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 agentmods add skills/softaworks/agent-toolkit/difficult-workplace-conversationsnpx skills add softaworks/agent-toolkit --skill difficult-workplace-conversationsgit clone --depth 1 https://github.com/softaworks/agent-toolkitWrote 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/softaworks/agent-toolkit/difficult-workplace-conversations)<a href="https://agentmods.dev/skills/softaworks/agent-toolkit/difficult-workplace-conversations"><img src="https://agentmods.dev/badge/skills/softaworks/agent-toolkit/difficult-workplace-conversations.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01539 |
| Opus 5 | $0.00023 | $0.00770 |
| Sonnet 5 | $0.00009 | $0.00308 |
| Haiku 4.5 | $0.00005 | $0.00154 |
Grade A, and why
difficult-workplace-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 4d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Difficult Conversations Skill
A structured framework for approaching challenging workplace conversations including conflicts, performance issues, sensitive feedback, and emotionally charged discussions.
When to Use This Skill
- Preparing for a challenging conversation with a colleague
- Addressing performance issues with a team member
- Delivering difficult feedback to a peer or manager
- Navigating conflict between team members
- Discussing sensitive topics (salary, promotion, termination)
- Handling emotional or defensive reactions
- Following up after difficult discussions
Core Framework: Preparation-Delivery-Followup
Difficult conversations succeed or fail based on three phases:
Phase 1: Preparation (Before)
Purpose: Set yourself up for a productive conversation
-
Clarify the Issue
- What specifically happened? (Observable facts only)
- What is the impact? (On you, team, work)
- What do you need to change?
-
Check Your Emotions
- What am I feeling? Why?
- Am I calm enough to have this conversation?
- What might trigger me during this conversation?
-
Consider Their Perspective
- How might they see this situation?
- What constraints or pressures might they have?
- What do they care about that I can acknowledge?
-
Define Your Goal
- What outcome do I want?
- What is the minimum acceptable result?
- What am I willing to compromise on?
Phase 2: Delivery (During)
Purpose: Have the conversation effectively
-
Open Neutrally
- Start with facts, not judgments
- Express intent to understand, not accuse
- Create psychological safety
-
Share Your Perspective
- Describe behavior, not character
- Focus on impact, not intention
- Use "I" statements, not "you always"
-
Listen Actively
- Ask clarifying questions
- Acknowledge their viewpoint
- Look for shared interests
-
Seek Resolution
- Propose specific actions
- Agree on next steps
- Set check-in timeline
What ships with it
5 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.
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.
- 4d ago First seen · 239 lines · 47 tokens per session scan A 99dd7bca21e4
difficult-workplace-conversations is a skill published in the GitHub repository softaworks/agent-toolkit (2,422 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 1,539 once invoked, about $0.0002 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
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…