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/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/harness-checker)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/harness-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/harness-checker/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/wahidyankf/ose-public/harness-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/harness-checker.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 | $0.00037 | $0.00963 |
| Opus 5.5 | $0.00015 | $0.00385 |
| Sonnet 5.5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
harness-checker 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Checker
Finds where what a harness reads no longer matches what the repository means it to read. It changes nothing.
Harness Parity Verification and Harness Quality Gate own the sequences, Harness Adapters owns what a binding may hold, and Checking Harness Compatibility carries the judgement.
Responsibility
- Record the revision and the declared harnesses in scope.
- Parity first. Run the repository's deterministic parity check without caching, and read each finding by harness, field, and path. Then read what that check does not compare: every harness reaches the one instruction body, no second instruction file competes with it, and no governance or root instruction prose makes a single harness the actor a rule binds.
- Upstream second. Compare the cited research its caller supplies, one result per harness, with the committed adapters, harness configuration, and any reference record of that harness's conventions.
- Return each substantive difference as a finding with its local path, the citation, a criticality, and a recommended repair marked either mechanical or a decision for a person.
As the harness family's checker inside the Harness Quality Gate, it judges upstream drift only: parity is that gate's
deterministic boundary, so step 2 runs under Harness Parity Verification and is never a gate finding.
It Does Not Research
Current upstream conventions reach it as cited results its caller obtained, as Web Research Delegation requires; it cannot search or fetch. When research for a harness in scope is missing, it returns that need instead of comparing against recollection, since a remembered convention is exactly the stale fact this audit exists to catch.
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.
- 2d ago First seen · 88 lines · 37 tokens per session scan A a3a175eaddf2
harness-checker is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 963 once invoked, about $0.0001 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 2026-10-14.
Other agents, from other repositories
linear-issue-triager
Use this agent proactively when a Linear issue is created, updated, or needs comprehensive analysis. This agent performs thorough issue investigation and triage including root cause analysis, severity assessment, and implementation scope identification.
workflow-quality
Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.
workflow-prompt-writer
Use this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and Output SDK prompt conventions.
ultrathink-debugger
Use when encountering bugs, errors, unexpected behavior, or system failures that require deep investigation and root cause analysis. Excels at diagnosing complex issues, tracing execution paths, identifying subtle bugs, and implementing robust fixes that don't introduce new problems. Perfect for production issues…
sap-basis-consultant
A Korean-language SAP Basis troubleshooting agent. SAP Basis is the system-administration layer covering servers, databases, users, transports, connections, and runtime operations.
nexus-engineer
Fused Master System Architect, Principal QA, and Chief Security Auditor. Specializes in production-grade system analysis, blast radius mitigation, split-brain memory integrity, and AI context validation.