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 skills/drn/dots/cross-agentnpx skills add drn/dots --skill cross-agentgit clone --depth 1 https://github.com/drn/dotsWhat 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 | $0.00040 | $0.03919 |
| Opus 5 | $0.00020 | $0.01959 |
| Sonnet 5 | $0.00008 | $0.00784 |
| Haiku 4.5 | $0.00004 | $0.00392 |
Grade B, and why
cross-agent 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.
- Existing .claude/skills: !`find .claude/skills -maxdepth 2 -name SKILL.md 2>/dev/null | head -30` How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Agent Skill Setup
Migrate a repository's skills to the Agent Skills open standard so they work across Claude Code, Codex, and Copilot.
Arguments
$ARGUMENTS- Optional: path to target repo (defaults to current working directory)
Context
- Existing .agents/skills: !
find .agents/skills -maxdepth 2 -name SKILL.md 2>/dev/null | head -30 - Existing .claude/commands: !
find .claude/commands -maxdepth 1 -name "*.md" 2>/dev/null | head -30 - Existing .claude/skills: !
find .claude/skills -maxdepth 2 -name SKILL.md 2>/dev/null | head -30 - AGENTS.md exists: !
find . -maxdepth 1 -name AGENTS.md 2>/dev/null | head -1 - CLAUDE.md type: !
file CLAUDE.md 2>/dev/null | head -1 - claude.md (lowercase) exists: !
find . -maxdepth 1 -type f 2>/dev/null | grep '/claude\.md$' | head -1 - Copilot instructions: !
find .github -maxdepth 1 -name copilot-instructions.md 2>/dev/null | head -1 - Subtree CLAUDE.md files: !
find . -mindepth 2 -maxdepth 4 -name CLAUDE.md -not -path './.git/*' 2>/dev/null | head -20 - Subtree AGENTS.md files: !
find . -mindepth 2 -maxdepth 4 -name AGENTS.md -not -path './.git/*' 2>/dev/null | head -20 - Git root: !
git rev-parse --show-toplevel 2>/dev/null | head -1
Instructions
Step 0: Pre-flight
Verify this is a git repository. If not, stop and report.
If $ARGUMENTS contains a path, cd to it first.
Step 1: Discover Repo State
Scan for existing skills in all locations:
.agents/skills/*/SKILL.md(already canonical).claude/commands/*.md(Claude flat commands).claude/skills/*/SKILL.md(Claude directory skills) Also check for a lowercaseclaude.md— Claude Code requiresCLAUDE.md(uppercase) for discovery. Usels -1 | grep '^claude\.md$'to detect the wrong casing (a plaintest -fis unreliable on case-insensitive filesystems).
Classify the repo:
- GREENFIELD: No skills anywhere. Create infrastructure only.
- CLAUDE-ONLY: Skills in
.claude/but no.agents/skills/. Full migration needed. - PARTIAL:
.agents/skills/exists but missing infrastructure (no AGENTS.md, no Copilot instructions, no sync scripts). - COMPLETE:
.agents/skills/exists with all infrastructure. Run validation only.
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 · 305 lines · 40 tokens per session scan B a3702bcb0fed
cross-agent is a skill published in the GitHub repository drn/dots (23 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 3,919 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…