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-ally-far-attack-neargit 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-ally-far-attack-near)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-ally-far-attack-near"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-ally-far-attack-near/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-ally-far-attack-near"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-ally-far-attack-near.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 | $0.00051 | $0.03796 |
| Opus 5 | $0.00026 | $0.01898 |
| Sonnet 5 | $0.00010 | $0.00759 |
| Haiku 4.5 | $0.00005 | $0.00380 |
Grade A, and why
apply-ally-far-attack-near 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 9d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Ally Far, Attack Near
When expanding against multiple competitors sequentially, first identify which distant actors could intervene to rescue your immediate targets; form alliances with those distant actors to neutralise the rescue option; then attack near targets in sequence, closest first — because attacking without neutralising the rescue option allows any target to hold out until reinforced, and attacking distant targets while near threats remain creates a two-front vulnerability that your opponents can exploit.
Why This Is Best Practice
Origin: In approximately 266 BC, Fan Sui (范雎) was appointed as a minister to King Zhaoxiang of Qin (秦昭王). Qin had been pursuing an expansionist strategy but with limited systematic doctrine: attacking sometimes near, sometimes far, creating tactical victories without strategic accumulation. Fan Sui submitted a memorial to the king that identified the critical error: Qin had been attacking states far away (Qi, for example) while leaving the near states of Han and Wei intact. Any distant conquest was impossible to hold because Han and Wei were still strong enough to threaten Qin's flanks and disrupt supply lines to distant occupied territory. Fan Sui's doctrine: 远交近攻 — form distant alliances, attack near targets. His specific proposal: ally with Qi (distant, no direct territorial conflict with Qin) and attack Han and Wei (near, directly threatening Qin's expansion corridor). The logic was geometric: near states threaten your flanks and can interdict supply to distant occupied territory; distant states cannot be threatened by you (no direct territorial pressure) but can rescue near states if those near states are under attack. Eliminate the near threats first, with the distant alliance in place to prevent rescue. Then renegotiate the distant alliance from a position of increased strength.
Qin adopted this doctrine and executed it systematically over the following decades. By 221 BC — approximately 45 years after Fan Sui's memorial — Qin had unified all of China, eliminating each near state in sequence while managing alliances with more distant ones. The doctrine was not the only factor, but the systematic near-to-far sequencing was a consistent feature of Qin's conquest strategy.
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.
- 9d ago First seen · 116 lines · 51 tokens per session scan A a5d4284f23ef
apply-ally-far-attack-near is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 24d ago), licensed MIT. It adds 51 tokens to every session and 3,796 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
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.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
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.
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.