloud flows into a Power Pages site. Lists available flows, suggests relevant ones based on intent, identifies scenarios and web roles, creates metadata files, and generates client-side code to call flows. Handles both new flow registration and adding already-registered flows to additional…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
deploy-site
Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.