Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/k1lgor/virtual-companynpx agentmods add commands/k1lgor/virtual-company/skillsWrote 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/commands/k1lgor/virtual-company/skills)<a href="https://agentmods.dev/commands/k1lgor/virtual-company/skills"><img src="https://agentmods.dev/badge/commands/k1lgor/virtual-company/skills.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 5.1 | $0.00014 | $0.02877 |
| Opus 5 | $0.00007 | $0.01438 |
| Sonnet 5 | $0.00003 | $0.00575 |
| Haiku 4.5 | $0.00001 | $0.00288 |
Grade A, and why
skills 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 8d 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 Skills Command
List all available agent skills with their descriptions, use cases, and routing guidance.
🛑 The Iron Law
NO SKILL LISTING WITHOUT FRONTMATTER VALIDATION
Every skill listed must have valid frontmatter with at minimum: name, description, and capabilities. Skills with missing or malformed frontmatter are flagged, not silently skipped.
No exceptions. No "probably fine" shortcuts. No listing without reading.
Violating this law means: you show skills that may not exist, may be broken, or may mislead the user. A wrong listing is worse than no listing. This is non-negotiable — every listing is a promise of quality. No exceptions. Ever.
📐 Decision Tree: Filter Modes
graph TD
A[User runs /skills] --> B{Filter provided?}
B -->|No| C[List all skills grouped by category]
B -->|Yes| D{Filter type?}
D -->|Keyword| E[Search name + description + capabilities]
D -->|Category| F[Show only that category]
D -->|Exact name| G{Skill exists?}
G -->|Yes| H[Show full skill detail]
G -->|No| I[Suggest closest matches]
E --> J{Results found?}
F --> J
J -->|Yes| K[Display results table]
J -->|No| L[Suggest alternatives or broader search]
H --> K
I --> K
📐 Decision Tree: Skill Validation Before Display
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.
- 8d ago First seen · 327 lines · 14 tokens per session scan A e160ce4314dc
skills is a command published in the GitHub repository k1lgor/virtual-company (4 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 2,877 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 2026-08-31.
Other commands, from other repositories
ship
Complete PR workflow from commit to production with validation.
audit-project
Multi-agent code review with iterative improvement.
onboard
Guided setup — discover knowledge files, create subscriptions, enable telemetry, and close the feedback loop. Safe to re-run (additive).
new-sdk-app
Create and setup a new Claude Agent SDK application.
ship-error-handling
This file contains error handling procedures for /ship.
remove-sub
Unsubscribe from a skill event. Removes or disables subscriptions with scope-aware options.