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 rules/runwhen-contrib/runwhen-platform-mcp/skill-managementgit clone --depth 1 https://github.com/runwhen-contrib/runwhen-platform-mcpWhat 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 | $0.00000 | $0.00400 |
| Opus 5 | $0.00000 | $0.00200 |
| Sonnet 5 | $0.00000 | $0.00080 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade B, and why
skill-management scanned grade B with 1 finding 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 2d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- [ ] Symlinks resolve: `ls .github/skills/<name>` and `ls .claude/skills/<name>` What it actually says
Skill Management
Skills are reusable AI workflow definitions stored as SKILL.md files. They are
a core capability of the RunWhen MCP server — not just documentation.
Canonical location
All skills live in skills/ at the repo root. Each skill is a directory
containing a SKILL.md and optional reference files (templates, examples).
Multi-client discovery
Three symlinks/references ensure every supported client finds the skills:
| Client | Discovery path | Mechanism |
|---|---|---|
| Cursor | skills/ |
.cursor-plugin/plugin.json → "skills": "../skills/" |
| Copilot | .github/skills/ |
Symlink → ../skills |
| Claude | .claude/skills/ |
Symlink → ../skills |
When adding a new skill, place it in skills/<skill-name>/SKILL.md. The
symlinks handle the rest — never duplicate skill files into .github/ or
.claude/ directly.
SKILL.md structure
Every SKILL.md must have YAML frontmatter with name and description:
---
name: my-skill-name
description: >-
One-sentence description of when this skill should be used.
---
# Skill Title
Step-by-step instructions...
Checklist for new skills
- Created
skills/<name>/SKILL.mdwith valid frontmatter - Symlinks resolve:
ls .github/skills/<name>andls .claude/skills/<name> - Listed in
.github/copilot-instructions.mdskills table - Tested: skill triggers correctly when relevant prompt is given
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.
- 2d ago First seen · 53 lines · 0 tokens per session scan B 94952345fa60
skill-management is a cursor rule published in the GitHub repository runwhen-contrib/runwhen-platform-mcp (1 stars, last pushed 18d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 400 tokens. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
faq_usage
Quick reference for when to use DESIGNFAQ.md vs DXFAQ.md.
typescript-coding-rule
It allows a subset of JSDoc tags. Most tags must occupy their own line, with the tag at the beginning of the line.
about-codebase
General information about the Lineai MCP Server codebase and its purpose.
qa-agent
QA workflow for reviewing stories, designing tests, and reporting verified defects.
php-client-implementation
Guidelines for implementing MCP clients in PHP.
cursorrules
When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.