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/tickets-refine)<a href="https://agentmods.dev/commands/catwillgh/mainframe/tickets-refine"><img src="https://agentmods.dev/badge/commands/catwillgh/mainframe/tickets-refine.svg" alt="Measured on agentmods" 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 | $0.01297 |
| Opus 5 | $0.00000 | $0.00648 |
| Sonnet 5 | $0.00000 | $0.00259 |
| Haiku 4.5 | $0.00000 | $0.00130 |
Grade A, and why
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 today.
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 — 75 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.
Expand each eligible ticket as far as reliable evidence and the refinement authority allow, 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.
Establish the queue and authority
Resolve the current project root, its configured issue route, and the lifecycle states that represent new observations or tickets awaiting more scope evidence. Do not use another project's queue or MAINFRAME's central harness-feedback queue.
If the project has no configured issue route or refinement lifecycle, return the exact missing configuration and stop without inventing one. If the queue is external, mutate it only when the current caller supplied that authority. Otherwise perform the permitted investigation and return the complete ticket updates with the exact missing write action.
The invocation authorizes only the project inspection, safe focused checks, and ticket mutations required for refinement within the supplied environment and authority. It does not authorize implementation, deployment, remote or shared writes, destructive operations, dependency installation, broad infrastructure changes, repository-history changes, commits, or pushes.
Preserve the current checkout, branch, unrelated dirty work, existing processes, and user-owned configuration.
Process exactly one ticket at a time
Read the current eligible queue afresh. Select one ticket and keep it as the only active ticket until its evidence, scope, identity, and next state are complete. Do not investigate separate tickets concurrently. Delegated work, when available and useful, may gather bounded evidence only for that same active ticket and must return its sources, limitations, and unverified assumptions.
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.
- today First seen · 75 lines · 0 tokens per session scan A 90aba5fe814d
tickets-refine is a command published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,297 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 2026-09-08.
Other commands, from other repositories
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
plan-ceo-review
Strategic product gate — challenge the brief, find the 10-star product hiding inside the request, before writing any code.
team
Virtual eng team orchestrator. Runs a goal end-to-end through the whole team — strategy → plan → build → QA → ship — conducted by the engineering-manager, delegating to every specialist. One entry point that connects /ceo-review, /eng-review, /qa, and /ship.
content-start
Content production session start command. Gives the daily content session a structured start, shows pending work, and sets priorities.
onboard
Project onboarding command. For adapting to a new project quickly and thoroughly.
proposal
Client proposal command. Builds a professional client proposal from project summaries. Valid for 30 days.