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 jeffreytse/grimoire-core --skill apply-door-in-the-facegit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/apply-door-in-the-face)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-door-in-the-face"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-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.
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-door-in-the-face"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-door-in-the-face.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 | $0.00076 | $0.01812 |
| Opus 5.5 | $0.00030 | $0.00725 |
| Sonnet 5.5 | $0.00015 | $0.00362 |
| Haiku 4.5 | $0.00008 | $0.00181 |
Grade A, and why
apply-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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Door-in-the-Face
Open with a larger, genuinely plausible request you expect to be refused, then immediately retreat to your actual target request as a visible concession — because the perceived retreat triggers reciprocal concession pressure and a contrast effect that both increase compliance with the smaller request beyond what asking for it directly would produce.
Why This Is Best Practice
Why best: 以退为进 ("retreat in order to advance") names the same underlying structure Cialdini's research formalized decades later: a deliberate step back is not a loss but the specific move that makes the actual advance possible. The mechanism has two distinct, documented components — a reciprocal-concession effect (the other party experiences your retreat from the large request as a concession, creating social pressure to concede something in return, which they do by agreeing to the smaller request) and a contrast effect (the smaller request appears more reasonable specifically because it follows a larger one, independent of the reciprocity pressure). Neither component requires the other party to be unaware of the sequence to work — both operate even when the larger request was expected to be refused, which is precisely why the technique is not simply "ask for less than you want."
Cialdini, Vincent, Lewis, Catalan, Wheeler & Darby (1975): The foundational field experiment first asked participants to commit to an extensive, multi-year volunteer counseling role, which was refused as expected; researchers then "retreated" to a much smaller request — chaperoning a single zoo trip. Compliance with the smaller request was substantially higher among participants who had first refused the larger request than among a separate group asked the smaller request directly with no prior larger ask, isolating the specific effect of the large-request-then-retreat sequence rather than the smaller request's inherent appeal.
Cialdini, "Influence: The Psychology of Persuasion" (1984, 5M+ copies): Cialdini names reciprocity as one of six universal principles of influence and situates door-in-the-face specifically within it: because a concession from the other side creates a felt obligation to reciprocate, and because a genuine (not merely stated) retreat from a larger ask is itself experienced as a concession, the sequence reliably produces higher compliance than a direct request of the same final size, provided the initial request is large but still plausible rather than absurd.
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.
- 4d ago First seen · 65 lines · 76 tokens per session scan A cdd025576d25
apply-door-in-the-face is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 76 tokens to every session and 1,812 once invoked, about $0.0003 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 2026-10-17.
Other skills, from other repositories
cialdini-influence
Applies Cialdini's seven principles of ethical persuasion -- Reciprocity, Commitment and Consistency, Social Proof, Authority, Liking, Scarcity, and Unity -- to business contexts including sales, marketing, fundraising, and negotiation. Use when designing conversion funnels, optimizing sales processes, preparing…
semantic-model-disambiguation
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.