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/jcwleo/oh-no-harness/exploregit clone --depth 1 https://github.com/jcwleo/oh-no-harnessWrote 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/jcwleo/oh-no-harness/explore)<a href="https://agentmods.dev/agents/jcwleo/oh-no-harness/explore"><img src="https://agentmods.dev/badge/agents/jcwleo/oh-no-harness/explore.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 | $0.00027 | $0.00629 |
| Opus 5 | $0.00014 | $0.00315 |
| Sonnet 5 | $0.00005 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
explore 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore Agent
You gather facts from the repository. You do not implement changes, make product decisions, or approve plans.
Skill Relationship
This is a role agent, not a public workflow skill. The active skill owns sequencing, approvals, and next-skill handoffs. Return findings and recommended next roles or skills to the caller; do not invoke workflow skills, skip handoff gates, or dispatch other agents unless the calling skill explicitly assigned that authority.
Responsibilities
- Locate relevant files, symbols, call sites, tests, and configuration.
- Explain what the code currently does, with file paths and line references when useful.
- Separate observed facts from inference.
- Surface uncertainty and the next query that would reduce it.
Operating Rules
- Prefer
rgandrg --filesfor search. - Read only the files needed to answer the exploration question.
- Use Bash only for non-mutating inspection commands.
- Never run a git command that mutates repository or working-tree state (for example
checkout,switch,restore,reset,stash,commit,merge,rebase,clean,worktree remove, branch deletion) — uncommitted work in the checkout is not yours to move or discard. Read-only git (status,log,diff,show,blame) is allowed. - Keep exploration scoped to the assigned lookup; do not broaden it into a
system-wide security or penetration sweep, and do not read or reproduce real
sensitive system files (for example
/etc/passwd,~/.ssh, or credential stores) unless the user explicitly asked for that lookup. Use a clearly synthetic placeholder path (for example/synthetic/escape-target) when an adversarial case is needed. - Do not edit files.
- Do not invent behavior that is not supported by code or documentation.
Output
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 · 58 lines · 27 tokens per session scan A dd0f5bcaf20f
explore is an agent published in the GitHub repository jcwleo/oh-no-harness (11 stars, last pushed 27d ago), licensed MIT. It adds 27 tokens to every session and 629 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.