issue-logger

A workflow for turning a described SuperPlane problem into a structured issue. SuperPlane is the software project whose bug or request is being recorded.

In plain words
What is it for?
Use it to draft bug, enhancement, feature, or papercut reports, save them in tmp/pm_logger, and optionally create them on GitHub.
Why use it?
It removes the need to research the project, choose an issue category, set a priority, and format the report from scratch.

Command for Cursor

Install

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.

agentmods
npx agentmods add commands/superplanehq/superplane/issue-logger
Clone the repo
git clone --depth 1 https://github.com/superplanehq/superplane

Made for: Cursor.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 932 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00932
Opus 5 $0.00017 $0.00466
Sonnet 5 $0.00007 $0.00186
Haiku 4.5 $0.00003 $0.00093

Measured yesterday against content hash d277c3cda9ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-logger 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 yesterday.

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.

.cursor/commands/issue-logger.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Logger

You are helping the user log a general SuperPlane issue (not an integration issue). They will describe an improvement, bug, or request in natural language. Your job is to research and understand it in SuperPlane context, classify the issue type, suggest priority (P1–P4), propose a title and body in tmp/pm_logger, and optionally create the issue on GitHub with the correct label and Board Priority.

Use the skill superplane-issue-logger for the full workflow: research and understanding, issue type classification (bug / enhancement / feature / papercut), priority rules (P1–P4), body templates, draft location (tmp/pm_logger/), screenshot handling, and optional GitHub MCP steps (create issue, type label, Board, Priority; suggest video after creation). Follow the issue-logger-conventions rule when creating or editing files in tmp/pm_logger.

Input

  • The user's message: a natural-language description of the improvement, bug, or request (e.g. "The Copy button in the toolbar is truncated", "Add bulk select for canvas nodes", "Small typo in the settings header").
  • If the description is vague, ask for: what exactly is wrong or desired, where in the app it happens, expected vs actual (for bugs), and steps to reproduce (for bugs).
  • If they describe multiple items, ask which one to capture first or create separate drafts.

Process

  1. Research and clarify: Use docs/contributing and docs.superplane.com as needed. If the description is unclear, prompt the user before classifying.
  2. Classify: Map to exactly one of bug, enhancement, feature, papercut using the skill's definitions (e.g. breaks flow → bug; annoying but workable → papercut).
  3. Suggest priority: Propose P1–P4 with a brief rationale using the skill's rules. Ask the user to confirm or change before writing the draft.
  4. Draft: Write a short title (max 40 characters) and body to tmp/pm_logger/<slug>.md using the correct short template (bug, papercut, enhancement, feature). Title: one or two concrete concepts; not a full list of details, not too vague (e.g. "layout and icons" not "polish", not "long names/IDs rendering, icons, responsive width"). Do not put Priority in the body (it is set via the Board only). For bug or papercut, if the user didn't provide a screenshot, ask in chat; if they pasted one in chat, note that they can paste it into the issue after creation (MCP cannot upload images to the issue body).
  5. Optional — log to GitHub: Only after the user has verified the draft and explicitly approved (e.g. "looks good", "log it"). Do not create the issue until then. When approved: read the draft, create the issue via GitHub MCP, add the type label (bug / enhancement / feature / papercut), add to SuperPlane Board (project 2), set Priority (P1–P4) via Board fields, then suggest they attach a video to the issue.

Read the full file on GitHub · 36 lines

Changes

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.

  1. yesterday First seen · 36 lines · 34 tokens per session scan A d277c3cda9ad

Subscribe to this mod's changes

issue-logger is a command published in the GitHub repository superplanehq/superplane (5,633 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 932 once invoked, about $0.0002 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 2026-08-30.