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-record-project-problemgit 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-record-project-problem)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-record-project-problem"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-record-project-problem/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-record-project-problem"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-record-project-problem.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 | $0.00040 | $0.00915 |
| Opus 5.5 | $0.00016 | $0.00366 |
| Sonnet 5.5 | $0.00008 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
mainframe-record-project-problem 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record a project problem
Operate in the current project: the repository named by the task or, absent that, the active working repository. An explicit request to use this skill means apply the recording method there. Keep discovery and ticket writes inside that project and its explicitly configured issue routes.
Use this skill when work exposes a concrete problem in the receiving project and resolving it is outside the assigned result. Preserve the finding without silently expanding scope, then continue the assigned work when the problem does not prevent a valid or safe result.
First decide whether the problem belongs to the active work. If it prevents achieving or verifying the assigned result, return it to that work instead of deferring it to a ticket. Do not use a ticket to make unfinished in-scope work appear complete.
When the work will deliberately leave an evidenced problem unresolved, read references/surface-ticket.md and apply its surfacing boundary before recording or returning the finding.
If no concrete project finding exists yet, keep this method ready for the assigned work; do not fabricate tickets or start a random search campaign.
Use the project's queue
When the project uses docs/tickets/AGENTS.md, read that contract and create observations with its required YAML fields and Evidence section. Preserve matching open records; recording does not perform campaign investigation or lifecycle transitions.
Otherwise inspect only the current project's effective instructions and configured issue locations. Honor an established local queue or external tracker; do not establish a competing source of truth. Existing noncanonical tickets require the explicit mainframe-tickets-init migration workflow, not silent normalization by this skill.
If no issue route exists and local documentation writes are authorized, establish docs/tickets/ using references/new-queue.md, then record the evidenced finding in open/observations/. An explicit request to apply this skill authorizes this local setup unless the task or project forbids it; automatic use stays within existing write authority. Create the rule files and directories, not an audit campaign or artificial records. Preserve the project's tracked/ignored ownership and do not change ignore rules without a settled choice.
What ships with it
2 files 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.
- 8d ago Changed · +6 lines · +8 tokens per session 97f890123959
- 9d ago Changed 79fda8f08842
- 14d ago Changed · -39 tokens per session ffdf01b109fd
- 1mo ago First seen · 51 lines · 71 tokens per session scan A b19d61088b43
mainframe-record-project-problem is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 915 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.
omc-plan
Strategic planning with optional interview workflow.
ask-navigator
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it…
project-session-manager
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions.
ultragoal
Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session.
uctm-init
An initialization procedure for uc-taskmanager, a project task-management pipeline. It creates a works directory and, with permission, adds the file and command access the agent needs to local settings.