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-differentiated-reciprocitygit 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-differentiated-reciprocity)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-differentiated-reciprocity"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-differentiated-reciprocity/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-differentiated-reciprocity"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-differentiated-reciprocity.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 | $0.00079 | $0.01974 |
| Opus 5.5 | $0.00032 | $0.00790 |
| Sonnet 5.5 | $0.00016 | $0.00395 |
| Haiku 4.5 | $0.00008 | $0.00197 |
Grade A, and why
apply-differentiated-reciprocity 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Differentiated Reciprocity
Respond to a wrong with proportionate fairness — neither indiscriminate forgiveness that erodes accountability nor escalating retaliation that compounds the conflict — and respond to genuine kindness with kindness in kind, rather than applying the same response regardless of how you were actually treated.
Why This Is Best Practice
Origin: In the Analects (論語, Book 14, "Xian Wen"), a questioner asks Confucius about the popular notion of repaying a wrong with kindness (以德報怨) — essentially unconditional forgiveness toward those who wrong you. Confucius rejects this directly, asking: if a wrong is repaid with kindness, how then would genuine kindness itself be repaid? His stated position is a differentiated response: repay a wrong with 直 — proportionate directness, fairness, an undistorted response that is neither excessively lenient nor excessively harsh — and repay kindness with kindness (以德報德), reciprocating good treatment in kind. The teaching's structure is a deliberate rejection of two failure modes: indiscriminate leniency, which erodes the accountability that makes fair dealing sustainable, and (by the same logic) indiscriminate retaliation, which escalates conflict rather than resolving it.
Adopted by: Robert Axelrod's iterated-tournament research in The Evolution of Cooperation (1984) — a foundational, widely taught result in game theory — found that reciprocity-based strategies (respond to cooperation with cooperation, respond to defection with a proportionate, non-escalating response) systematically outperformed both unconditionally cooperative strategies, which are exploited by bad-faith actors, and unconditionally hostile strategies, which forfeit the sustained gains available from mutual cooperation. Nowak and Sigmund's later refinement (Nature, 1992/1993) found that strategies combining bounded forgiveness with continued responsiveness to a genuine pattern of wrongdoing ("generous tit-for-tat") are more stable over repeated interaction than strict, unforgiving retaliation.
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 · 64 lines · 79 tokens per session scan A cfb0f583c88a
apply-differentiated-reciprocity is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 1,974 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 2026-09-03.
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.