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 liqiongyu/lenny_skills_plus --skill having-difficult-conversationsgit clone --depth 1 https://github.com/liqiongyu/lenny_skills_plusWrote 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/liqiongyu/lenny_skills_plus/having-difficult-conversations)<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/having-difficult-conversations"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/having-difficult-conversations/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/liqiongyu/lenny_skills_plus/having-difficult-conversations"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/having-difficult-conversations.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 | $0.00022 | $0.02205 |
| Opus 5 | $0.00011 | $0.01103 |
| Sonnet 5 | $0.00004 | $0.00441 |
| Haiku 4.5 | $0.00002 | $0.00220 |
Grade A, and why
having-difficult-conversations 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 11d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Having Difficult Conversations
Scope
Covers
- Planning and delivering clear, respectful, direct conversations about performance, behavior, expectations, and decisions
- Turning “insight about feedback” into concrete artifacts: brief → talk track → reactions plan → follow-up
- Using Radical Candor as a default stance: care personally + challenge directly
- Preserving dignity in high-stakes moments (especially layoffs/terminations): private, human, and unambiguous
- Separating feelings from attributions so feedback stays specific and actionable
When to use
- “Help me prepare a difficult conversation with my direct report / peer.”
- “Write a talk track for performance feedback (with specific examples).”
- “I need to deny a promotion—help me be direct and still leave hope + a path.”
- “Prepare a layoff/termination conversation talk track (I have HR involved).”
- “Draft a follow-up message after a hard conversation that documents next steps.”
When NOT to use
- You need to decide whether to promote/terminate (use your company’s performance process; involve HR/leadership)
- You’re handling harassment, discrimination, threats, or an investigation (stop and follow HR/legal policy)
- You need legal advice, severance guidance, or policy interpretation (involve HR/legal)
- The situation is a mental health or safety crisis (seek professional help and follow company policy)
- You want an ongoing coaching and 1:1 system for your reports (use
running-effective-1-1s) - You want to develop PM skills through coaching, not deliver specific feedback (use
coaching-pms) - You need to set expectations or push back upward with your manager (use
managing-up) - You want to run a blameless retrospective after an incident or failure (use
post-mortems-retrospectives)
Inputs
Minimum required
- Conversation type (feedback, performance, promotion denial, layoff/termination) + relationship (manager/report/peer)
- Desired outcome (what should be true immediately after + in 2–4 weeks)
- 2–5 concrete examples/facts (what happened, when, impact) + expectations/standards
- Constraints: timeline/urgency, location (in-person/video), HR/legal involvement (if applicable)
- Any support you can offer (coaching, resources, training, timeline, check-ins)
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- eval/eval_config.json 1.7 KB
- eval/SHOWCASE.md 4.9 KB
- eval/with_skill.md 26 KB
- eval/without_skill.md 14 KB
- README.md 1.3 KB
- references/CHECKLISTS.md 2.3 KB
- references/EXAMPLES.md 866 B
- references/INTAKE.md 2.4 KB
- references/RUBRIC.md 3.0 KB
- references/SOURCE_SUMMARY.md 1013 B
- references/TEMPLATES.md 3.7 KB
- references/WORKFLOW.md 4.4 KB
- skillpack.json 406 B
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.
- 11d ago First seen · 136 lines · 22 tokens per session scan A 21fae2cc0e64
having-difficult-conversations is a skill published in the GitHub repository liqiongyu/lenny_skills_plus (52 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 2,205 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
hourly-rate-time
A time-management method based on assigning a high personal value to each hour. It treats time as a limited resource and uses that value to decide which tasks to do, outsource, or skip.
screen-detox
A habit-change framework for reducing non-work screen use such as social media, short videos, games, and endless scrolling.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
exec-weekly-agenda-generator
Synthesize the past week across meetings, chat, email, and calendar to generate a ranked list of 5-10 topics for the weekly leadership team meeting. Use when the user asks to prep for their leadership meeting, generate meeting topics, build the agenda, or says "prep me for Monday.".
meeting-follow-up-pipeline
Turn a completed meeting into a debrief, decisions, action items, ready-to-send follow-up drafts, and proposed writebacks. Use when the user asks to debrief a meeting, process their last meeting, review meeting follow-ups, or run the meeting follow-up pipeline.