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-debuggit 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-debug)<a href="https://agentmods.dev/skills/first-fluke/oh-my-agent/oma-debug"><img src="https://agentmods.dev/badge/skills/first-fluke/oh-my-agent/oma-debug.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01345 |
| Opus 5 | $0.00021 | $0.00673 |
| Sonnet 5 | $0.00008 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
oma-debug 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 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.
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Agent - Bug Fixing Specialist
Scheduling
Goal
Reproduce, diagnose, minimally fix, and regression-test bugs while preserving scope discipline and documenting root cause.
Intent signature
- User reports a bug, crash, traceback, exception, error message, performance issue, intermittent failure, or regression.
- User needs root cause analysis plus a minimal code fix and regression test.
When to use
- User reports a bug with error messages
- Something is broken and needs fixing
- Performance issues or slowdowns
- Intermittent failures or race conditions
- Regression bugs
When NOT to use
- Building new features -> use Frontend/Backend/Mobile agents
- General code review -> use QA Agent
Expected inputs
- Error message, failing behavior, reproduction steps, logs, test failure, or affected code path
- Existing tests, stack traces, environment notes, and suspected regression boundary
Expected outputs
- Root cause explanation
- Minimal fix scoped to the failing behavior
- Regression test or explicit reason it cannot be added
- Bug documentation under
.agents/results/bugs/when appropriate
Dependencies
resources/execution-protocol.md, examples, checklist, common patterns, and debugging checklist- Local codebase search and symbol/reference tools
- Project test, lint, typecheck, and runtime commands
Control-flow features
- Branches by reproduction success, error class, suspected layer, and verification outcome
- Reads logs/code/tests and writes code/tests/docs
- Must search for similar patterns after fixing
Structural Flow
Entry
- Capture the reported symptom and suspected scope.
- Reproduce or establish the closest reliable failing signal.
- Identify affected files, tests, and related patterns.
Scenes
- PREPARE: Gather symptoms, logs, reproduction path, and verification command.
- ACQUIRE: Read failing code, tests, references, and similar patterns.
- REASON: Isolate root cause and reject unsupported hypotheses.
- ACT: Apply minimal fix and regression test.
- VERIFY: Re-run failing and related checks.
- FINALIZE: Document root cause, fix, test, and residual risk.
What ships with it
6 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.
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 58a2ba9c275d
- 7d ago First seen · 149 lines · 42 tokens per session scan A 079e3a4c5874
oma-debug is a skill published in the GitHub repository first-fluke/oh-my-agent (1,273 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,345 once invoked, about $0.0002 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 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.
pinchtab-dev
Develop and contribute to the PinchTab project. Use when working on PinchTab source code, adding features, fixing bugs, running tests, or preparing PRs. Triggers on "work on pinchtab", "pinchtab development", "contribute to pinchtab", "fix pinchtab bug", "add pinchtab feature".
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
dos-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use dos-enforce-tune for policy knobs.
reqforge-greenkeeper
name: reqforge-greenkeeper description: Used when maintaining the ReqForge repository itself and its release gates fail — pnpm test, pnpm forge-smoke, pnpm sync:discover, adapter drift, skill fixtures, loadouts, or test-demo golden path. Restores a green, synced state with minimal changes. Not for bugs in user apps…
subagent-pre-existing-misattribution
Catch subagent reviewers misattributing test failures across the pre-existing / PR-introduced boundary — in BOTH directions. Use when: (1) a multi-task subagent-driven plan reports "N pre-existing failures, unrelated" across consecutive tasks and the count never changes, (2) an architectural / final reviewer at the…