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-merit-selectiongit 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-merit-selection)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-merit-selection"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-merit-selection/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-merit-selection"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-merit-selection.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 | $0.00065 | $0.02553 |
| Opus 5 | $0.00032 | $0.01277 |
| Sonnet 5 | $0.00013 | $0.00511 |
| Haiku 4.5 | $0.00006 | $0.00255 |
Grade A, and why
apply-merit-selection 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 5d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Merit Selection
When evaluating candidates for selection, promotion, or recommendation, test your judgment against the reversed-relationship check: would you make the same decision if this person were your personal enemy? If not, bias — not merit — is driving the evaluation.
Why This Is Best Practice
左传 襄公三年 (~570 BC) — 祁奚举贤:
外举不弃仇,内举不失亲。
"Externally recommend even your enemy; internally do not withhold recommendation from your own kin."
Why best: When the senior minister Qi Xi (祁奚) was asked to recommend a replacement for his own position, he immediately recommended Jie Hu — his personal enemy. When asked again for a recommendation later, he recommended his own son, Qi Wu. In both cases, the recommendation was on merit alone. The historian's commentary: "Qi Xi was impartial — he recommended his enemy without favoritism against him, and recommended his family without favoritism toward them." The principle is not that personal relationships are irrelevant, but that they must be explicitly counteracted: you test whether your evaluation would survive if the relationship were reversed. If it would not, the evaluation is not meritocratic.
Cecilia Rouse & Claudia Goldin — "Orchestrating Impartiality" (2000, American Economic Review): The most empirically rigorous study of bias in talent evaluation. When symphony orchestras switched from sighted to blind auditions (screen blocking the evaluators' view of the performer), the probability of a woman advancing past preliminary rounds increased by approximately 50%. The auditioners believed they were evaluating on merit before the blind audition was introduced; they were wrong. The performance itself did not change — only the evaluator's knowledge of the performer's identity changed. This study is cited in virtually every discussion of selection bias and is the empirical foundation for structured, blind evaluation processes at Google, Deloitte, KPMG, and others.
NFL Rooney Rule (2003): The Diversity Advisory Committee of the NFL established a requirement that teams must interview at least one minority candidate for any head coach opening. The finding that motivated the rule: teams were systematically not including minority candidates in consideration pools, not because of deliberate exclusion but because hiring decisions were made through informal networks where minority coaches were not present. The Rooney Rule forces the evaluation pool to include candidates outside the default relationship network. Since its introduction, the percentage of minority head coaches in the NFL increased significantly. Adopted in modified forms by Amazon, Cigna, Microsoft, and others as "diverse slate" requirements in hiring.
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.
- 5d ago First seen · 79 lines · 65 tokens per session scan A 28aad67b15c2
apply-merit-selection is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 20d ago), licensed MIT. It adds 65 tokens to every session and 2,553 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
inclusive-leadership
Provides daily practices for building genuinely inclusive teams through language audits, bias interruption, equitable hiring, cross-cultural sensitivity, and systemic fairness. Use when team composition lacks diversity, when DEI initiatives face backlash, when women or underrepresented groups stall in advancement…
org-report
Generate an executive organization brief (leadership chain, direct reports, extended teams, and vendor partners) for a target person. Produces a Word + PDF report from a directory MCP source (WorkIQ is the reference implementation) and displays it in a Copilot canvas. Triggers on "generate org report for X", "build…
meeting-efficiency
Agenda design, time boxing, decision capture, async alternatives, and productive facilitation.
coaching-techniques
GROW model, active listening, developmental feedback, and team growth approaches.
stakeholder-management
Influence mapping, communication strategies, and expectation management for complex organizations.
business-analysis
Patterns for requirements elicitation, BRDs, process analysis, and stakeholder alignment.