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 fatihguner/foreman --skill psychological-safetygit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/psychological-safety)<a href="https://agentmods.dev/skills/fatihguner/foreman/psychological-safety"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/psychological-safety/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/fatihguner/foreman/psychological-safety"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/psychological-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium YARA Match · line 40 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00088 | $0.03489 |
| Opus 5 | $0.00044 | $0.01744 |
| Sonnet 5 | $0.00018 | $0.00698 |
| Haiku 4.5 | $0.00009 | $0.00349 |
Grade A, and why
psychological-safety 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 5d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Psychological Safety
When Google set out to discover what made its best teams effective, the company expected to find that optimal team composition -- the right mix of skills, seniority, and personality types -- was the primary driver. Project Aristotle, as the two-year internal research initiative was named, analysed 180 Google teams and found something different. Who was on the team mattered far less than how the team worked together. The single most important factor distinguishing high-performing teams from the rest was psychological safety: the shared belief among team members that the team is safe for interpersonal risk-taking. Not trust in the abstract, but the specific, felt confidence that speaking up with a question, concern, mistake, or half-formed idea will not result in punishment or humiliation. Amy Edmondson, the Harvard Business School professor who originated the concept, had been studying it for over a decade before Google's data confirmed its primacy. The finding carries particular weight for startups, where the margin for error is thin, the information environment is ambiguous, and the consequences of silence -- unvoiced concerns, unraised objections, unreported failures -- can be existential.
The Framework
What Psychological Safety Is (and Is Not)
Edmondson is precise about the boundaries of the concept. Psychological safety is not:
- Niceness. Teams with high psychological safety can have fierce debates. The difference is that the fierceness targets ideas, not people.
- Lower standards. Psychological safety does not mean reducing accountability. It means creating conditions where people can be honest about problems, which is a prerequisite for genuine accountability.
- Unconditional agreement. The point is not that everyone feels comfortable all the time. The point is that discomfort comes from intellectual challenge, not from fear of retaliation.
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.
- 5d ago First seen · 208 lines · 88 tokens per session scan A 4854966431f8
psychological-safety is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 5d ago), licensed MIT. It adds 88 tokens to every session and 3,489 once invoked, about $0.0004 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 2026-09-06.
Other skills, from other repositories
design-team-culture
Use when a manager wants to intentionally shape the values, behaviors, and working patterns that define how their team operates — going beyond written norms to embed culture through rituals, stories, symbols, and leader modeling.
apply-five-commander-virtues
Use when assessing, developing, or hiring for leadership capability — to evaluate a leader against the five virtues that Sun Tzu identifies as determinants of strategic success and diagnose which virtue deficits are causing organisational or competitive failures.
dumbest-in-the-room
A leadership practice for building a team whose members have deeper expertise than the leader in their areas. The leader focuses more on asking questions, sharing information, and giving people authority to decide.
ai-adoption-change-management
Use this skill when planning or executing the human side of an Agentforce or Einstein AI feature rollout — user trust-building, AI-specific training, structured feedback collection via the Feedback API, and adoption measurement via Agentforce Analytics. NOT for turning the Einstein for Sales features on — use…
manage-taskboard
Manage Codex Taskboard / e-taskboard work with taskctl. Use for taskboard issue IDs, status sync, comments, or taskctl cloud setup—not for unrelated product docs.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…