Agent skill

Bangle Followup Operator

Operate recurring Bangle.io agent follow-ups after a thread has already started.

AGPL-3.0Auto-check passedDevelopment

Install Bangle Followup Operator

skills CLI

$ npx skills add bangle-io/bangle-io --skill bangle-followup-operator -a claude-code

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

GitHub CLI

$ gh skill install bangle-io/bangle-io bangle-followup-operator --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/bangle-io/bangle-io.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/bangle-followup-operator .claude/skills/bangle-followup-operator && 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/

Paste into Claude Code

Install the "bangle-followup-operator" agent skill from https://github.com/bangle-io/bangle-io/tree/main/.codex/skills/bangle-followup-operator into .claude/skills/bangle-followup-operator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bangle-followup-operator", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/bangle-io/bangle-io/tree/main/.codex/skills/bangle-followup-operator

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add bangle-io/bangle-io --skill bangle-followup-operator -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install bangle-io/bangle-io bangle-followup-operator --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bangle-io/bangle-io.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/bangle-followup-operator .agents/skills/bangle-followup-operator && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "bangle-followup-operator" agent skill from https://github.com/bangle-io/bangle-io/tree/main/.codex/skills/bangle-followup-operator into .agents/skills/bangle-followup-operator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bangle-followup-operator", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add bangle-io/bangle-io --skill bangle-followup-operator -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install bangle-io/bangle-io bangle-followup-operator --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bangle-io/bangle-io.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/bangle-followup-operator .cursor/skills/bangle-followup-operator && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "bangle-followup-operator" agent skill from https://github.com/bangle-io/bangle-io/tree/main/.codex/skills/bangle-followup-operator into .cursor/skills/bangle-followup-operator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bangle-followup-operator", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/bangle-io/bangle-io.git --path .codex/skills/bangle-followup-operator

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add bangle-io/bangle-io --skill bangle-followup-operator -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install bangle-io/bangle-io bangle-followup-operator --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bangle-io/bangle-io.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/bangle-followup-operator .gemini/skills/bangle-followup-operator && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "bangle-followup-operator" agent skill from https://github.com/bangle-io/bangle-io/tree/main/.codex/skills/bangle-followup-operator into .gemini/skills/bangle-followup-operator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bangle-followup-operator", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install bangle-io/bangle-io bangle-followup-operator

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add bangle-io/bangle-io --skill bangle-followup-operator -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/bangle-io/bangle-io.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/bangle-followup-operator .github/skills/bangle-followup-operator && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "bangle-followup-operator" agent skill from https://github.com/bangle-io/bangle-io/tree/main/.codex/skills/bangle-followup-operator into .github/skills/bangle-followup-operator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bangle-followup-operator", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add bangle-io/bangle-io --skill bangle-followup-operator -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install bangle-io/bangle-io bangle-followup-operator --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bangle-io/bangle-io.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/bangle-followup-operator .opencode/skills/bangle-followup-operator && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "bangle-followup-operator" agent skill from https://github.com/bangle-io/bangle-io/tree/main/.codex/skills/bangle-followup-operator into .opencode/skills/bangle-followup-operator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bangle-followup-operator", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: bangle-followup-operator
GitHub stars: 1.2k
Token cost: ~991 tokens
SKILL.md length: 467 words
Files: 2
Skills in repo: 5
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Operate recurring Bangle.io agent follow-ups after a thread has already started.

Works in 3 steps: Read the latest prompt and recent… → Check repository state from the root:… → Infer terse prompts like continue, what…
The user asks to continue
SKILL.md covers Overview, Reconstruct State, Route the Follow-up and Close Out
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Bangle Followup Operator is an agent skill from bangle-io/bangle-io. Operate recurring Bangle.io agent follow-ups after a thread has already started. Use when the user asks to continue, check status, decide what is next, push, create or update a PR, poll CI, rebase, merge, release, run Playwright/manual UX checks, spawn or aggregate code-review subagents, run thermonuclear review, address review findings, make a plan, add a project task, or asks "we good?", "pushed?", "PR?", "did you test?", "what should I test?", or similar follow-up prompts in the Bangle repo.

Its SKILL.md is about 990 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Code review, Browser testing and Subagents. It works with Playwright. The repository describes itself as: A web only WYSIWYG note taking app that saves notes locally in markdown format. v2: https://app.bangle.io/. The licence is AGPL-3.0.

When your agent uses it

The user asks to continue
Decide what is next
Run Playwright/manual UX checks
Aggregate code-review subagents

Example prompts

“we good?”
“pushed?”
“did you test?”
“/bangle-followup-operator”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Read the latest prompt and recent conversation turns using the thread/history tools available in the current agent environment.
Check repository state from the root: branch, dirty files, remotes, active PR, recent commits, and any generated worktree context.
Infer terse prompts like continue, what next, we good, pushed?, or PR? from the immediately previous work before asking for clarification.

What it can do on your machine

Read from SKILL.md and the folder at commit c3310c5. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Bangle Followup Operator loads about 991 tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 467 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~131
When it runs · the whole SKILL.md, loaded when a task matches: ~991

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 bangle-io/bangle-io at commit c3310c5, republished under its AGPL-3.0 licence (© bangle-io). 467 words, ~991 tokens.

Download SKILL.mdSave it as .claude/skills/bangle-followup-operator/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: bangle-followup-operator
description: Operate recurring Bangle.io agent follow-ups after a thread has already started. Use when the user asks to continue, check status, decide what is next, push, create or update a PR, poll CI, rebase, merge, release, run Playwright/manual UX checks, spawn or aggregate code-review subagents, run thermonuclear review, address review findings, make a plan, add a project task, or asks "we good?", "pushed?", "PR?", "did you test?", "what should I test?", or similar follow-up prompts in the Bangle repo.

Bangle Follow-up Operator

Overview

Use this skill to convert short Bangle follow-ups into the next concrete action. Keep repository-wide engineering policy in AGENTS.md/CLAUDE.md; keep plan-specific policy in plans/AGENTS.md.

Reconstruct State

Read the latest prompt and recent conversation turns using the thread/history tools available in the current agent environment.
Check repository state from the root: branch, dirty files, remotes, active PR, recent commits, and any generated worktree context.
Infer terse prompts like continue, what next, we good, pushed?, or PR? from the immediately previous work before asking for clarification.

Route the Follow-up

Continue or status

Inspect unfinished commands, partial edits, unpushed commits, failed checks, and PR/CI state.
Report exact current state, then continue the next unfinished step.

Review or subagent request

For thermonuclear review, use the thermonuclear-code-quality-review skill.
For normal review or subagent review, pass raw scope: repo path, branch/PR, diff target, constraints, and whether the agent may edit.
Aggregate findings into must fix, worth fixing, and defer/track.

Address findings or "do it"

Re-read the cited code and tests before editing.
Implement only fixes that match the user's scope and improve the branch.
Prefer changes that reduce total uncertainty and complexity. Type and lint cleanup has strong ROI when it clarifies a real boundary, improves useful caller inference, or makes an invalid state unrepresentable. Reconsider it when satisfying the rule adds conditional type machinery, assertions, or downstream churn without a concrete new guarantee. Type-level wildcards and runtime boundary leaks can look similar in a scan but have different risk; judge the resulting API and implementation, not the warning count alone.
After edits, run focused checks first, then the required AGENTS.md gates for the changed surface.

Show full SKILL.md (190 more words)Show less

UI, UX, or Playwright follow-up

Use playwright-cli, browser, or Chrome tools when the user asks for manual UX validation, screenshots, authenticated Chrome, or visual comparison.
If the user points at production, t3code, prosekit, or another local reference, inspect that reference before claiming parity.

PR, git, CI, and deploy follow-up

Before push/PR/merge/release, verify branch, remote, dirty state, and target PR.
After push, provide the PR URL or branch and poll relevant GitHub checks when requested.
For Cloudflare preview or GitHub Action comments, verify whether displayed commit hashes are PR head SHAs, merge SHAs, or deployment branch SHAs before patching.
For releases, use the applicable Bangle release skill and AGENTS.md release gates.

Planning or project task

For durable plans under plans/, read plans/AGENTS.md first.
For adding, updating, triaging, scheduling, or reconciling Bangle project items, use bangle-project-operator.
When a plan is fully done, move it to plans/archived/, set status: completed, set archived: true, set archived_on: YYYY-MM-DD in the YAML frontmatter, update updated, and include the DONE note required by plans/AGENTS.md.

Close Out

State what changed or what was found.
Include branch/PR/push/CI status when relevant.
Include checks run and any checks intentionally not run.

Files

SKILL.md and 1 other file in .codex/skills/bangle-followup-operator of bangle-io/bangle-io.

SKILL.md
agents/openai.yaml

Open the folder on GitHubat commit c3310c5

Compare with similar skills

Bangle Followup Operator 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.

Bangle Followup Operator compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Bangle Followup Operator this skillbangle-io/bangle-io	1.2k	—	~991	Automated safety check: Pass	AGPL-3.0	3 days ago
QAKiln-AI/Kiln	5.2k	—	~3.6k	Automated safety check: Pass	Custom licence	yesterday
Code Reviewnteract/semiotic	2.7k	—	~1.5k	Automated safety check: Pass	Apache-2.0	2 days ago
Playwright Java QA ReviewTahanima/playwright-java-test-automation-architecture	113	—	~561	Automated safety check: Pass	MIT	7 mo ago
Verifier SetupAI-Builder-Club/skills	1.3k	—	~2.1k	Automated safety check: Pass	None	23 days ago
Review And Fixhmislk/hmis	236	—	~4.9k	Automated safety check: Pass	GPL-3.0	today

Similar skills

QA
Kiln-AI/Kiln
Multi-agent, browser-driven QA pass over a branch or PR — scope it, plan it, fan out one subagent per testing area in its own isolated sandbox, compile a severity-ranked markdown report.
5.2k GitHub stars~3.6k tokensUpdated yesterday
Testing & QAAuto-check passed
Code Review
nteract/semiotic
Review Semiotic pull requests for behavioral bugs, regressions, contract drift, and missing evidence.
2.7k GitHub stars~1.5k tokensUpdated 2 days ago
DevelopmentAuto-check passed
Playwright Java QA Review
Tahanima/playwright-java-test-automation-architecture
Reviews Playwright-Java test code in phases, checking page-object architecture, then using a Playwright MCP tool to verify shaky locators live.
113 GitHub stars~561 tokensUpdated 7 mo ago
Testing & QAAuto-check passed
Verifier Setup
AI-Builder-Club/skills
Set a repo up to prove engineering-task work actually works before it ships.
1.3k GitHub stars~2.1k tokensUpdated 23 days ago
Testing & QAAuto-check passed
Review And Fix
hmislk/hmis
Deep-review one open PR, apply the resulting fixes, verify each one live (build → local redeploy → Playwright + DB), commit, push, drive CI to green, then reply to the review threads.
236 GitHub stars~4.9k tokensUpdated today
Testing & QAAuto-check passed
E Tax
kazukinagata/shinkoku
This skill should be used when the user wants to file their tax return electronically via the 確定申告書等作成コーナー (NTA Tax Return Preparation Corner) using Claude in Chrome, Antigravity Browser Sub-Agent…
364 GitHub stars~9.1k tokensUpdated 29 days ago
Business, Finance & HRAuto-check passed

More from bangle-io/bangle-io

Bangle Project Operator
bangle-io/bangle-io
Keep the Bangle 2 GitHub Project aligned with the bangle-io repository.
1.2k GitHub stars~1.4k tokensUpdated 3 days ago
Auto-check passed
Wordgard
bangle-io/bangle-io
Write idiomatic Wordgard editor code (schema elements, extensions, commands, decorations, markdown specs) for the editor-w stack.
1.2k GitHub stars~1.5k tokensUpdated 3 days ago
Auto-check passed
Bangle Desktop Release
bangle-io/bangle-io
Build, test, package, and release the Bangle.io Electron desktop app.
1.2k GitHub stars~297 tokensUpdated 3 days ago
Auto-check passed
Thermonuclear Code Quality Review
bangle-io/bangle-io
Perform an unusually strict code-quality audit focused on structural simplification, maintainability, abstraction quality, file growth, branching complexity, type boundaries, architectural…
1.2k GitHub stars~1.4k tokensUpdated 3 days ago
Auto-check passed

Works with

Playwright

Questions about Bangle Followup Operator

What does Bangle Followup Operator do?

Operate recurring Bangle.io agent follow-ups after a thread has already started. Bangle Followup Operator is an agent skill from bangle-io/bangle-io.io agent follow-ups after a thread has already started.

When should I use Bangle Followup Operator?

Bangle Followup Operator fits situations like: the user asks to continue; decide what is next; run Playwright/manual UX checks; aggregate code-review subagents.

How do I install Bangle Followup Operator in Claude Code?

Run `npx skills add bangle-io/bangle-io --skill bangle-followup-operator -a claude-code`. Or copy the skill folder (.codex/skills/bangle-followup-operator in bangle-io/bangle-io) into .claude/skills/bangle-followup-operator in your project. Claude Code loads it when a task matches its description.

How do I install Bangle Followup Operator in Codex?

Run `npx skills add bangle-io/bangle-io --skill bangle-followup-operator -a codex`. Or copy the skill folder (.codex/skills/bangle-followup-operator in bangle-io/bangle-io) into .agents/skills/bangle-followup-operator in your project. Codex loads it when a task matches its description.

Can I use Bangle Followup Operator 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 bangle-io/bangle-io --skill bangle-followup-operator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bangle-followup-operator, .gemini/skills/bangle-followup-operator, .github/skills/bangle-followup-operator and .opencode/skills/bangle-followup-operator in your project.

What does Bangle Followup Operator need to run?

SKILL.md names no scripts, command-line tools or credentials: Bangle Followup Operator is instructions for the agent only.

Does Bangle Followup Operator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bangle Followup Operator 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 Bangle Followup Operator use?

Bangle Followup Operator is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bangle Followup Operator use?

About 991 tokens (SKILL.md is roughly 4k 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 Bangle Followup Operator?

Skills that share tags, products or a category with Bangle Followup Operator: QA (Kiln-AI/Kiln, 5.2k stars), Code Review (nteract/semiotic, 2.7k stars), Playwright Java QA Review (Tahanima/playwright-java-test-automation-architecture, 113 stars) and Verifier Setup (AI-Builder-Club/skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bangle Followup Operator?

bangle-io (a GitHub organization) maintains it in bangle-io/bangle-io, which has 1,233 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 5, 2026.

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

Install Bangle Followup Operator

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Bangle Follow-up Operator

Overview

Reconstruct State

Route the Follow-up

Continue or status

Review or subagent request

Address findings or "do it"

UI, UX, or Playwright follow-up

PR, git, CI, and deploy follow-up

Planning or project task

Close Out

Files

Compare with similar skills

Similar skills

More from bangle-io/bangle-io

Related

Questions about Bangle Followup Operator