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 skills add first-fluke/oh-my-agent --skill oma-orchestrationgit 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/skills/first-fluke/oh-my-agent/oma-orchestration)<a href="https://agentmods.dev/skills/first-fluke/oh-my-agent/oma-orchestration"><img src="https://agentmods.dev/badge/skills/first-fluke/oh-my-agent/oma-orchestration/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/skills/first-fluke/oh-my-agent/oma-orchestration"><img src="https://agentmods.dev/badge/skills/first-fluke/oh-my-agent/oma-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 238 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 240 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Rogue Agent · line 293 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00044 | $0.03539 |
| Opus 5 | $0.00022 | $0.01769 |
| Sonnet 5 | $0.00009 | $0.00708 |
| Haiku 4.5 | $0.00004 | $0.00354 |
Grade C, and why
oma-orchestration scanned grade C with 1 finding 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 yesterday.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- oma-docs:ignore-start --> Copies of this mod
1 near-identical copy found in the catalogue:
- oma-orchestration — 100% identical, 92 lines differ
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestration - Automated Multi-Agent Coordination
Scheduling
Goal
Automatically orchestrate multi-agent execution with task decomposition, native/fallback dispatch, memory coordination, progress monitoring, verification, QA cross-review, retry, and result collection.
Intent signature
- User asks to orchestrate, run in parallel, automate multi-agent execution, or coordinate full-stack work end to end.
- Task requires multiple specialist agents and a persistent review/remediation loop.
When to use
- Complex feature requires multiple specialized agents working in parallel
- User wants automated execution without manually spawning agents
- Full-stack implementation spanning backend, frontend, mobile, and QA
- User says "run it automatically", "run in parallel", or similar automation requests
When NOT to use
- Simple single-domain task -> use the specific agent directly
- User wants step-by-step manual control -> use oma-coordination
- Quick bug fixes or minor changes
Expected inputs
- Complex feature or workflow request
- Project config, model/vendor routing, agent types, task constraints, and workspace/session needs
- Acceptance criteria and verification expectations
Expected outputs
- Orchestrator session state, task board, progress files, result files, and final summary
- Specialist agent outputs after mechanical checks, automated verify, and QA cross-review
- Review history and retry/remediation status when loops fail
Dependencies
.agents/oma-config.yaml,.codex/agents/*.toml,.gemini/agents/*.md, or fallbackoma agent spawn- Memory provider config, subagent prompt template, scripts, task templates, verify script, and session metrics
Control-flow features
- Branches by vendor/native dispatch availability, priority tiers, agent completion/failure, verification status, QA verdict, retry limits, and clarification debt
- Spawns processes/agents and reads/writes memory/result files
- Preserves unresolved evidence when bounded recovery stops
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- config/cli-config.yaml 3.4 KB
- resources/memory-schema.md 6.7 KB
- resources/subagent-prompt-template.md 4.5 KB
- scripts/parallel-run.sh 231 B runs code
- scripts/spawn-agent.sh 178 B runs code
- scripts/verify.sh 542 B runs code
- templates/backend-task.md 608 B
- templates/debug-task.md 339 B
- templates/frontend-task.md 598 B
- templates/mobile-task.md 604 B
- templates/qa-task.md 441 B
- templates/tasks-example.yaml 418 B
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.
- yesterday Changed · -6 lines · +1 tokens per session 174338fb10d8
- 4d ago Changed 449f08343e21
- 11d ago First seen · 325 lines · 43 tokens per session scan C 98e846deae96
oma-orchestration is a skill published in the GitHub repository first-fluke/oh-my-agent (1,283 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 3,539 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
ai-fleet-project-execution
AI fleet project execution (orchestrator=PM, marketing agent, backend dev agent, video agent). Fast-iteration architecture pivots and inter-agent task delegation across multi-hour sessions. Use when a user assigns a multi-agent project with "take it as a team" instruction.
github-pr-rebase-merge
Merge a stack of GitHub PRs sequentially when they share files and will cause cascading conflicts. Triggers when user says "merge the PRs sorban" or similar, and the PRs come from external forks (cannot push back to PR branch).
memoria-heartbeat
Minden körben átnézi az ELŐZŐ KÖR ÓTA történteket, menti a fontosat, és skill-eket generál ha volt komplex munka.
handoff
Generate a HANDOFF.md context transfer document for session continuity. Use when switching sessions, handing off to another agent, or preserving complex task context before a context window reset. Trigger on "/handoff" command or "handoff:" prefix in inter-agent messages.
approval-request-handling
A fő-ágens eljárása, amikor egy sub-ágens jóváhagyást kér az approval API-n keresztül ([APPROVALREQUEST] inter-agent üzenet). Kiküldi a kérést a tulajdonosnak, feldolgozza a szöveges válaszát, és lezárja az approvalt. Akkor használd, ha [APPROVALREQUEST] kezdetű inter-agent üzenetet kapsz.