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 ai-stakeholder-balancegit 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/ai-stakeholder-balance)<a href="https://agentmods.dev/skills/fatihguner/foreman/ai-stakeholder-balance"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-stakeholder-balance/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/ai-stakeholder-balance"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-stakeholder-balance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00104 | $0.03820 |
| Opus 5 | $0.00052 | $0.01910 |
| Sonnet 5 | $0.00021 | $0.00764 |
| Haiku 4.5 | $0.00010 | $0.00382 |
Grade A, and why
ai-stakeholder-balance 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 — 186 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.
AI Stakeholder Balance
A scale, by definition, must have two sides. Most leaders deploying AI place efficiency on one side and load the other with nothing at all -- then marvel at how quickly things tip over. The promise of artificial intelligence is real: faster decisions, lower costs, sharper predictions. But efficiency is not a value-neutral concept. Efficiency for whom is the question that separates organisations that extract lasting value from AI from those that generate headlines about algorithmic bias, workforce revolts, and regulatory backlash. When Boston deployed an AI-optimised school bus scheduling system designed by two MIT graduates to trim a $100 million transportation budget, the algorithm dutifully reshuffled start times across hundreds of schools. It did not, however, consider that shifting elementary school start times to 7:15 a.m. would create a childcare gap that forced parents to change jobs or scramble for emergency arrangements. The city dropped the plan. The algorithm had optimised for cost. It had forgotten the humans.
The Framework
The Stakeholder Triad in AI Adoption
AI adoption decisions radiate outward in concentric circles. At the centre sit the three stakeholder groups whose interests a leader must actively balance: employees, customers, and society. Most leaders acknowledge the first two and entirely forget the third.
Employees are the most immediately affected. Surveys indicate that organisations expect automation to increase workforce capacity by 30 to 40 percent -- a statistic that, from the employee's perspective, reads as a 30 to 40 percent reduction in their perceived indispensability. Employees fear job loss, but they also fear something subtler: the erosion of agency, the sense that they have become appendages to an algorithm rather than professionals exercising judgment.
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 Changed · +185 lines · +104 tokens per session 274e2aa5f274
- 11d ago First seen · 1 lines · 0 tokens per session scan A 3f6bc859f786
ai-stakeholder-balance is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 6d ago), licensed MIT. It adds 104 tokens to every session and 3,820 once invoked, about $0.0005 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
implementing-iso-27001-information-security-management
ISO/IEC 27001:2022 is the international standard for establishing, implementing, maintaining, and continually improving an Information Security Management System (ISMS). This skill covers the complete.
performing-nist-csf-maturity-assessment
The NIST Cybersecurity Framework (CSF) 2.0, released in February 2024, provides a comprehensive taxonomy for managing cybersecurity risk through six core Functions - Govern, Identify, Protect, Detect, Respond, and Recover. This skill covers conducting a maturity assessment against the CSF using Implementation Tiers to…
conducting-cyber-risk-assessment-with-nist-800-30
Conduct a defensible cybersecurity risk assessment using the NIST SP 800-30 Rev 1 methodology: prepare scope and a risk model, identify threat sources and threat events, identify vulnerabilities and predisposing conditions, determine likelihood and impact, compute risk, and communicate results as a prioritized risk…
newsroom-ai-policy
Generate a newsroom AI usage policy: where AI is allowed, where it is banned, disclosure rules, quality gates, and accountability structures — tailored to the publication's editorial values.
Compliance Checker
Check regulatory compliance across finance, tax, employment, data privacy, and industry-specific requirements.
AI Safety Auditor
Audit AI systems for safety, bias, and responsible deployment.