New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Mulmoterminal Bug Report

by receptron in receptron/mulmoterminal

Help desk for "MulmoTerminal is broken". An agent skill from receptron/mulmoterminal.

MITAuto-check passedTesting & QA

Install Mulmoterminal Bug Report

skills CLI
$ npx skills add receptron/mulmoterminal --skill mulmoterminal-bug-report -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install receptron/mulmoterminal mulmoterminal-bug-report --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/receptron/mulmoterminal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/server/skills/mulmoterminal-bug-report .claude/skills/mulmoterminal-bug-report && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mulmoterminal-bug-report
GitHub stars
238
Token cost
~1.7k tokens
SKILL.md length
799 words
Files
2
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Help desk for "MulmoTerminal is broken". An agent skill from receptron/mulmoterminal.

  • Works in 4 steps: Hear the symptom (collect nothing yet) → Is it configuration, or by design? (this… → Is it already known? → …
  • The user says MulmoTerminal is broken / weird / not working
  • SKILL.md covers Rules that hold in every step, Step 1 — Hear the symptom…, Step 2 — Is it configuration,… and Step 3 — Is it already known?, plus 2 more sections
  • Calls curl, gh and node

What it does

Mulmoterminal Bug Report is an agent skill from receptron/mulmoterminal. Help desk for "MulmoTerminal is broken". Hears out the symptom, then checks whether the behaviour is actually configuration or by design — reading the real config, schema and version rather than guessing — searches the existing issues, and only files a GitHub issue for what survives all of that, with the environment and repro details collected and masked. Use when the user says MulmoTerminal is broken / weird / not working, wants to report a bug or file an issue about it, or asks why MulmoTerminal behaves the way…

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `faq.md`).

It sits in Testing & QA, covering QA and bug reports and Customer support. It works with GitHub. The repository describes itself as: Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT. The licence is MIT.

When your agent uses it

  • The user says MulmoTerminal is broken / weird / not working
  • Wants to report a bug
  • File an issue about it
  • Asks why MulmoTerminal behaves the way it does

Example prompts

  • “MulmoTerminal is broken”
  • “/mulmoterminal-bug-report”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Hear the symptom (collect nothing yet)
  2. Is it configuration, or by design? (this is the actual job)
  3. Is it already known?
  4. File it

What it can do on your machine

Read from SKILL.md and the folder at commit 41cec8f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • gh
    • node
    • claude
    • codex

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl and gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mulmoterminal Bug Report loads about 1.7k tokens when it runs. Until then it costs about 150 tokens; SKILL.md has 799 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~150
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from receptron/mulmoterminal at commit 41cec8f, republished under its MIT licence (© receptron). 799 words, ~1,730 tokens.

Download SKILL.mdSave it as .claude/skills/mulmoterminal-bug-report/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
mulmoterminal-bug-report
description
Help desk for "MulmoTerminal is broken". Hears out the symptom, then checks whether the behaviour is actually configuration or by design — reading the real config, schema and version rather than guessing — searches the existing issues, and only files a GitHub issue for what survives all of that, with the environment and repro details collected and masked. Use when the user says MulmoTerminal is broken / weird / not working, wants to report a bug or file an issue about it, or asks why MulmoTerminal behaves the way it does. Works in whatever language the user writes in.

MulmoTerminal — is it a bug?

The goal is that the user ends up unblocked, not that an issue gets filed. An issue is what's left after the other three steps fail to explain the behaviour.

Work the steps in order. Stop the moment the user is unblocked.

Rules that hold in every step

  • Never assert "that's by design" from memory. Say it only with a reason attached: a config key, an implementation file, a guide page. faq.md is an index of where to look — it deliberately contains no values.
  • Read the real thing. Current and default values come from the user's actual config file, the schema in the source, or the running server — never from this file, and never from recollection.
  • "I don't know" is an allowed answer. If a step cannot decide, say so and go to the next one. Never close the conversation by guessing.
  • Nothing leaves the machine before the user has seen it in full and said yes.
  • Reply in the language the user writes in.

Step 1 — Hear the symptom (collect nothing yet)

Ask with AskUserQuestion, options first — a user who is already frustrated should be picking, not composing. Up to 4 questions per call; two calls cover this comfortably.

  • What kind — display looks wrong / input doesn't work / a session died or won't connect / won't start at all / phone features / something else
  • Where — a grid cell / the zoomed view / the single view / the file browser / settings / phone
  • Which agent — claude / codex / shell / a launcher cell / a command cell
  • How often — every time / sometimes / once
  • Since when — after an update / it always did this / not sure

Then, in prose: what did you expect, and what happened instead? Those two sentences are what the next step is judged against, so get them before touching anything else.

Step 2 — Is it configuration, or by design? (this is the actual job)

  1. Read faq.md (next to this file) and find the entry closest to the symptom.
  2. Follow its pointers to the real values:
    • global config: ~/.mulmoterminal/config.json
    • directory config: <the directory in question>/.mulmoterminal.json
    • the running server: curl --noproxy localhost -s http://localhost:34567/api/config (34567 is the default port; if the user changed it, it's the port in their browser's address bar). /api/update-status, /api/sessions, /api/git-status?cwd=<dir> and /api/dir-config?cwd=<dir> answer too.
    • the source files named by the entry, when the question is about accepted values or behaviour
  3. If that explains the gap between expected and actual, say why, show the fix, and stop.
    • If the fix is a .mulmoterminal.json, hand off to /mulmoterminal-config instead of dictating JSON — it knows the schema and validates.
  4. If nothing explains it, or the explanation is a guess, go to Step 3. Do not stretch the FAQ to cover a symptom it doesn't cover.

Solved here? Offer to post it as an FAQ issue (see the last section) — but only if someone else would plausibly hit the same wall.

Show full SKILL.md (317 more words)Show less

Step 3 — Is it already known?

bash
gh issue list --repo receptron/mulmoterminal --state all --limit 20 --search "<symptom keywords>"

No gh? Hand over the search URL instead: https://github.com/receptron/mulmoterminal/issues?q=<keywords>

  • Closed and fixed → compare the user's version against the release that fixed it. If they're simply behind, tell them to update and stop. (Version: the package's package.json; /api/update-status says whether a newer one exists.)
  • Open → do not open a second one. Offer to add this user's environment and repro steps as a comment — a second reproduction is worth more than a duplicate.
  • Nothing found → Step 4.

Step 4 — File it

Only now collect details.

bash
node -p "require('<install dir>/package.json').version"   # or the version in the web header
node -v && uname -sm && echo "$SHELL"
tmux -V; gh --version | head -1; claude --version; codex --version    # each may be absent; only the latest tmux is supported, so an older one is the first thing to update
curl --noproxy localhost -s http://localhost:34567/api/update-status
curl --noproxy localhost -s http://localhost:34567/api/sessions      # summarize: cell count, agents, live vs tmux-only
curl --noproxy localhost -s "http://localhost:34567/api/git-status?cwd=<dir>"
cat ~/.mulmoterminal/config.json                  # mask before quoting
cat <dir>/.mulmoterminal.json                     # mask before quoting

Ask the user for what the host cannot see: the browser and its version, any red errors in the browser console, and a screenshot if the symptom is visual.

Masking, before anything is written into a report:

  • Anything key-shaped — *_KEY, *_TOKEN, Authorization, provider credentials — is reported as the key name with *** for the value. Never the value, not even partially.
  • Shorten the home directory to ~ in every path.
  • A terminal screenshot can carry prompt text and internal paths — say so before it's attached.

Report body:

markdown
## What happened
## What I expected
## Steps to reproduce
1.
## Environment
- mulmoterminal / Node / OS / browser
- tmux / gh / claude / codex
- how it was started (npx, local dev)
## Attachments

Show the whole thing, get an explicit yes, then:

bash
gh issue create --repo receptron/mulmoterminal --title "<title>" --body-file <file>

No gh? Print the markdown for copy-paste plus https://github.com/receptron/mulmoterminal/issues/new.

FAQ issues (when Step 2 resolved it)

A question that took a human to answer is a signal about the product, so it's worth recording — but only with the user's agreement, and never as an authoritative answer.

  • Title: the question as the user asked it. Body: what was asked, what the answer turned out to be, and where it was checked (config key / file).
  • Open the body with a line saying the answer came from this skill and is awaiting maintainer review — the answer here is a draft, not documentation.
  • If an FAQ issue for the same question already exists, comment there instead of opening another.
  • Never edit faq.md yourself. A maintainer reviews the issue and folds it into the repo; this skill only posts.

© receptron, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in server/skills/mulmoterminal-bug-report of receptron/mulmoterminal.

  • SKILL.md
  • faq.md

Open the folder on GitHubat commit 41cec8f

Compare with similar skills

Mulmoterminal Bug Report next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Mulmoterminal Bug Report compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mulmoterminal Bug Report this skillreceptron/mulmoterminal238—~1.7kAutomated safety check: PassMIT
Bug ReproducerAnastasiyaW/codex-claude-code-config154—~4.1kAutomated safety check: PassMIT
Weavebench Cua ReproduceAMAP-ML/LongHorizon-Harness1.7k—~1.6kAutomated safety check: PassMIT
Evidence-Driven Testingmichaelshimeles/skills1.3k1 repos~3.9kAutomated safety check: PassNone
Create GitHub IssueNVIDIA/OpenShell16k—~1.7kAutomated safety check: PassApache-2.0
Triage IssuesClickHouse/clickhouse-java1.6k—~904Automated safety check: PassApache-2.0

Similar skills

  • Bug Reproducer

    AnastasiyaW/codex-claude-code-config

    Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix.

    154 GitHub stars~4.1k tokensUpdated today
    Testing & QAAuto-check passed

  • Weavebench Cua Reproduce

    AMAP-ML/LongHorizon-Harness

    Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.

    1.7k GitHub stars~1.6k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

  • Evidence-Driven Testing

    michaelshimeles/skills

    Records an annotated screen recording of the agent testing an app hands-on, then posts the video and a results summary to the PR and tracker issue.

    1.3k GitHub starsUsed in 1 repo~3.9k tokens
    Testing & QAAuto-check passed

  • Create GitHub Issue

    NVIDIA/OpenShell

    Official

    Create GitHub issues using the gh CLI. An agent skill from NVIDIA/OpenShell.

    16k GitHub stars~1.7k tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Triage Issues

    ClickHouse/clickhouse-java

    Analyzes a single GitHub issue at a time. An agent skill from ClickHouse/clickhouse-java.

    1.6k GitHub stars~904 tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Gentle AI Issue Creation

    Gentleman-Programming/gentle-shell

    Create and triage GitHub issues from repository evidence. An agent skill from Gentleman-Programming/gentle-shell.

    1.3k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check passed

More from receptron/mulmoterminal

All 31 skills in this repo

  • Mulmoterminal Decisions

    receptron/mulmoterminal

    Check what this project's humans have already been asked, and how they answered, before asking them something similar.

    238 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Mulmoterminal Help

    receptron/mulmoterminal

    Help desk for questions about MulmoTerminal itself — what it can do, how a feature or a part of the screen works, how to set something up, what is new in this version or in the latest one.

    238 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Mulmoterminal Notify

    receptron/mulmoterminal

    Decide which moments MulmoTerminal beeps or pushes for, and what each one plays — soundKinds, sounds and pushKinds in ~/.mulmoterminal/config.json, plus a per-project sound / sounds in…

    238 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Mulmoterminal Theme

    receptron/mulmoterminal

    Build a colour scheme of your own for MulmoTerminal — one that joins Midnight, Nord, Daylight and Solarized in Settings' theme picker and can then be pinned per project.

    238 GitHub stars~2.5k tokensUpdated today
    Auto-check passed

  • Blueprint Ask Answer

    receptron/mulmoterminal

    Answer each question from the named documents only, quoting where the answer is written, or saying plainly that the documents do not say — changing nothing yet.

    238 GitHub stars~780 tokensUpdated today
    Auto-check passed

  • Blueprint Cloudflare Security

    receptron/mulmoterminal

    Review the finished Worker against OWASP Top 10:2025, fix what is exploitable, prove each fix with a test, and report.

    237 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check: notes

Works with

Categories

Questions about Mulmoterminal Bug Report

What does Mulmoterminal Bug Report do?

Help desk for "MulmoTerminal is broken". An agent skill from receptron/mulmoterminal. Mulmoterminal Bug Report is an agent skill from receptron/mulmoterminal. Help desk for "MulmoTerminal is broken".

When should I use Mulmoterminal Bug Report?

Mulmoterminal Bug Report fits situations like: the user says MulmoTerminal is broken / weird / not working; wants to report a bug; file an issue about it; asks why MulmoTerminal behaves the way it does.

How do I install Mulmoterminal Bug Report in Claude Code?

Run `npx skills add receptron/mulmoterminal --skill mulmoterminal-bug-report -a claude-code`. Or copy the skill folder (server/skills/mulmoterminal-bug-report in receptron/mulmoterminal) into .claude/skills/mulmoterminal-bug-report in your project. Claude Code loads it when a task matches its description.

How do I install Mulmoterminal Bug Report in Codex?

Run `npx skills add receptron/mulmoterminal --skill mulmoterminal-bug-report -a codex`. Or copy the skill folder (server/skills/mulmoterminal-bug-report in receptron/mulmoterminal) into .agents/skills/mulmoterminal-bug-report in your project. Codex loads it when a task matches its description.

Can I use Mulmoterminal Bug Report in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add receptron/mulmoterminal --skill mulmoterminal-bug-report -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mulmoterminal-bug-report, .gemini/skills/mulmoterminal-bug-report, .github/skills/mulmoterminal-bug-report and .opencode/skills/mulmoterminal-bug-report in your project.

What does Mulmoterminal Bug Report need to run?

Going by SKILL.md and its folder, Mulmoterminal Bug Report needs the command-line tools its instructions call (curl, gh, node, claude and codex).

Does Mulmoterminal Bug Report access the network?

SKILL.md contains no URLs. Its commands use curl and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Mulmoterminal Bug Report safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Mulmoterminal Bug Report use?

Mulmoterminal Bug Report is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mulmoterminal Bug Report use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mulmoterminal Bug Report?

Skills that share tags, products or a category with Mulmoterminal Bug Report: Bug Reproducer (AnastasiyaW/codex-claude-code-config, 154 stars), Weavebench Cua Reproduce (AMAP-ML/LongHorizon-Harness, 1.7k stars), Evidence-Driven Testing (michaelshimeles/skills, 1.3k stars) and Create GitHub Issue (NVIDIA/OpenShell, 16k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mulmoterminal Bug Report?

receptron (a GitHub organization) maintains it in receptron/mulmoterminal, which has 238 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 11, 2026.

Source: receptron/mulmoterminal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.