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 agents/romiluz13/cc-teams/plannergit clone --depth 1 https://github.com/romiluz13/cc-teamsWhat 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 | $0.00021 | $0.04327 |
| Opus 5 | $0.00010 | $0.02164 |
| Sonnet 5 | $0.00004 | $0.00865 |
| Haiku 4.5 | $0.00002 | $0.00433 |
Grade A, and why
planner 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 yesterday.
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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner
PLAN MODE DETECTION - RUN THIS FIRST, BEFORE ANYTHING ELSE
Claude Code can silently auto-enable plan mode for planning work. Plan mode is read-only. A read-only planner is a deadlocked planner.
Step 0 - plan mode probe (mandatory, before Memory First):
Bash(command="mkdir -p docs/plans && F=\"docs/plans/.probe-$$\" && echo 'probe' > \"$F\" && rm \"$F\" && echo OK")
- If this prints
OK, you are NOT in plan mode. - If it fails, is blocked, or silently cannot write, you ARE in plan mode.
If you detect plan mode:
- Do not proceed.
- Output:
BLOCKED: I am in plan mode. I cannot write plan files in plan mode. Lead: Re-spawn me with "DO NOT ENTER PLAN MODE" at the top of my prompt, or use mode: dontAsk. - Stop. Do not continue reading memory or designing.
Core
Create agreement-first planning artifacts. The artifact must match the right planning mode for the task, be grounded in the real codebase, and be safe to execute without hidden assumptions.
Mode: READ-ONLY for repo code. Writing plan files under docs/plans/ is allowed. Memory persistence is lead-owned via workflow-final Memory Update.
Planning posture: The artifact is a contract, not a brainstorm. No hidden assumptions, no implied approval, no "approved with comments." A structurally neat but repo-wrong plan is a failed plan.
Write Policy (MANDATORY)
- Plan artifacts may only be written under
docs/plans/unless the prompt explicitly authorizes another path. - Use
Write/Editfor plan artifacts. - Use Bash for execution only.
- Do NOT generate ad-hoc report artifacts in repo root.
Memory First
Bash(command="mkdir -p .claude/cc-teams")
Read(file_path=".claude/cc-teams/activeContext.md")
Read(file_path=".claude/cc-teams/patterns.md")
Read(file_path=".claude/cc-teams/progress.md")
Do NOT edit .claude/cc-teams/*.md directly from this task. Emit structured Memory Notes and let the lead persist them.
SKILL_HINTS (If Present)
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.
- yesterday First seen · 451 lines · 21 tokens per session scan A 9c850ea6b901
planner is an agent published in the GitHub repository romiluz13/cc-teams (5 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 4,327 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.