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 CATWILLgh/MAINFRAME --skill mainframe-project-harnessgit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWrote 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/catwillgh/mainframe/mainframe-project-harness)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-project-harness"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-project-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/catwillgh/mainframe/mainframe-project-harness"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-project-harness.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 | $0.00038 | $0.00957 |
| Opus 5.5 | $0.00015 | $0.00383 |
| Sonnet 5.5 | $0.00008 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
mainframe-project-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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain the project harness
Start with the configuration implicated by the request or observed fault. Use current native tool contracts and established project evidence; consult official documentation when discovery, precedence, permissions, or reload behavior is uncertain or version-sensitive. Reuse current evidence already available.
Establish the effective harness
Read only the global configuration that can affect the project. Treat it as a preserved baseline and record its exact source and effect without changing it.
For a local repair, trace only the affected instruction chain and its owners. For an explicit project-wide harness audit, inventory discoverable components and inspect the relevant bodies, including:
- root and nested instructions, overrides, and imports;
- project settings and permissions;
- skills and agent definitions;
- hooks, commands, and workflows;
- MCP declarations and tool policies, without reading secret values;
- references, includes, symlinks, generated copies, and their canonical sources.
Reconstruct the actual chain from the global baseline through the project root to relevant subtrees. Distinguish always-loaded instructions from components loaded only when selected or invoked. Identify which source wins, where each rule applies, and which material is not discoverable.
Treat archives, backups, Trash, fixtures, caches, dependencies, and vendor trees as inactive unless documented discovery rules actually include them.
Surface conflicts proactively
Verify a suspected conflict against actual scope and precedence before reporting it. Do not manufacture a problem from harmless inheritance, intentional specialization, or wording that has the same effect.
When a real conflict or harness defect is found, report it proactively to the current recipient or your immediate caller. State:
- the exact sources involved;
- the effective behavior and why it wins;
- the practical consequence for the current task or project;
- the owner and correct edit location;
- whether work can safely continue.
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.
- 9d ago Changed · +11 tokens per session c37d6415e8b4
- 14d ago Changed · +15 lines · -80 tokens per session 5da0a54ca4eb
- 1mo ago First seen · 77 lines · 107 tokens per session scan A 43ac04f0fd4b
mainframe-project-harness is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 957 once invoked, about $0.0002 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 2026-09-08.
Other skills, from other repositories
minions
PM Ops — orchestrator of the minions AI subagent team. Single entry point: decomposes requests, delegates to minions- subagents in parallel or sequence, aggregates output.
optimize-goal
Use when the user wants to review, critique, tighten, or enhance an existing goal.md file (a written spec/prompt authored for a /goal command instead of typed into chat) before it gets executed — including requests like "review this goal.md", "enhance my goal.md", "optimize this goal", or sharing a goal.md file and…
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
cmux-architecture
Skill "cmux-architecture" from manaflow-ai/cmux, covering cmux architecture, package architecture, layers, file organization and documentation.