CodingAgent

A coordinator for running multiple coding agents at the same time, with separate working copies of a code repository. tmux keeps command-line sessions running, while worktrees isolate each agent’s changes.

In plain words
What is it for?
Use it to assign separate bugs or features to parallel agents, monitor their sessions, and gather their completed changes.
Why use it?
It lets several independent issues be worked on concurrently without mixing their files or terminal sessions. It also provides workflows for checking progress and collecting results.

Skill for Claude CodeCodex

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 skills/carbeneai/forge/codingagent
Any agent
npx skills add CarbeneAI/Forge --skill codingagent
Clone the repo
git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,166 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 $0.00057 $0.01166
Opus 5 $0.00028 $0.00583
Sonnet 5 $0.00011 $0.00233
Haiku 4.5 $0.00006 $0.00117

Measured 2d ago against content hash c6190b5ab229, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CodingAgent 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 2d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (tools/AgentLauncher.ts, tools/Manage.sh, tools/SessionManager.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/CodingAgent/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodingAgent

Orchestrate multiple parallel coding agents using tmux sessions for PTY support and git worktrees for isolated development environments.

Workflow Routing

When executing a workflow, call the notification script via Bash:

${PAI_DIR}/tools/skill-workflow-notification WorkflowName CodingAgent
Workflow Trigger File
SpawnAgents "spawn agents", "fix these issues", "parallel coding" workflows/SpawnAgents.md
MonitorSessions "check agents", "monitor progress", "session status" workflows/MonitorSessions.md
CollectResults "gather results", "agents done", "merge work" workflows/CollectResults.md

Examples

Example 1: Fix multiple GitHub issues in parallel

User: "Fix issues #123, #124, and #125 in parallel"
→ Invokes SpawnAgents workflow
→ Creates git worktrees for each issue
→ Spawns tmux sessions with Claude Code agents
→ Each agent works on one issue independently
→ Notifies via Telegram when complete

Example 2: Check progress on parallel agents

User: "How are my coding agents doing?"
→ Invokes MonitorSessions workflow
→ Lists active pai-agent-* tmux sessions
→ Captures recent output from each
→ Reports status and progress

Example 3: Collect finished work

User: "Gather the results from all agents"
→ Invokes CollectResults workflow
→ Checks which agents have completed
→ Summarizes changes per worktree
→ Provides merge instructions

Key Concepts

Why tmux?

Claude Code requires a pseudo-terminal (PTY) for interactive features. tmux provides:

  • PTY allocation - Full terminal emulation for Claude Code
  • Session persistence - Agents continue running if connection drops
  • Output capture - Retrieve agent output without interrupting
  • Parallel execution - Multiple independent sessions

Socket Isolation

All PAI agent sessions use a dedicated socket:

SOCKET="${TMPDIR:-/tmp}/pai-agents.sock"

Read the full file on GitHub · 166 lines

Files

What ships with it

9 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.

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. 2d ago First seen · 166 lines · 57 tokens per session scan A c6190b5ab229

Subscribe to this mod's changes

CodingAgent is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 1,166 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

pentesting-everything

Guides authorized penetration testing with PentestingEverything as the source-grounded knowledge base. Use when scoping an engagement, building domain checklists, hunting a vulnerability class, choosing tools/commands, or drafting evidence-based findings from this repository's Markdown.

m14r41/PentestingEverything · 56 tokens

implementing-devsecops-security-scanning

Integrates Static Application Security Testing (SAST), Dynamic Application Security Testing (DAST), and Software Composition Analysis (SCA) into CI/CD pipelines using open-source tools. Covers Semgrep for SAST, Trivy for SCA and container scanning, OWASP ZAP for DAST, and Gitleaks for secrets detection. Activates for…

xalgorix/xalgorix · 109 tokens

hunt-ato

Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session…

Zyrexnn/Cybermes · 241 tokens

aod-orchestrate

Multi-feature orchestration skill that bridges /aod.blueprint output to parallel wave execution. Groups synced GitHub Issues by ICE priority tier (P0/P1/P2) into sequential waves, creates Task records, spawns batch sessions via the orchestrator API, monitors completion, and reports results. Supports --issues…

davidmatousek/tachi · 110 tokens

security

Claude-powered SAST and SCA security scan skill. Invoked automatically as the Security Scan step (Step 7) of /aod.build (after Design Quality Gate, before Code Simplification) or standalone via /security. Analyzes all code files and dependency manifests changed on the feature branch relative to main for OWASP Top 10…

davidmatousek/tachi · 165 tokens

aod-foundation

Guided post-init workshop that helps new AOD Kit adopters establish product vision and design identity. Two-part flow: Part 1 (Vision) asks 5 guided questions to populate product-vision.md; Part 2 (Design) browses archetypes to generate brand files (brand.md, tokens.css, anti-patterns.md). Supports --vision and…

davidmatousek/tachi · 98 tokens