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/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/commands/catwillgh/mainframe/mainframe-tickets-refine)<a href="https://agentmods.dev/commands/catwillgh/mainframe/mainframe-tickets-refine"><img src="https://agentmods.dev/badge/commands/catwillgh/mainframe/mainframe-tickets-refine/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/commands/catwillgh/mainframe/mainframe-tickets-refine"><img src="https://agentmods.dev/badge/commands/catwillgh/mainframe/mainframe-tickets-refine.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 | $0.00000 | $0.02284 |
| Opus 5.5 | $0.00000 | $0.00914 |
| Sonnet 5.5 | $0.00000 | $0.00457 |
| Haiku 4.5 | $0.00000 | $0.00228 |
Grade A, and why
mainframe-tickets-refine 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 8d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine project tickets
This is a user-invocable command. Execute it only because the current invocation explicitly selected it. It takes no arguments: every invocation processes the complete current project queue that is eligible for refinement.
Investigate each eligible ticket deeply: establish its code execution path, cause or supported mechanism, blast radius, and relationship to other tickets. Consolidate the evidence, route it to the correct next state, and continue until no ticket remains that this command can further process. Do not search the project broadly for new problems or implement fixes during this command.
When the user first starts a native goal and then invokes this command in a separate message, perform the campaign under that existing goal. Do not create a second goal or interpret the command as a request to investigate just one ticket.
Read the initialized ticket contract
Read docs/tickets/AGENTS.md and check its directory, record-format, and lifecycle rules before queue writes. If the root, contract, or required layout is missing or conflicts with effective project rules, report that mainframe-tickets-init must initialize or reconcile it; do not run initialization implicitly, invent another tracker, or migrate unrelated records. Use docs/tickets/ in the current project only. The directory is state: do not add a YAML status field. Preserve string IDs, required frontmatter, meaningful evidence and links. Exclude .campaigns/ and .migration/ from every ticket scan.
Select from docs/tickets/open/observations/ and open/needs-scope-review/. Investigate one record at a time, adding Investigation (trace, mechanism, alternatives and blast radius), Acceptance, and any applicable Relationships, User decision or Blocker sections. Consolidate evidence before moving or retiring records. Route to open/ready/ with execution: autonomous and an evidence-backed Autonomous implementation boundary only when no user-owned decision remains; otherwise use open/needs-decision/, retain open/needs-scope-review/ for unavailable evidence, or use archive/rejected/ for a proved rejection, supersession or duplicate. Preserve an existing execution: user-approved route when a re-investigated ticket returns to ready; do not convert it to autonomous queue work without explicit authority. Assign autonomous only to work without that preserved route and with the demonstrated autonomous boundary. Do not fabricate user approval. Save campaign progress under .campaigns/ and validate each record's required YAML fields and links after moves.
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.
- 8d ago Changed d8810b6b3bcc
- 9d ago Changed · +17 lines 5a5bf4c385c4
- 14d ago First seen · 77 lines · 0 tokens per session scan A 02d839e3da81
mainframe-tickets-refine is a command published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,284 tokens. 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 2026-10-02.
Other commands, from other repositories
add-package
Add and configure new project dependencies.
changelog-demo-command
Demo changelog automation features.
opsx-bulk-archive
Archive multiple completed changes at once.
iteration-drive
Drive the active iteration to completion — Phase 2 Autonomous Execute, Phase 3 iteration-close, Phase 4 Create PR, Phase 5 PR merge-ready loop (prefer babysit/-babysit; optional greploop when repo has it; else CI fallback) until mergeable, then Phase 6 post-merge close once the PR is verified merged. Not Done until…
project-stage-detect
Detect project phase and recommend actions.
dev-story
Implement a story with full context.