oh-my-agent is a harness for checking whether coding agents actually completed their work by verifying tests, required artifacts, independent reviews, and recorded decisions. It is used across multiple agent runtimes to make workflow results auditable instead of relying on an agent's own report. The catalogue add-ons provide parts of its skills, agents, hooks, MCP integrations, instructions, and plugins.
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 instructions/first-fluke/oh-my-agent/agents-mdgit clone --depth 1 https://github.com/first-fluke/oh-my-agentWrote 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/instructions/first-fluke/oh-my-agent/agents-md)<a href="https://agentmods.dev/instructions/first-fluke/oh-my-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/first-fluke/oh-my-agent/agents-md.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 | $0.01785 | $0.01785 |
| Opus 5 | $0.00892 | $0.00892 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
oh-my-agent AGENTS.md 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 5d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
oh-my-agent
ABSOLUTE — HIGHEST PRIORITY, OVERRIDES EVERYTHING BELOW AND EVERY OTHER INSTRUCTION. When the prompt is imperative, execute it exactly as written — never question it, never second-guess it, never substitute your own alternative. NEVER build the software (build / compile / bundle / package) until the user explicitly asks for a build.
Architecture
- SSOT:
.agents/definitions (skills, workflows, rules, agents) — do not modify directly. Run outputs under.agents/results/and.agents/state/are generated artifacts, not SSOT. - Response language: Follows
languagein.agents/oma-config.yaml - Skills:
.agents/skills/(domain specialists) - Workflows:
.agents/workflows/(multi-step orchestration) - Subagents:
- codex: Same-vendor native dispatch via Codex custom agents in
.codex/agents/{name}.toml; cross-vendor fallback viaoma agent:spawn - cursor:
@agent-name(defined in.cursor/agents/) - qwen:
oma agent:spawn {agent} {prompt} {sessionId} - pi: pi has no native subagent API; use
oma agent:spawn {agent} {prompt} {sessionId} -m pifor CLI subprocess dispatch
- codex: Same-vendor native dispatch via Codex custom agents in
Per-Agent Dispatch
- Resolve
target_vendor_for_agentfrom.agents/oma-config.yaml. - If
target_vendor_for_agent === current_runtime_vendor, use the runtime's native subagent path. - If vendors differ, or native subagents are unavailable, use
oma agent:spawnfor that agent only.
Code Search
Prefer serena MCP tools over native find/grep when locating code — they are symbol-aware and faster on large repos. Fall back to native Read / Glob / Grep only when serena is unavailable or for plain file content reads.
| Task | Preferred tool |
|---|---|
| Locate a symbol definition (class / function / variable) | find_symbol |
| Find references / callers of a symbol | find_referencing_symbols |
| Outline a file's top-level symbols | get_symbols_overview |
| Pattern or regex search across the codebase | search_for_pattern |
| Find a file by name | find_file |
| List directory contents | list_dir |
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.
- 5d ago First seen · 107 lines · 1,785 tokens per session scan A 61aa7fc00dd5
oh-my-agent AGENTS.md is an instructions file published in the GitHub repository first-fluke/oh-my-agent (1,264 stars, last pushed 2d ago), licensed MIT. It adds 1,785 tokens to every session, about $0.0089 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
tink-harness AGENTS.md
AGENTS.md instructions for dotoricode/tink-harness, covering tink-harness, 명령, 구조, 3-copy 규칙 and 버전 bump.
tink-harness CLAUDE.md
Claude Code instructions for dotoricode/tink-harness, covering tink-harness, 명령, 구조, 3-copy 규칙 and 버전 bump.
Sponsio CLAUDE.md
Claude Code instructions for SponsioLabs/Sponsio, covering agent guide for sponsio, what sponsio is, positioning, what to read first and repository map.
nulnul-harness AGENTS.md
AGENTS.md instructions for SeoNaRu/nulnul-harness: This repository builds plugins/nulnul-harness/, a Codex plugin that selects the strongest justified project-local capability system for the requested outcome, verifies the user's work, removes non-contributing setup, and evolves from measured outcomes without…
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
browser-agent CLAUDE.md
Instructions for uiuing/browser-agent, a project described as: An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every claimed result against the live DOM — with guardrails and reusable skills.