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/edgedelta/claude-code-plugins/edgedelta-teammatesnpx skills add edgedelta/claude-code-plugins --skill edgedelta-teammatesgit clone --depth 1 https://github.com/edgedelta/claude-code-pluginsWhat 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 | $0.00037 | $0.03319 |
| Opus 5 | $0.00018 | $0.01659 |
| Sonnet 5 | $0.00007 | $0.00664 |
| Haiku 4.5 | $0.00004 | $0.00332 |
Grade A, and why
edgedelta-teammates 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 3d 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EdgeDelta Teammates Skill
Creates, configures, and manages EdgeDelta AI teammates. Provides guidance on system prompt engineering, connector permissions, channel scoping, and teammate lifecycle management.
When to Use This Skill
Activate this skill when the user:
- Wants to create a new EdgeDelta teammate
- Asks about teammate configuration or system prompts
- Needs to scope a teammate to specific responsibilities
- Wants to understand teammate permissions or connector access
- Asks about specialized vs custom teammates
- Mentions "teammate", "AI agent", "system prompt", "OnCall AI" in EdgeDelta context
- Wants to troubleshoot teammate behavior or refine prompts
Core Capabilities
- Teammate Design: Guide persona design with audience, scope, and decision boundaries
- System Prompt Engineering: Build effective masterPrompt, userPrompt, and toolingPrompt templates
- Permission Scoping: Configure connector-level permissions (Allow vs Ask Permission)
- Channel Assignment: Scope teammates to relevant channels and workflows
- Lifecycle Management: Create, update, clone, deactivate, and delete teammates
Quick Reference Searches
For fast lookups without loading full skill context:
# Teammate configuration fields
grep -n "Configuration Fields" SKILL.md
# System prompt patterns
grep -n "Prompt Structure" SKILL.md
# Permission model
grep -n "Permission" SKILL.md
# Specialized teammates
grep -n "Specialized" SKILL.md
# Detailed prompt engineering guide
cat assets/references/prompt-engineering.md
# Teammate data model reference
cat assets/references/teammate-model.md
Workflows
Workflow 1: Create a Custom Teammate
When: User wants to build a new teammate from scratch
Steps:
- Design the persona - Ask three questions before building:
- Audience and scope: Who will interact with this teammate? What questions should it refuse?
- Data sources and tools: Which connectors expose the telemetry or systems it needs?
- Decision boundaries: Can it execute changes, execute with approval, or only analyze and advise?
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 342 lines · 37 tokens per session scan A 260c2f723bbb
edgedelta-teammates is a skill published in the GitHub repository edgedelta/claude-code-plugins (2 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 3,319 once invoked, about $0.0002 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 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…