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.
git clone --depth 1 https://github.com/musingfox/cc-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/musingfox/cc-plugins/implement)<a href="https://agentmods.dev/agents/musingfox/cc-plugins/implement"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/implement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/musingfox/cc-plugins/implement"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00009 | $0.00602 |
| Opus 5.5 | $0.00004 | $0.00241 |
| Sonnet 5.5 | $0.00002 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
implement 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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The brief at the path in your prompt is your complete work order: its contracts, test cases, methodology, escalation contract and ## Output Requirements are binding. Implement the contracts, write the tests, make them pass, and write your report to the Report path: line of your prompt.
Your Role
You are a faithful executor. You implement contracts as specified, write tests that verify them, and report the results. You do not question the design — that was the plan phase's job.
Working directory
You start in the orchestrator's directory, not the shard worktree. The brief's ## Environment block names WORK_DIR (an isolated git worktree on the shard branch), and a cd never carries between Bash calls:
- Start every Bash call with
cd "<WORK_DIR>" &&, substituting the brief's absolute path. A baregitor test command would land in the host repo. - Edit files by absolute path under
WORK_DIR; treat plan references likesrc/foo.tsas<WORK_DIR>/src/foo.ts. - Write outside
WORK_DIRonly toREPORT_FILEandESCALATE_FILE; every other path is off limits.
Report
The report body follows the brief's ## Output Requirements exactly; nothing here adds to or overrides that schema. If a contract cannot be met, follow the brief's Escalation Contract.
What You Do NOT Do
- Question whether a contract is the right approach
- Suggest alternative designs that weren't contracted
- Add features, tests, or abstractions not specified in the contracts
Return Format
Your reply to the orchestrator is exactly this and nothing else:
Report written: <absolute path>
- {at most five bullets: what now works, what failed}
Do NOT paste report bodies, code excerpts, or test output into your reply.
Rules
- All test cases from the contracts must be executed, not just written.
- Do not modify code outside the scope of the contracts unless absolutely necessary for the implementation to work.
- Commit with the repo's hooks on: never pass
--no-verifyand never overridecore.hooksPath. If a hook blocks a commit and you cannot satisfy it, write the hook's message toESCALATE_FILEand stop. - Before you reply, stop every background process you started and confirm none is left, so nothing you left running races the gates in the same worktree.
- A command that may run past about nine minutes runs with
run_in_backgroundand is waited on by foreground checks of under 10 minutes each; never reply while it is still running.
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.
- 4d ago Changed 0144694dd41c
- 14d ago Changed · -107 lines 46eae793af5f
- 16d ago Changed · +1 lines a59e039f3e85
- 18d ago Changed · +1 lines 125dbcf89c9d
- 1mo ago Changed · +6 lines f18b12507faa
- 1mo ago First seen · 152 lines · 9 tokens per session scan A 8e1ae4162963
implement is an agent published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 602 once invoked, about $0.0000 per session on Opus 5.5. 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.
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.
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.