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 design-speak-up-frameworkgit 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/design-speak-up-framework)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-speak-up-framework"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-speak-up-framework/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/design-speak-up-framework"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-speak-up-framework.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 | $0.00064 | $0.03125 |
| Opus 5 | $0.00032 | $0.01563 |
| Sonnet 5 | $0.00013 | $0.00625 |
| Haiku 4.5 | $0.00006 | $0.00313 |
Grade A, and why
design-speak-up-framework 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 6d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Speak-Up Framework
Design the channels, protections, and cultural norms that make it possible and expected for people to report wrongdoing — because without explicit design, fear of retaliation systematically suppresses the information that would have prevented the most serious organizational failures.
Why This Is Best Practice
谷梁传 (Guliang Chi, ~5th–4th century BC):
讨贼之义 — The obligation to oppose wrongdoing.
Why best: The 谷梁传 contains repeated moral commentary on historical cases where those with standing remained neutral in the face of wrongdoing — and treats that neutrality as moral failure equivalent to complicity. The principle: having the knowledge and standing to report wrongdoing, and choosing silence to protect oneself, is not an ethically neutral position. This is not merely a moral claim; it is an institutional design insight — institutions in which witnessing wrongdoing creates a duty to report, rather than a risk to manage, have better integrity and fewer catastrophic failures than institutions where silence is the rational choice.
Sarbanes-Oxley Act §301 (2002): Enacted after the Enron, WorldCom, and Tyco accounting scandals — all of which involved employees who knew of the fraud but feared reporting it. SOX §301 requires all public companies to establish procedures for receiving and addressing complaints about accounting controls and auditing matters, including anonymous submission mechanisms. The explicit legislative finding: absent a structured speak-up mechanism, employees with knowledge of financial wrongdoing face career-ending consequences for disclosure, so they stay silent. SOX made the infrastructure for speak-up a legal requirement for all ~6,000 US public companies.
Dodd-Frank Act §§922–924 (2010): Established the SEC whistleblower program in response to the 2008 financial crisis, during which multiple employees at major financial institutions had knowledge of misconduct but stayed silent. Dodd-Frank provides financial rewards (10–30% of sanctions above $1M) and explicit anti-retaliation protections to whistleblowers. Since 2011: 50,000+ tips received; $1.3B+ in awards; multiple major enforcement actions triggered by employee disclosures. The explicit design rationale: financial incentive for disclosure and legal protection from retaliation must both exist simultaneously for reporting to occur at scale.
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.
- 6d ago First seen · 108 lines · 64 tokens per session scan A dc72e9adf28b
design-speak-up-framework is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 21d ago), licensed MIT. It adds 64 tokens to every session and 3,125 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
hr-time-attendance
Help HR and payroll teams design, audit, and communicate time and attendance policies, including clock-in rules, overtime, leave tracking, and time-tracking system configuration. Use when asked to set up a time tracking policy, calculate overtime, design a shift attendance policy, write a lateness policy, or similar…
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…
coaching-techniques
GROW model, active listening, developmental feedback, and team growth approaches.
counseling-psychology
Therapeutic frameworks, assessment, ethical practice, and client documentation for counselors and psychologists.
meeting-efficiency
Agenda design, time boxing, decision capture, async alternatives, and productive facilitation.
scaffolding-generator
Pattern-aware code scaffolding that detects existing conventions and generates new components matching the codebase style. Use when asked to "scaffold a component", "generate boilerplate", "create a new module", "bootstrap a service", "add a new endpoint", "create a new controller", or "add a new feature module".…