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/chrstian6/contractorWrote 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/chrstian6/contractor/readme)<a href="https://agentmods.dev/agents/chrstian6/contractor/readme"><img src="https://agentmods.dev/badge/agents/chrstian6/contractor/readme/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/chrstian6/contractor/readme"><img src="https://agentmods.dev/badge/agents/chrstian6/contractor/readme.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 | $0.00000 | $0.01405 |
| Opus 5.5 | $0.00000 | $0.00562 |
| Sonnet 5.5 | $0.00000 | $0.00281 |
| Haiku 4.5 | $0.00000 | $0.00140 |
Grade A, and why
README 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 1mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The agent org — layout and conventions
One folder per agent. Claude Code loads .claude/agents/**/*.md recursively,
so the nesting is free; a file is only treated as an agent definition if its
frontmatter carries a name:. Everything else in the folder is a co-located doc.
.claude/agents/
_lib/learn.sh # the self-improvement loop, executable
<agent>/
AGENT.md # the definition — has `name:` frontmatter, IS the agent
LEARNINGS.md # no frontmatter → a doc, not an agent. Append-only.
Why AGENT.md and not <agent>.md
Two files in the same directory whose frontmatter name matches collide —
the loser is discarded silently and the winner follows unsorted readdir order,
so which definition is live can differ between machines. One agent per folder
makes that collision structurally impossible.
It also means a single glob — **/.claude/agents/**/AGENT.md — names every
mandate in the org, which is what a deny rule needs to protect them all at once.
The definitions are RUN PROCEDURES, not prompts
Each AGENT.md is a numbered sequence of steps, each with a DONE WHEN line,
bookended by a RECALL step and a LEARN step, and closed by a HARD STOPS
block. This is deliberate:
- A prose prompt is obeyed when remembered. A numbered step with a completion condition is checkable — by the agent, and by whoever reads the hand-back.
- It matches the doctrine the rest of this repo already runs on: prefer a guard that executes over a guard that is written down . Where a step can be a command, it is written as a command.
When you edit a definition, keep the shape: steps in execution order, one DONE WHEN each, commands as commands.
Load in proportion to the task
An agent that loads everything it might need, every time, is not being thorough — it is being expensive, and whoever is waiting pays for it. Measured in a live run of one org's designer: ~121k tokens consumed before it had looked at a single screen, against a ~13k floor. The cause was two steps marked MANDATORY that never said how much.
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.
- 1mo ago First seen · 119 lines · 0 tokens per session scan A 2fe3ceb95cde
README is an agent published in the GitHub repository chrstian6/contractor (40 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,405 tokens. 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 2026-08-30.
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.