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-force-concentrationgit 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-force-concentration)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-force-concentration"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-force-concentration/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-force-concentration"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-force-concentration.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 | $0.00048 | $0.02294 |
| Opus 5.5 | $0.00019 | $0.00918 |
| Sonnet 5.5 | $0.00010 | $0.00459 |
| Haiku 4.5 | $0.00005 | $0.00229 |
Grade A, and why
apply-force-concentration 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Force Concentration
Map every contested area as empty or full, concentrate all force on the empty while completely avoiding the full, remain formless to prevent the opponent from concentrating against you, and shape the engagement so the opponent's strength becomes irrelevant.
Why This Is Best Practice
Origin: Chapter 6 of The Art of War — "Weak Points and Strong" (虛實, Emptiness and Fullness) — is the tactical chapter that operationalises the indirect strategy principle. "An army may be likened to water, for just as flowing water avoids the heights and hastens to the lowlands, so an army avoids strength and strikes weakness." (Ch.6, Giles trans.) Chapter 12 (Attack by Fire) extends the principle: disruption — like fire — multiplies force at the point of application.
Adopted by: Moltke the Elder's campaign theory (19th century Prussian military) operationalised this as Kesselschlacht (encirclement) — concentrate overwhelming force at a single point rather than equal force along the entire front. Peter Thiel's Zero to One restates it for startups: dominate a small market completely rather than entering a large market partially. Amazon's geographic expansion strategy executed it precisely — dominate one city (Seattle), then the next, rather than launching everywhere simultaneously with insufficient density.
Impact: Dispersed force produces dispersed results — mediocre everywhere. Concentrated force produces decisive results in the chosen engagement, even against a stronger opponent overall. A startup with 10% of an incumbent's resources that concentrates 100% on a single segment can achieve local superiority and win that segment, then use that position to expand.
Why best: Most organisations spread resources because it feels safer — coverage everywhere, committed to nothing. This produces an opponent who is weak everywhere and dominant nowhere. Concentration requires the discipline to explicitly abandon contests you cannot win and commit fully to the contests you can. The principle scales from feature prioritisation to market selection to sales territory allocation.
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 Changed · +1 lines 6108e8703cac
- 1mo ago First seen · 122 lines · 48 tokens per session scan A d2bede296e81
apply-force-concentration is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 48 tokens to every session and 2,294 once invoked, about $0.0002 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 2026-09-03.
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.