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-asymmetric-matching-strategygit 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-asymmetric-matching-strategy)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-asymmetric-matching-strategy"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-asymmetric-matching-strategy/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-asymmetric-matching-strategy"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-asymmetric-matching-strategy.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 | $0.00039 | $0.02287 |
| Opus 5.5 | $0.00016 | $0.00915 |
| Sonnet 5.5 | $0.00008 | $0.00457 |
| Haiku 4.5 | $0.00004 | $0.00229 |
Grade A, and why
apply-asymmetric-matching-strategy 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 1mo 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Asymmetric Matching Strategy
Rank your assets and your opponent's assets, sacrifice the slot you will certainly lose, and redeploy those resources to win the contests that determine the overall outcome.
Why This Is Best Practice
Origin: During the Warring States period (~4th century BC), the nobleman Tian Ji (田忌) repeatedly lost horse-racing bets against King Wei of Qi despite having competitive horses, because he matched horses of equal class — and lost narrowly each time. The strategist Sun Bin (孙膑) advised him to deliberately enter his worst horse against the king's best (accepting that loss), then match his best horse against the king's second-best, and his second-best against the king's weakest. Tian Ji won 2 of 3 races and won the bet. The king's lineup did not change; only the assignment did.
Adopted by: The underlying mathematics is formalised as the assignment problem in operations research, solved optimally by the Hungarian algorithm (Kuhn, 1955). It is used in logistics, military resource allocation, competitive sports scheduling (seeding), and auction strategy. Military doctrine (Sun Tzu's Art of War, which Sun Bin descended from) explicitly addresses avoiding strength-against-strength engagement. Consulting firms (McKinsey, BCG) apply the same logic to portfolio prioritisation: concede markets where you cannot win, concentrate where you can.
Impact: The strategy converts a position of overall disadvantage into a winning majority by exploiting information asymmetry and sequencing freedom. It is counter-intuitive: most people match strength-for-strength (which leads to symmetric losses) or spread resources evenly (which leads to symmetric mediocrity). The asymmetric match wins more often than either default and does so with the same total resources.
Why best: The strategy works because winning a contest by one unit counts the same as winning it by ten. A narrow win against the opponent's second-best is worth as much as an impossible win against their best. Concentrating to guarantee wins where possible, and deliberately accepting the certain loss, is a higher-expected-value allocation than symmetric matching.
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.
- 1mo ago First seen · 120 lines · 39 tokens per session scan A 49a2e042006b
apply-asymmetric-matching-strategy is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 2,287 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.