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 agentmods add skills/catwillgh/mainframe/mainframe-tickets-verifynpx skills add CATWILLgh/MAINFRAME --skill mainframe-tickets-verifygit 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-tickets-verify)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-tickets-verify"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-tickets-verify.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 | $0.00073 | $0.00900 |
| Opus 5 | $0.00036 | $0.00450 |
| Sonnet 5 | $0.00015 | $0.00180 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
mainframe-tickets-verify 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 6d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify implemented tickets
Treat the native Goal objective and any plain-language scope supplied with the
explicit invocation as the run boundary. An empty scope means every eligible
ticket in docs/tickets/open/needs-verification/. Process one ticket at a time
until the selected queue is exhausted, the user pauses or cancels the run, or
no eligible work can continue because of an evidenced external blocker.
Do not continue if this task implemented any selected ticket. Independent verification must start in a fresh task with no ownership of the implementation. Before checking a ticket, read ticket-format.md and mainframe-testing-strategy.
Reconstruct the claim
Confirm that the ticket remains in open/needs-verification/, then inspect its
full recorded history, the actual implementation, relevant repository history,
and the current affected paths. Treat the ticket prose, implementation notes,
and prior green commands as leads rather than proof.
State the original observable problem, the claimed correction, and the business or technical contract that would distinguish success from a plausible false positive. Inspect every command, project script, fixture, setup step, and external dependency before running it. Do not touch a remote, shared, staging, or production environment without separate explicit authority.
Obtain independent evidence
Reproduce the original gap through its regression protection or the smallest faithful current observation. Run focused checks and proportionate broader checks that can expose regressions in the affected contract, meaningful error paths, and cleanup behavior. Use deterministic interleavings for concurrency claims. When generated output, serialization, installation, or another consumer-facing artifact is part of the result, inspect the real produced shape or consumer boundary rather than only its source.
Use a real dependency or deployed check only when that boundary is the risk and the environment is available and authorized. Never convert an unavailable environment, a passing mock, a coverage percentage, or an unrelated green suite into evidence for a claim it cannot prove. Report only observations made in this verification task.
What ships with it
1 file 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.
- 6d ago First seen · 88 lines · 73 tokens per session scan A 799cdca50fb1
mainframe-tickets-verify is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 16d ago), licensed MIT. It adds 73 tokens to every session and 900 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).
eval-harness
Assessment-driven development — Quantify code generation quality with pass@k / pass^k metrics, automatically scored by Grader.
ph-grill-me
(PH) Pressure-test a concrete decision, design, or plan only when the user asks to examine assumptions, alternatives, risks, or trade-offs.
git-worktree
Create isolated git worktrees for feature development without switching branches.
ph-tdd
(PH) Use after an approved delivery boundary to define a focused failing behavior test before implementation.