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-borrowed-forcegit 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-borrowed-force)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-borrowed-force"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-borrowed-force/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-borrowed-force"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-borrowed-force.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 | $0.00050 | $0.02135 |
| Opus 5 | $0.00025 | $0.01068 |
| Sonnet 5 | $0.00010 | $0.00427 |
| Haiku 4.5 | $0.00005 | $0.00214 |
Grade A, and why
apply-borrowed-force 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 6d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Borrowed Force
Enlist third parties with their own genuine aligned interest to attack what you cannot attack directly, staying out of the foreground while the proxy acts in their own name.
Why This Is Best Practice
Origin: Stratagem #3 of the Thirty-Six Stratagems: "Kill with a borrowed knife." The general who can mobilise enemies of his enemy — without exposing his own forces — wins without the cost of direct battle. The insight is that many parties have aligned interests with yours but different standing to act: regulators have enforcement authority you lack; press has reach you cannot buy; customers have credibility suppliers cannot manufacture; open-source communities have technical capability you cannot staff.
Adopted by: Borrowed force is the mechanism behind most successful antitrust enforcement, open-source commoditisation strategies, and analyst-driven market category creation. Netscape made Internet Explorer's bundling a regulatory issue by providing evidence to the DOJ — not by suing Microsoft itself. IBM's release of PC architecture stimulated a clone market it could not have built: borrowed force that ultimately commoditised hardware and created the conditions for Microsoft's dominance, and then Google's. Sun Tzu's own principle — "Supreme excellence consists in breaking the enemy's resistance without fighting" — applies when the proxy does the breaking.
Impact: Direct attack on a stronger opponent uses your resources and strengthens the opponent's narrative of being threatened by a competitor. Borrowed force uses the opponent's own relationships against them: a regulator's investigation, a press exposé, a customer coalition's complaint, or an open-source alternative has a legitimacy and a reach that direct competitive attack does not. The proxy's standing and credibility multiply your effective force.
Why best: The key constraint on borrowed force is that the proxy must have genuine aligned interest — manufactured proxies are transparent and counterproductive. This is not a manipulation strategy; it is an alignment strategy: finding parties whose authentic interests coincide with yours and providing the resources or information that help them act on those interests.
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.
- 6d ago First seen · 112 lines · 50 tokens per session scan A f890354229e9
apply-borrowed-force is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 20d ago), licensed MIT. It adds 50 tokens to every session and 2,135 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
counseling-psychology
Therapeutic frameworks, assessment, ethical practice, and client documentation for counselors and psychologists.
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.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
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.