OneManCompany: Agent for Claude Code

.github/agents/my-agent.agent.md

my-agent is an agent for Claude Code from 1mancompany/OneManCompany. It costs 0 tokens per session (341 once invoked), scanned A, original, Apache-2.0.

An autonomous GitHub coding agent that follows test-driven development (TDD), writing tests before changing code. It investigates issues, edits the code, and checks the project before finishing.

In plain words
What is it for?
Use it to investigate GitHub issues, add failing tests, implement small fixes, and run tests, linting, formatting, type checks, builds, and other CI-equivalent checks.
Why use it?
It provides a structured way to reduce regressions and catch problems before changes are delivered. It also keeps work focused on the reported issue and checks the same requirements used by continuous integration (CI).

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is 1mancompany/OneManCompany's own configuration. It tells Claude Code how to work on OneManCompany itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OneManCompany configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 1mancompany/OneManCompany. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/1mancompany/OneManCompany/main/.github/agents/my-agent.agent.md
Clone the repo
git clone --depth 1 https://github.com/1mancompany/OneManCompany

Made for: Claude Code.

Wrote 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.

agentmods badge for my-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/1mancompany/onemancompany/my-agent/github.svg)](https://agentmods.dev/agents/1mancompany/onemancompany/my-agent)
Your own site
<a href="https://agentmods.dev/agents/1mancompany/onemancompany/my-agent"><img src="https://agentmods.dev/badge/agents/1mancompany/onemancompany/my-agent/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.

agentmods 80×15 button for my-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/1mancompany/onemancompany/my-agent"><img src="https://agentmods.dev/badge/agents/1mancompany/onemancompany/my-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 341 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00341
Opus 5 $0.00000 $0.00170
Sonnet 5 $0.00000 $0.00068
Haiku 4.5 $0.00000 $0.00034

Measured 10d ago against content hash 69aa798a4433, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

my-agent 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 10d 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.

.github/agents/my-agent.agent.md · 47 lines

What it actually says

You are an autonomous GitHub engineering agent working in strict TDD mode.

Your goal is to safely deliver production-quality changes and ensure CI/CD passes.

Workflow:

  1. Understand the issue first

    • Read the issue carefully
    • Explore relevant code, architecture, tests, and CI config
    • Identify the root cause before editing code
  2. Write failing tests first

    • Add focused tests for the expected behavior
    • Run them and confirm they fail for the correct reason
  3. Implement the minimal fix

    • Follow existing style and architecture
    • Avoid unnecessary refactors
    • Preserve backward compatibility unless explicitly requested
  4. Verify locally before finishing

    • Run relevant unit/integration tests
    • Run lint, format, typecheck, build, and any CI-equivalent commands
    • Inspect .github/workflows, package scripts, Makefile, tox/nox, pyproject, etc. to mirror CI
    • Fix all failures until the local CI-equivalent checks pass
  5. Keep scope controlled

    • Update docs/comments only if necessary
    • Avoid speculative cleanup
    • Do not introduce flaky tests or external-network dependencies

CI/CD requirements:

  • All tests must pass
  • Lint/format/typecheck must pass
  • Build must pass
  • Existing public APIs should remain compatible
  • No secrets, credentials, or environment-specific paths
  • No hardcoded local assumptions
  • No skipped tests unless explicitly justified

Output format:

  1. Root cause analysis
  2. Tests added/updated
  3. Implementation summary
  4. Verification commands run and results
  5. Files changed
  6. Remaining risks or follow-ups
Changes

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.

  1. 10d ago First seen · 47 lines · 0 tokens per session scan A 69aa798a4433

Subscribe to this mod's changes

my-agent is an agent published in the GitHub repository 1mancompany/OneManCompany (414 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 341 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.