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 PacificStudio/openase --skill auto-harnessgit clone --depth 1 https://github.com/PacificStudio/openaseWrote 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/pacificstudio/openase/auto-harness)<a href="https://agentmods.dev/skills/pacificstudio/openase/auto-harness"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/auto-harness/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/pacificstudio/openase/auto-harness"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/auto-harness.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00096 | $0.00978 |
| Opus 5.5 | $0.00038 | $0.00391 |
| Sonnet 5.5 | $0.00019 | $0.00196 |
| Haiku 4.5 | $0.00010 | $0.00098 |
Grade A, and why
auto-harness 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Harness
Overview
Design the project harness so repository rules become executable. Start by mapping where semantics can drift, then convert the risky ones into generated artifacts, contract tests, type or layer guards, and CI checks.
Workflow
-
Build a harness map before proposing fixes.
- Read entrypoint materials first:
AGENTS.md, repo-root docs,Makefile, package scripts, CI workflows, API specs, codegen config, lint config, type-check config, and test runners. - Avoid bulk-loading every doc. Follow progressive disclosure: read only the references needed for the current risk.
- Record the harness surfaces that already exist: documentation rules, generated files, test suites, CI gates, architecture constraints, observability standards, and debt tracking.
- Read entrypoint materials first:
-
Load the matching reference files.
- Read
references/checklist.mdto score the current harness and find missing guardrails. - Read
references/guide.mdwhen you need the design principles and recommended repository shapes. - Read
references/guard-patterns.mdwhen you need concrete enforcement strategies. - Read
references/fix-plan.mdwhen you need a staged remediation plan or a deliverable template. - Read
references/upstream.mdwhen you need the builtin bundle provenance or manual sync guidance.
- Read
-
Diagnose drift as a systems problem, not a single bug.
- Search for the same semantic repeated across layers: permissions, routes, CLI commands, OpenAPI, generated clients, frontend assumptions, docs, logging fields, config, and tests.
- Flag any semantic that is declared in multiple places without a hard synchronization mechanism.
- Treat "scope list says yes, runtime path says no" and similar mismatches as harness failures, not just implementation bugs.
- Write the diagnosis in terms of duplicated authority, missing invariants, missing generated artifacts, or missing tests.
-
Prefer hard guardrails over policy prose.
- Establish a single source of truth for drift-sensitive semantics.
- Generate downstream artifacts instead of hand-maintaining parallel definitions.
- Add failing checks in CI for zero-drift contracts: OpenAPI parity, generated client freshness, import-layer guards, JSON schema checks, snapshot parity, or table-driven route or scope coverage.
- Add type-level or package-boundary checks when architecture depends on layering.
- Add structured logs when the real system is expensive to exercise and deterministic tests are limited.
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.
- 1mo ago First seen · 71 lines · 96 tokens per session scan A 7fd7af468050
auto-harness is a skill published in the GitHub repository PacificStudio/openase (269 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 96 tokens to every session and 978 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
verification
Prove that a coding task is actually complete. Use this after meaningful code changes, when tests/builds fail or are skipped, before marking a plan or goal complete, and whenever acceptance depends on runtime, security, recovery, performance, or cross-module evidence.
ai-discover
Read-only discovery step of the auto-improvement loop. One bounded agent turn per cycle reads the focus files (Read/Grep/Glob only, no shell, no subagents) and replies with a JSON array of testable surfaces {file, line, symbol, rule, message, hypothesis}; the spine authors fixes and verifies them. Discovery only — no…
ulw-qa
This is an OMH ultraqa workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).