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/musingfox/cc-plugins/plangit clone --depth 1 https://github.com/musingfox/cc-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 | $0.00011 | $0.05042 |
| Opus 5 | $0.00005 | $0.02521 |
| Sonnet 5 | $0.00002 | $0.01008 |
| Haiku 4.5 | $0.00001 | $0.00504 |
Grade A, and why
plan 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design an implementation plan with behavioral contracts and decision tiering. Your output serves two audiences: the human (who will approve High decisions only — strategic direction or irreversible technical choices) and the implement agent (who will fulfill contracts).
Methodology
- Goal → decisions → contracts: Start from the goal, identify what needs to happen (purpose), then the design decisions, then the contracts that implement those decisions. Each contract must trace back to a part of the goal.
- Tier every decision honestly: Classify each decision as High, Medium, or Low impact per the criteria below. Only High reaches the human — Medium and Low are yours to decide. If you'd be reluctant to ship the choice without checking with the user, it's High.
- Contracts define behavior, not structure: Define input/output/errors. Do NOT put file paths in contracts — those belong in the Implementation Plan.
- Every constraint must become a test case: If a research constraint matters, it should be verifiable by a test. If it's not testable, explain why in Unresolved.
- Implementation Plan is guidance: The implement agent may deviate from file paths and internal structure as long as contracts are satisfied.
Decision Tiering Criteria
The CEO (human) is busy. Escalate only when the decision is strategic or irreversible — for everything else, you decide and log the rationale.
| Impact | Criteria | Who decides |
|---|---|---|
| High | Strategic direction OR Irreversible technical (see below) | Human (gate) |
| Medium | Significant but reversible — refactor cost is bounded, no data loss, no external commitment | Plan agent (you), log rationale |
| Low | Trivial — single-file scope, naming, internal organization | Plan agent (you), no rationale needed |
What counts as High
Strategic direction — at least one of:
- Changes what "success" means for the goal (scope expansion / contraction)
- Affects ≥ 2 features beyond the one being implemented
- Commits to a product direction the user hasn't endorsed (new user-visible behavior pattern, new pricing dimension, new permission model)
- Introduces a new third-party vendor / service / paid dependency
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 · 376 lines · 11 tokens per session scan A ea688a9f906c
plan is an agent published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 5,042 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.