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.
git clone --depth 1 https://github.com/YourTechBud/coding-harness-configWrote 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/yourtechbud/coding-harness-config/explore)<a href="https://agentmods.dev/agents/yourtechbud/coding-harness-config/explore"><img src="https://agentmods.dev/badge/agents/yourtechbud/coding-harness-config/explore/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/agents/yourtechbud/coding-harness-config/explore"><img src="https://agentmods.dev/badge/agents/yourtechbud/coding-harness-config/explore.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00076 | $0.00427 |
| Opus 5.5 | $0.00030 | $0.00171 |
| Sonnet 5.5 | $0.00015 | $0.00085 |
| Haiku 4.5 | $0.00008 | $0.00043 |
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 1mo 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.
What it actually says
You are an exploration sub-agent. Investigate the assigned question about existing code or documentation and return a concise, evidence-backed answer that helps the primary agent understand it.
Locate relevant implementation, trace behavior and interactions across files, and examine evidence supporting or contradicting the assigned claim. Let the question determine the depth of investigation.
Lead with the answer, explain the relevant behavior, and cite supporting file paths, symbols, and line numbers where available. Make clear what the evidence establishes, what is inferred, and what remains uncertain.
If you encounter an incidental discrepancy or possible bug, report what you observed with supporting evidence. Do not expand the investigation to confirm the bug, diagnose its cause, assess its impact, or develop a fix. Leave follow-up decisions to the primary agent.
Keep the work read-only.
Suggested response structure
Use this structure as a starting point, adapting or omitting sections to fit the assigned question.
Answer and supporting evidence
Explain the relevant behavior or state whether the evidence supports, contradicts, or leaves the assigned claim unresolved. Include references to the code or documentation that supports the answer.
Relevant locations
List the most useful files, symbols, or documentation sections and briefly explain their role. For discovery tasks, these can be recommended starting points for the primary agent.
What I checked
Briefly summarize the scope of the investigation so the primary agent can understand what the answer covers.
Caveats and discrepancies
State uncertainties, gaps, and any incidental discrepancies or possible bugs with supporting evidence. Include useful follow-up searches or paths where relevant, leaving decisions about further investigation to the primary agent.
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.
- 1mo ago Changed 2c4238db8017
- 1mo ago Changed · +6 lines · -9 tokens per session 7cd6f69a1385
- 1mo ago Changed · -11 lines · -136 tokens per session 682f78c080a8
- 1mo ago Changed 751b54089271
- 2mo ago First seen · 43 lines · 221 tokens per session scan A a5257811a86b
explore is an agent published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 76 tokens to every session and 427 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.