door-in-the-face

door-in-the-face is a skill for Claude Code, Codex from deciqAI/knowledge-skills. It costs 123 tokens per session (1,916 once invoked), scanned A, original, MIT.

A negotiation technique that begins with a large request, expects refusal, and then retreats to a smaller request. The smaller request may seem more acceptable because the retreat looks like a concession.

In plain words
What is it for?
Use it to recognise or design two-step requests in negotiations, fundraising, and sales, while judging whether the first request is credible and appropriate.
Why use it?
It explains why someone may agree more readily after rejecting an initial demand and helps identify when this pattern is being used on you.

Skill for Claude CodeCodex

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

Good fit Use it to recognise or design two-step requests in negotiations, fundraising, and sales, while judging whether the first request is credible and appropriate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deciqai/knowledge-skills/door-in-the-face
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 deciqAI/knowledge-skills --skill door-in-the-face
Clone the repo
git clone --depth 1 https://github.com/deciqAI/knowledge-skills

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 door-in-the-face

README.md
[![agentmods](https://agentmods.dev/badge/skills/deciqai/knowledge-skills/door-in-the-face/github.svg)](https://agentmods.dev/skills/deciqai/knowledge-skills/door-in-the-face)
Your own site
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/door-in-the-face"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/door-in-the-face/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 door-in-the-face

Your own site · 80×15
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/door-in-the-face"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/door-in-the-face.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,916 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 $0.00123 $0.01916
Opus 5 $0.00062 $0.00958
Sonnet 5 $0.00025 $0.00383
Haiku 4.5 $0.00012 $0.00192

Measured 11d ago against content hash 694a4d56618b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

door-in-the-face 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 11d 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.

door-in-the-face/SKILL.md · 122 lines

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.

Door-in-the-Face Technique

Overview

Ask for something large (expect refusal), then retreat to the smaller request you actually wanted. The empirically documented result: compliance with the smaller ask is 2-3x higher than asking for it directly (Cialdini et al., 1975). The mechanism is reciprocal concession — the target perceives your retreat as a concession and feels social pressure to match it.

Three operations: recognize DITF when used on you; design it ethically as a proposer; distinguish it from pure anchoring (two requests with refusal vs. a single number). Composes with reciprocity, anchoring, signaling-games, batna-zopa.

When to Use

  • Designing a negotiation opening where you want to land at a specific price/term
  • Designing a fundraising ask where the target gift is moderate but commitment to the cause is high
  • Designing a sales process where you want customers in a specific tier
  • Recognizing that you are being run with DITF by an opposing party
  • Someone says: "door-in-the-face," "reciprocal concession," "anchor high then retreat," "they conceded so I should too"

Not when: the larger request is so absurd the target reads the opening as bad faith (the technique collapses); the target has no reciprocity norm operating; you are negotiating with a counterparty who will read your retreat as DITF.

Coaching Novices (Adaptive Front Door)

  • Engine mode: user has a concrete case → run The Process directly.
  • Coach mode: user is unfamiliar or has no concrete case → guide step by step.

In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.

  1. One-line: if you ask for X (large) and get refused, then ask for Y (smaller, what you actually wanted), you get Y more often than if you asked for Y directly — because the target feels they should concede after watching you concede.
  2. Check fit — absurd-anchor situations → DITF collapses; point elsewhere.
  3. Elicit the real situation.

[WAIT — do not advance until user responds]

  1. One question at a time: is this technique being used on me? What's the actual smaller ask? What's my counterparty's BATNA?

[WAIT — do not advance until user responds]

  1. Close: the specific opening + retreat sequence, or the specific defense.

[WAIT — do not advance until user responds]

Read the full file on GitHub · 122 lines

Files

What ships with it

2 files 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.

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. 11d ago First seen · 122 lines · 123 tokens per session scan A 694a4d56618b

Subscribe to this mod's changes

door-in-the-face is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 123 tokens to every session and 1,916 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.

Related

Other skills, from other repositories

edge-tts

Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…

aahl/skills · 85 tokens

mcp-deepwiki

Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.

aahl/skills · 44 tokens

tianqi

A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.

aahl/skills · 24 tokens

cto-advisor

Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".

alebgl77/claude-inc · 62 tokens

compliance-check

Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…

alebgl77/claude-inc · 98 tokens

plan-payroll

Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…

alebgl77/claude-inc · 0 tokens