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-hostile-room-conversiongit 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-hostile-room-conversion)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-hostile-room-conversion"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-hostile-room-conversion/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-hostile-room-conversion"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-hostile-room-conversion.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 | $0.00064 | $0.04117 |
| Opus 5.5 | $0.00026 | $0.01647 |
| Sonnet 5.5 | $0.00013 | $0.00823 |
| Haiku 4.5 | $0.00006 | $0.00412 |
Grade A, and why
apply-hostile-room-conversion 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Hostile Room Conversion
Before presenting your positive case, engage each major objector individually by name — exposing the logical inconsistency in their specific position, not defending your own — until no one in the room can maintain their stated objection without contradicting themselves or each other; then make your case briefly to a room that is now free to accept it.
Why This Is Best Practice
Origin: In 208 AD, Cao Cao's army of several hundred thousand soldiers was advancing south. Sun Quan, ruler of the Jiangdong territories, faced two options: surrender or resist. His court was dominated by advisors — led by the senior counsellor Zhang Zhao — who favoured surrender. Into this court came Zhuge Liang, alone, as Liu Bei's envoy, proposing the alliance that would become the Battle of Red Cliffs. The odds against him were extreme: a room full of pre-committed surrender advocates, each with prepared arguments, each reinforcing the others' position through collective presence. Zhuge Liang did not open with the case for alliance. He addressed each scholar individually, by name, in sequence. To Zhang Zhao's argument about Cao Cao's overwhelming numbers, he exposed the contradiction with Zhang Zhao's own prior advocacy for Sun Quan's independence. To each subsequent objection, he identified either an internal inconsistency in the objector's position or a contradiction with the position of a scholar who had just been addressed. He did not make the positive case for the alliance until the room had watched every major objection dismantled. By the end, Sun Quan called the alliance. The Battle of Red Cliffs followed, and the Three Kingdoms era began.
Adopted by: The sequential-individual-defeat mechanism underlies the most effective performances in adversarial group settings. Cicero's prosecution of Gaius Verres (70 BC) systematically dismantled each of Verres' witnesses and character supporters before presenting the substantive case — the jury had already watched the defence collapse before the prosecution's case began. Modern high-stakes practitioners include Steve Jobs at his most effective product presentations, where objections to price, competitive comparison, or market need were addressed one by one before the positive case was made: "You might say it's too expensive — [addresses]. You might say Apple doesn't know the phone business — [addresses]. You might say the market already has smartphones — [addresses]. Now here's what we actually built." Congressional testimony by executives prepared by elite litigation teams follows the same structure: each anticipated hostile question gets addressed individually before the witness's positive narrative.
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 · 138 lines · 64 tokens per session scan A 0bb4eccdaf75
apply-hostile-room-conversion is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 64 tokens to every session and 4,117 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
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.
agent-governance
Patterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.