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-init)<a href="https://agentmods.dev/commands/catwillgh/mainframe/mainframe-tickets-init"><img src="https://agentmods.dev/badge/commands/catwillgh/mainframe/mainframe-tickets-init/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-init"><img src="https://agentmods.dev/badge/commands/catwillgh/mainframe/mainframe-tickets-init.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 | $0.02629 |
| Opus 5.5 | $0.00000 | $0.01052 |
| Sonnet 5.5 | $0.00000 | $0.00526 |
| Haiku 4.5 | $0.00000 | $0.00263 |
Grade A, and why
mainframe-tickets-init 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize or normalize the project's ticket system
This is an explicit user-invoked, no-argument command for the current project. Establish docs/tickets/ and migrate existing project tickets into the standard below. Do not investigate ticket claims, deduplicate problems, implement fixes, or infer user approval. Run only for the current project under an explicit initialization request.
Resolve and preserve existing ownership
Resolve the current project and inspect its effective instructions and existing ticket locations, schemas, links, and tracked/ignored ownership. Confine discovery to that project and explicitly configured issue routes. Preserve unrelated documents, code, dirty work, and user configuration. Reuse the project's established ownership for ticket files; if no evidence decides whether new records should be shared through Git or remain local, resolve that one choice before changing ignore rules.
The invocation authorizes local ticket migration and ticket-rule files. An external tracker is not a local directory to move: use an already authorized export when available, preserve external identities and URLs, and do not mutate the service or establish a competing live queue without an explicit source-of-truth decision. Report such a boundary instead of pretending initialization succeeded.
Inventory records and proposed old-to-new paths before moving them. Identify semantic state from explicit metadata and history, not folder spelling alone. Preserve existing IDs, body content, meaningful history, evidence, and relationships. Assign new four-character lowercase hexadecimal IDs only to records without an ID, checking all active and archived IDs for collisions. Quote IDs in YAML, including numeric-only IDs. Never overwrite records or silently regenerate conflicting existing IDs; resolve an ambiguous identity before migrating the affected records.
Map records conservatively
Map each existing record to one destination:
| Evidence already in the record | Destination |
|---|---|
| New finding with no completed investigation | open/observations/ |
| Unclear open state, missing investigation, or unsupported readiness | open/needs-scope-review/ |
| A specific unresolved user-owned decision or authority requirement | open/needs-decision/ |
| Completed investigation, fixed expected behavior and explicit autonomous boundary | open/ready/, execution: autonomous |
| Completed investigation plus recorded user approval for one bounded implementation | open/ready/, execution: user-approved |
| Completed implementation with evidence awaiting an independent check | open/needs-verification/, preserve its evidenced execution route |
| Existing explicit terminal resolution | archive/resolved/ |
| Existing explicit rejection, supersession, or duplicate outcome | archive/rejected/ |
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 3c88b1a4d594
- 9d ago First seen · 136 lines · 0 tokens per session scan A a0c787e3b1ee
mainframe-tickets-init 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 2,629 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 2026-10-07.
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.