Agent skill

Coding Agent

by TermiX-official in TermiX-official/cryptoclaw

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process.

MITAuto-check passedDevelopment

Install Coding Agent

skills CLI
$ npx skills add TermiX-official/cryptoclaw --skill coding-agent -a claude-code

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

GitHub CLI
$ gh skill install TermiX-official/cryptoclaw coding-agent --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/TermiX-official/cryptoclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/coding-agent .claude/skills/coding-agent && 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
coding-agent
GitHub stars
100
Used in
8 other repos
Token cost
~2.7k tokens
SKILL.md length
699 words
Files
1
Skills in repo
34
Repo updated
First seen
Licence
MIT

At a glance

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process.

  • Works in 9 steps: Always use pty:true - coding agents need… → Respect tool choice - if user asks for… → Be patient - don't kill sessions because… → …
  • Building/creating new features
  • SKILL.md covers ⚠️ PTY Mode Required!, Quick Start: One-Shot Tasks, The Pattern: workdir +… and Codex CLI, plus 8 more sections
  • Calls bash, git and codex; reaches github.com

What it does

Coding Agent is an agent skill from TermiX-official/cryptoclaw. Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessionsspawn with runtime:"acp"), or any work in ~/clawd workspace (never…

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Refactoring. It works with Bash and Discord. The licence is MIT.

When your agent uses it

  • Building/creating new features
  • Reviewing PRs (spawn in temp dir)
  • Refactoring large codebases
  • Iterative coding that needs file exploration

Example prompts

  • “/coding-agent”

Requirements

  • Node.js

Workflow steps

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

  1. Always use pty:true - coding agents need a terminal!
  2. Respect tool choice - if user asks for Codex, use Codex.
  3. Be patient - don't kill sessions because they're "slow"
  4. Monitor with process:log - check progress without interfering
  5. full-auto for building - auto-approves changes
  6. vanilla for reviewing - no special flags needed
  7. Parallel is OK - run many Codex processes at once for batch work
  8. NEVER start Codex in ~/.openclaw/ - it'll read your soul docs and get weird ideas about the org chart!
  9. NEVER checkout branches in ~/Projects/openclaw/ - that's the LIVE OpenClaw instance!

What it can do on your machine

Read from SKILL.md and the folder at commit 9e1c91b. 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:

    • bash
    • git
    • codex
    • gh

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    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

Coding Agent loads about 2.7k tokens when it runs. Until then it costs about 149 tokens; SKILL.md has 699 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~149
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

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 TermiX-official/cryptoclaw at commit 9e1c91b, republished under its MIT licence (© TermiX-official). 699 words, ~2,663 tokens.

Download SKILL.mdSave it as .claude/skills/coding-agent/SKILL.md (or your agent's skills folder).
name
coding-agent
description
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Requires a bash tool that supports pty:true.

Coding Agent (bash-first)

Use bash (with optional background mode) for all coding agent work. Simple and effective.

⚠️ PTY Mode Required!

Coding agents (Codex, Claude Code, Pi) are interactive terminal applications that need a pseudo-terminal (PTY) to work correctly. Without PTY, you'll get broken output, missing colors, or the agent may hang.

Always use pty:true when running coding agents:

bash
# ✅ Correct - with PTY
bash pty:true command:"codex exec 'Your prompt'"

# ❌ Wrong - no PTY, agent may break
bash command:"codex exec 'Your prompt'"
Bash Tool Parameters
ParameterTypeDescription
commandstringThe shell command to run
ptybooleanUse for coding agents! Allocates a pseudo-terminal for interactive CLIs
workdirstringWorking directory (agent sees only this folder's context)
backgroundbooleanRun in background, returns sessionId for monitoring
timeoutnumberTimeout in seconds (kills process on expiry)
elevatedbooleanRun on host instead of sandbox (if allowed)
Process Tool Actions (for background sessions)
ActionDescription
listList all running/recent sessions
pollCheck if session is still running
logGet session output (with optional offset/limit)
writeSend raw data to stdin
submitSend data + newline (like typing and pressing Enter)
send-keysSend key tokens or hex bytes
pastePaste text (with optional bracketed mode)
killTerminate the session

Quick Start: One-Shot Tasks

For quick prompts/chats, create a temp git repo and run:

bash
# Quick chat (Codex needs a git repo!)
SCRATCH=$(mktemp -d) && cd $SCRATCH && git init && codex exec "Your prompt here"

# Or in a real project - with PTY!
bash pty:true workdir:~/Projects/myproject command:"codex exec 'Add error handling to the API calls'"

Why git init? Codex refuses to run outside a trusted git directory. Creating a temp repo solves this for scratch work.


The Pattern: workdir + background + pty

For longer tasks, use background mode with PTY:

bash
# Start agent in target directory (with PTY!)
bash pty:true workdir:~/project background:true command:"codex exec --full-auto 'Build a snake game'"
# Returns sessionId for tracking

# Monitor progress
process action:log sessionId:XXX

# Check if done
process action:poll sessionId:XXX

# Send input (if agent asks a question)
process action:write sessionId:XXX data:"y"

# Submit with Enter (like typing "yes" and pressing Enter)
process action:submit sessionId:XXX data:"yes"

# Kill if needed
process action:kill sessionId:XXX

Why workdir matters: Agent wakes up in a focused directory, doesn't wander off reading unrelated files (like your soul.md 😅).


Codex CLI

Model: gpt-5.2-codex is the default (set in ~/.codex/config.toml)

Flags
FlagEffect
exec "prompt"One-shot execution, exits when done
--full-autoSandboxed but auto-approves in workspace
--yoloNO sandbox, NO approvals (fastest, most dangerous)
Building/Creating
bash
# Quick one-shot (auto-approves) - remember PTY!
bash pty:true workdir:~/project command:"codex exec --full-auto 'Build a dark mode toggle'"

# Background for longer work
bash pty:true workdir:~/project background:true command:"codex --yolo 'Refactor the auth module'"
Reviewing PRs

⚠️ CRITICAL: Never review PRs in OpenClaw's own project folder! Clone to temp folder or use git worktree.

bash
# Clone to temp for safe review
REVIEW_DIR=$(mktemp -d)
git clone https://github.com/user/repo.git $REVIEW_DIR
cd $REVIEW_DIR && gh pr checkout 130
bash pty:true workdir:$REVIEW_DIR command:"codex review --base origin/main"
# Clean up after: trash $REVIEW_DIR

# Or use git worktree (keeps main intact)
git worktree add /tmp/pr-130-review pr-130-branch
bash pty:true workdir:/tmp/pr-130-review command:"codex review --base main"
Batch PR Reviews (parallel army!)
bash
# Fetch all PR refs first
git fetch origin '+refs/pull/*/head:refs/remotes/origin/pr/*'

# Deploy the army - one Codex per PR (all with PTY!)
bash pty:true workdir:~/project background:true command:"codex exec 'Review PR #86. git diff origin/main...origin/pr/86'"
bash pty:true workdir:~/project background:true command:"codex exec 'Review PR #87. git diff origin/main...origin/pr/87'"

# Monitor all
process action:list

# Post results to GitHub
gh pr comment <PR#> --body "<review content>"

Claude Code

bash
# With PTY for proper terminal output
bash pty:true workdir:~/project command:"claude 'Your task'"

# Background
bash pty:true workdir:~/project background:true command:"claude 'Your task'"

OpenCode

bash
bash pty:true workdir:~/project command:"opencode run 'Your task'"

Pi Coding Agent

bash
# Install: npm install -g @mariozechner/pi-coding-agent
bash pty:true workdir:~/project command:"pi 'Your task'"

# Non-interactive mode (PTY still recommended)
bash pty:true command:"pi -p 'Summarize src/'"

# Different provider/model
bash pty:true command:"pi --provider openai --model gpt-4o-mini -p 'Your task'"

Note: Pi now has Anthropic prompt caching enabled (PR #584, merged Jan 2026)!


Parallel Issue Fixing with git worktrees

For fixing multiple issues in parallel, use git worktrees:

bash
# 1. Create worktrees for each issue
git worktree add -b fix/issue-78 /tmp/issue-78 main
git worktree add -b fix/issue-99 /tmp/issue-99 main

# 2. Launch Codex in each (background + PTY!)
bash pty:true workdir:/tmp/issue-78 background:true command:"pnpm install && codex --yolo 'Fix issue #78: <description>. Commit and push.'"
bash pty:true workdir:/tmp/issue-99 background:true command:"pnpm install && codex --yolo 'Fix issue #99 from the approved ticket summary. Implement only the in-scope edits and commit after review.'"

# 3. Monitor progress
process action:list
process action:log sessionId:XXX

# 4. Create PRs after fixes
cd /tmp/issue-78 && git push -u origin fix/issue-78
gh pr create --repo user/repo --head fix/issue-78 --title "fix: ..." --body "..."

# 5. Cleanup
git worktree remove /tmp/issue-78
git worktree remove /tmp/issue-99

⚠️ Rules

  1. Always use pty:true - coding agents need a terminal!
  2. Respect tool choice - if user asks for Codex, use Codex.
    • Orchestrator mode: do NOT hand-code patches yourself.
    • If an agent fails/hangs, respawn it or ask the user for direction, but don't silently take over.
  3. Be patient - don't kill sessions because they're "slow"
  4. Monitor with process:log - check progress without interfering
  5. --full-auto for building - auto-approves changes
  6. vanilla for reviewing - no special flags needed
  7. Parallel is OK - run many Codex processes at once for batch work
  8. NEVER start Codex in ~/.openclaw/ - it'll read your soul docs and get weird ideas about the org chart!
  9. NEVER checkout branches in ~/Projects/openclaw/ - that's the LIVE OpenClaw instance!

Show full SKILL.md (239 more words)Show less

Progress Updates (Critical)

When you spawn coding agents in the background, keep the user in the loop.

  • Send 1 short message when you start (what's running + where).
  • Then only update again when something changes:
    • a milestone completes (build finished, tests passed)
    • the agent asks a question / needs input
    • you hit an error or need user action
    • the agent finishes (include what changed + where)
  • If you kill a session, immediately say you killed it and why.

This prevents the user from seeing only "Agent failed before reply" and having no idea what happened.


Auto-Notify on Completion

For long-running background tasks, append a wake trigger to your prompt so OpenClaw gets notified immediately when the agent finishes (instead of waiting for the next heartbeat):

... your task here.

When completely finished, run this command to notify me:
openclaw system event --text "Done: [brief summary of what was built]" --mode now

Example:

bash
bash pty:true workdir:~/project background:true command:"codex --yolo exec 'Build a REST API for todos.

When completely finished, run: openclaw system event --text \"Done: Built todos REST API with CRUD endpoints\" --mode now'"

This triggers an immediate wake event — Skippy gets pinged in seconds, not 10 minutes.


Learnings (Jan 2026)

  • PTY is essential: Coding agents are interactive terminal apps. Without pty:true, output breaks or agent hangs.
  • Git repo required: Codex won't run outside a git directory. Use mktemp -d && git init for scratch work.
  • exec is your friend: codex exec "prompt" runs and exits cleanly - perfect for one-shots.
  • submit vs write: Use submit to send input + Enter, write for raw data without newline.
  • Sass works: Codex responds well to playful prompts. Asked it to write a haiku about being second fiddle to a space lobster, got: "Second chair, I code / Space lobster sets the tempo / Keys glow, I follow" 🦞

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

Files

Just SKILL.md in skills/coding-agent of TermiX-official/cryptoclaw.

Open the folder on GitHubat commit 9e1c91b

Used in 8 other repositories

We found 11 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 8 other GitHub owners. This page covers the copy in TermiX-official/cryptoclaw, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Coding Agent 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.

Coding Agent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Coding Agent this skillTermiX-official/cryptoclaw1008 repos~2.7kAutomated safety check: PassMIT
FIXME Resolvertailcallhq/forgecode7.6k—~1.1kAutomated safety check: PassApache-2.0
GolangJanDeDobbeleer/oh-my-posh24k—~4.3kAutomated safety check: PassMIT
Code ChangesJanDeDobbeleer/oh-my-posh24k—~1.2kAutomated safety check: PassMIT
Scope Disciplinetiramisulabs/seyfert321—~632Automated safety check: PassMIT
Writing Bash Scriptsarchibate/dotfiles-opencode107—~413Automated safety check: PassNone

Similar skills

  • FIXME Resolver

    tailcallhq/forgecode

    Finds every FIXME comment in a codebase, groups related ones across files into one task, implements the work they describe and removes the comments once it is done.

    7.6k GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Golang

    JanDeDobbeleer/oh-my-posh

    Go coding standards and conventions for this project. An agent skill from JanDeDobbeleer/oh-my-posh.

    24k GitHub stars~4.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Code Changes

    JanDeDobbeleer/oh-my-posh

    Orchestration workflow for any task that ends in code changes: issue analysis, pull request review, feature implementation, bug fixes, refactors, or fleshing out an idea.

    24k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Scope Discipline

    tiramisulabs/seyfert

    Prevent scope creep when a plan or implementation starts absorbing adjacent fixes, speculative compatibility work, migrations, or unrelated refactors.

    321 GitHub stars~632 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Writing Bash Scripts

    archibate/dotfiles-opencode

    Create and refactor Bash scripts following conventions (strict mode, fct naming, quoting).

    107 GitHub stars~413 tokensUpdated 5 mo ago
    DevelopmentAuto-check passed
  • Finalize

    zifeo/lade

    Finalize a merge request: rebase onto main, run bugs, simplify, and specs in parallel, apply, then refactor last.

    133 GitHub stars~1k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from TermiX-official/cryptoclaw

All 34 skills in this repo
  • Prose

    TermiX-official/cryptoclaw

    OpenProse VM skill pack. An agent skill from TermiX-official/cryptoclaw.

    100 GitHub starsUsed in 3 repos~3.8k tokens
    Auto-check: notes
  • Merge PR

    TermiX-official/cryptoclaw

    Merge a GitHub PR via squash after /preparepr. An agent skill from TermiX-official/cryptoclaw.

    100 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Acp Router

    TermiX-official/cryptoclaw

    Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow).

    100 GitHub starsUsed in 2 repos~1.9k tokens
    Auto-check passed
  • Review PR

    TermiX-official/cryptoclaw

    Review-only GitHub pull request analysis with the gh CLI. An agent skill from TermiX-official/cryptoclaw.

    100 GitHub stars~1.7k tokensUpdated 4 mo ago
    Auto-check passed
  • Coingecko

    TermiX-official/cryptoclaw

    Query CoinGecko API for prices, market data, trending tokens, and historical charts.

    100 GitHub starsUsed in 1 repo~755 tokens
    Auto-check passed
  • Debank

    TermiX-official/cryptoclaw

    Query DeBank OpenAPI for wallet portfolios, token holdings, DeFi positions, and transaction history.

    100 GitHub starsUsed in 1 repo~889 tokens
    Auto-check passed

Works with

Categories

Questions about Coding Agent

What does Coding Agent do?

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Coding Agent is an agent skill from TermiX-official/cryptoclaw. Delegate coding tasks to Codex, Claude Code, or Pi agents via background process.

When should I use Coding Agent?

Coding Agent fits situations like: building/creating new features; reviewing PRs (spawn in temp dir); refactoring large codebases; iterative coding that needs file exploration.

How do I install Coding Agent in Claude Code?

Run `npx skills add TermiX-official/cryptoclaw --skill coding-agent -a claude-code`. Or copy the skill folder (skills/coding-agent in TermiX-official/cryptoclaw) into .claude/skills/coding-agent in your project. Claude Code loads it when a task matches its description.

How do I install Coding Agent in Codex?

Run `npx skills add TermiX-official/cryptoclaw --skill coding-agent -a codex`. Or copy the skill folder (skills/coding-agent in TermiX-official/cryptoclaw) into .agents/skills/coding-agent in your project. Codex loads it when a task matches its description.

Can I use Coding Agent 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 TermiX-official/cryptoclaw --skill coding-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/coding-agent, .gemini/skills/coding-agent, .github/skills/coding-agent and .opencode/skills/coding-agent in your project.

What does Coding Agent need to run?

Going by SKILL.md and its folder, Coding Agent needs the command-line tools its instructions call (bash, git, codex and gh). Our summary lists: Node.js.

Does Coding Agent access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Coding Agent 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 Coding Agent use?

Coding Agent 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 Coding Agent use?

About 2.7k tokens (SKILL.md is roughly 11k 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 Coding Agent?

Skills that share tags, products or a category with Coding Agent: FIXME Resolver (tailcallhq/forgecode, 7.6k stars), Golang (JanDeDobbeleer/oh-my-posh, 24k stars), Code Changes (JanDeDobbeleer/oh-my-posh, 24k stars) and Scope Discipline (tiramisulabs/seyfert, 321 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Coding Agent?

TermiX-official (a GitHub organization) maintains it in TermiX-official/cryptoclaw, which has 100 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on May 25, 2026.

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