Softaworks Agent Toolkit is a collection of packaged instructions, scripts, agents, and commands that give AI coding assistants reusable procedures for development, documentation, planning, and professional work. Developers install its components individually in compatible coding-agent environments; catalogue entries represent parts of this toolkit.
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 softaworks/agent-toolkit --skill feedback-masterygit 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/feedback-mastery)<a href="https://agentmods.dev/skills/softaworks/agent-toolkit/feedback-mastery"><img src="https://agentmods.dev/badge/skills/softaworks/agent-toolkit/feedback-mastery/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/softaworks/agent-toolkit/feedback-mastery"><img src="https://agentmods.dev/badge/skills/softaworks/agent-toolkit/feedback-mastery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00051 | $0.02490 |
| Opus 5.5 | $0.00020 | $0.00996 |
| Sonnet 5.5 | $0.00010 | $0.00498 |
| Haiku 4.5 | $0.00005 | $0.00249 |
Grade A, and why
feedback-mastery 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 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.
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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Conversations
Overview
This skill provides frameworks for navigating difficult workplace conversations and delivering effective feedback. Whether you're addressing performance issues, resolving conflicts, or giving constructive feedback, these structured approaches lead to better outcomes.
Core insight: Research shows that employees who approach difficult conversations with preparation and a clear framework are 60% more likely to reach a positive resolution than those who engage without a plan.
When to Use This Skill
Use this skill when:
- Preparing to give feedback to a colleague or direct report
- Addressing performance issues or missed expectations
- Navigating conflict between team members
- Having 1:1 conversations about sensitive topics
- Receiving feedback and wanting to respond constructively
- Managing expectations with stakeholders
Keywords: feedback, difficult conversation, 1:1, one-on-one, performance, conflict, expectations, behavior, confrontation
Core Frameworks
The Preparation-Delivery-Follow-up Model
A three-part structure for difficult conversations:
| Phase | Focus | Key Questions |
|---|---|---|
| Preparation | Understand the issue, define goals, manage emotions | What's the problem? What outcome do I want? Am I calm? |
| Delivery | Open neutrally, use facts not blame, encourage dialogue | How do I start? What evidence do I have? How do I involve them? |
| Follow-up | Document actions, set check-ins, provide support | What did we agree to? When will we check in? How do I support? |
The SBI Feedback Model
Situation-Behavior-Impact (SBI) structures feedback to be specific, objective, and actionable:
| Component | Description | Example |
|---|---|---|
| Situation | Describe the specific context | "During yesterday's code review..." |
| Behavior | State the observable action (not interpretation) | "...you interrupted Sarah three times while she was explaining her approach..." |
| Impact | Explain the effect on team/project/person | "...which made her hesitate to share ideas and slowed down our discussion." |
What ships with it
4 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.
- 1mo ago First seen · 293 lines · 51 tokens per session scan A d0ee923acf5e
feedback-mastery is a skill published in the GitHub repository softaworks/agent-toolkit (2,558 stars, last pushed 7mo ago), licensed MIT. It adds 51 tokens to every session and 2,490 once invoked, about $0.0002 per session on Opus 5.5. 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
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.