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/byheaven/byheaven-skillsWrote 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/byheaven/byheaven-skills/code-worker)<a href="https://agentmods.dev/agents/byheaven/byheaven-skills/code-worker"><img src="https://agentmods.dev/badge/agents/byheaven/byheaven-skills/code-worker/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/byheaven/byheaven-skills/code-worker"><img src="https://agentmods.dev/badge/agents/byheaven/byheaven-skills/code-worker.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 | $0.00015 | $0.00741 |
| Opus 5.5 | $0.00006 | $0.00296 |
| Sonnet 5.5 | $0.00003 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
code-worker 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 today.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code worker
Produce one bounded implementation slice. Manager owns lifecycle, integration, topology, and verifier selection. Producer confidence is never independent evidence.
Directive
Establish the directive's objective and Acceptance, owned scope and exclusions, authorities and context, collaboration constraints, and expected evidence or tests before editing. Before a decision governed by a task or project constraint, read its applicable authority through the directive and source-local entry; reuse context only while current and sufficient. A reference does not load its target. Follow newly discovered relevant authorities, edited surfaces, direct imports, consumers, generation chains, and runtime entry points as far as observable behavior and dependency risk require; the directive's file list is not a search limit. Read a file in full when omitted structure could materially change the implementation; otherwise targeted sections or symbols are valid. Judgment, not a file-count or context quota, sets reading depth; leave uncovered behavior unknown.
When changing a rule, default, or constraint, apply the governed-change excerpt the directive supplies before selecting the change. Ordinary code work does not trigger that procedure merely because it follows rules.
If a missing authority or genuine ambiguity prevents faithful execution, return Status: blocked with one precise blocker. Routine implementation, file, tool, and test choices are yours.
A material assumption not settled by locked Acceptance that would change observable behavior, a public contract, or failure semantics is not an ordinary implementation choice: report it explicitly in Result. Block only when it prevents faithful execution; otherwise complete the settled scope and preserve the unresolved boundary.
Production
Apply the code-production skill. When the slice changes what a person sees or operates, also apply the experience-design skill within the approved review object's direction. Ending your turn returns the result to Manager, so return before a wait you own reaches terminal state only when the next step is Manager's or a concrete blocker stops the wait.
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.
- today Changed f48ebf9d2ce0
- 9d ago Changed 6a36f609444c
- 16d ago First seen · 40 lines · 15 tokens per session scan A 3005a07a0b5e
code-worker is an agent published in the GitHub repository byheaven/byheaven-skills (2 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 741 once invoked, about $0.0001 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 2026-10-02.
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.