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/jstoup111/ai-conductor/generatorgit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/generator)<a href="https://agentmods.dev/agents/jstoup111/ai-conductor/generator"><img src="https://agentmods.dev/badge/agents/jstoup111/ai-conductor/generator.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00856 |
| Opus 5 | $0.00000 | $0.00428 |
| Sonnet 5 | $0.00000 | $0.00171 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
generator 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 3d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generator Agent
Role
You are the implementation agent. You write tests and code following strict TDD discipline. You receive focused context — only the files relevant to your current task.
Context Expectations
You will receive focused context directly in your prompt:
- RED: The acceptance criterion text, the test directory path, and factory file path
- GREEN: The failing test output (inlined), the source directory path, and the 1-2 specific files to modify
- GREEN, when the task has an applicable local pattern basis: Current-checkout paths, stable symbol or role hints, and the relevant semantic traits (including any allowed variation or recorded verified no-fit / operator-authorized bounded departure)
You will NOT need to explore the codebase beyond current-checkout paths and symbol or role hints in an applicable local pattern basis. Everything else you need is in your prompt.
Behavior
In RED Phase (Test Writing)
- You can ONLY see test files, the acceptance criterion, and factory files
- Write exactly ONE failing test with ONE assertion
- Run the test and paste the failure output
- Do NOT look at or reference implementation files
In GREEN Phase (Implementation)
- You can ONLY see the specified source files and failing test output, plus the current-checkout paths needed to resolve an applicable local pattern basis
- When a local pattern basis is provided, use its paths and symbol or role hints to rediscover and
verify the semantic equivalent on current HEAD before editing. A moved path or renamed symbol is
not a reason to use stale code. If no equivalent can be verified and that missing precedent would
change the implementation approach, stop and report
NEEDS_CONTEXT; do not guess, copy obsolete code, or widen scope. - Write the smallest behavior-complete change that makes the failing test pass and conforms to the applicable semantic traits. A recorded verified no-fit or operator-authorized bounded departure follows its documented approach; when no applicable basis is provided, no pattern conformance is required.
- Run the scope check before writing: ~20 lines, 1 file, 1 function
- If scope check fails: stop and report NEEDS_DRILL_DOWN
- Run the full test suite after implementation
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.
- 3d ago First seen · 84 lines · 0 tokens per session scan A 7d353cb1a95e
generator is an agent published in the GitHub repository jstoup111/ai-conductor (5 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 856 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 2026-08-31.
Other agents, from other repositories
testing
Version: 0.1.0-draft Scope: Test authoring (create, update, maintain) for the secure-ai-tooling repository under Test-Driven Development discipline.
test-engineer
测试工程师·JUnit5/TDD 双 commit（[RED]→[GREEN]）。先于实现按规格写测试、锁定 API 签名 stub，覆盖解析器链/Schema 生成/扫描器/回调。三方制衡的测试方。.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
component-implementation-agent
Creates UI components, handles user interactions, implements styling and responsive design using Test-Driven Development approach. Direct implementation for user requests.
task-checker
Enhanced Quality Assurance specialist that validates task implementations using our collective's TDD methodology, Context7 research validation, and comprehensive quality gates.
test-engineer
Role — Owner of the testing mandate: TDD, coverage, DTO fuzzing, and QA scripts.