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 run-skip-level-interviewgit 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/run-skip-level-interview)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/run-skip-level-interview"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-skip-level-interview/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/run-skip-level-interview"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-skip-level-interview.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 | $0.00047 | $0.01970 |
| Opus 5.5 | $0.00019 | $0.00788 |
| Sonnet 5.5 | $0.00009 | $0.00394 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade C, and why
run-skip-level-interview scanned grade C with 1 finding 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.
Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
This is the most important question. It explicitly invites information to bypass the filter. How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Skip-Level Interview
Conduct structured one-on-one conversations with employees who report to your direct reports — to hear candid assessments of team health and manager effectiveness that would not surface through normal reporting channels.
Why This Is Best Practice
Adopted by: Skip-level interviews are standard practice at Google, Amazon, Microsoft, and Netflix; Kim Scott's "Radical Candor" framework requires skip-level listening as a check on whether direct reports are being candid with their own managers; Frank Slootman documents using skip-levels as a standard CEO and division president practice at ServiceNow and Snowflake to maintain organizational health signals; the US Army uses skip-level sensing through informal "command climate surveys" as a leadership tool at every echelon Impact: Google's research on manager effectiveness (Project Oxygen) relied partly on upward feedback channels to identify what behaviors distinguished the highest-rated managers; McKinsey's 2021 organizational health research found that leaders who actively sought multi-level input were 2× more likely to identify performance-degrading cultural issues before they became structural; the primary organizational health risk identified in skip-levels is information that has already reached the senior manager's direct reports but has not been escalated — surfacing it creates an early-intervention window that does not exist without skip-level access Why best: Information filters as it travels up reporting chains — direct reports tell managers what they think the manager wants to hear, or what they judge safe to share; this filtering is systematic, not random, and removes precisely the signals that would be most useful to senior leaders; the manager's skip-level reports are two information-filter layers away from the senior manager and have the most to gain from candid assessment of whether their direct manager is effective
Sources: Scott "Radical Candor" (St. Martin's Press, 2017); Slootman "Amp It Up" (Wiley, 2022); Google re:Work "Guide: Identify What Makes a Great Manager"; SHRM "Upward Feedback" best practice guide
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 · 137 lines · 47 tokens per session scan C b70a231870dc
run-skip-level-interview is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 1,970 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
saga-orchestration
Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…
deep-work-optimization
Focus blocks, distraction management, and flow state triggers for cognitively demanding work.
make-skill-template
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional…
meeting-efficiency
Agenda design, time boxing, decision capture, async alternatives, and productive facilitation.
disagreement-protocol
Canonical phrasing for respectful disagreement without capitulation — structural resistance to sycophancy.
fix-once-auto-inject
One-time fixes get repeated manually.