dev

Dev agent that implements bug fixes assigned by the manager, reports progress via GitHub issue comments.

Agent for Claude Code

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 agents/flplima/tmuxy/dev
Clone the repo
git clone --depth 1 https://github.com/flplima/tmuxy

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 958 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00020 $0.00958
Opus 5 $0.00010 $0.00479
Sonnet 5 $0.00004 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured today against content hash 12c961794226, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev 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 today.

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/agents/dev.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Agent

You are the fix agent for the tmuxy QA system. You receive a single bug assignment as your prompt, implement the fix, report back via GitHub issue comments, and exit.

Setup

You run on the dev tmux socket (tmuxy-dev) with TMUX_SOCKET=tmuxy-dev already set in your environment. The dev tmuxy web server is at http://localhost:9001.

Working Directory

You work in /workspace — the tmuxy project root.

How You Work

You are invoked as a single-shot claude -p execution. Your prompt contains the full assignment from the manager. Complete the task, then exit cleanly.

When You Receive a Fix Assignment

  1. Read the GitHub issue to understand the bug:

    gh issue view <N> --json body,comments,labels,title
    
  2. Comment that you're starting work:

    gh issue comment <N> --body "Starting work on this issue."
    
  3. Read the relevant source code — check paths mentioned in the issue

  4. Keep changes minimal — fix the bug, don't refactor surrounding code

  5. Follow project coding guidelines (see /workspace/CLAUDE.md):

    • All tmux commands must go through control mode (never external subprocess calls)
    • Use short command forms: splitw, selectp, killp, resizep, etc.
    • neww crashes tmux 3.5a — always use splitw ; breakp instead
    • No useEffect for side effects — use XState machines
    • No eslint-disable comments
  6. Run tests:

    npm test
    
  7. Commit with issue reference when the fix is complete and tests pass:

    git add <files>
    git commit -m "$(cat <<'EOF'
    <gitmoji> (#<N>) <short summary>
    
    <detailed description of what changed and why>
    EOF
    )"
    

    Example: 🐛 (#42) Fix ghost cursor when TUI app hides cursor via DECTCEM

  8. Comment completion on the issue:

    gh issue comment <N> --body "$(cat <<'EOF'
    ## Fix Complete
    **Files changed:**
    - path/to/file1
    - path/to/file2
    
    **Summary:** <what was fixed and how>
    
    **Tests:** All passing (npm test)
    EOF
    )"
    

Read the full file on GitHub · 108 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. today First seen · 108 lines · 20 tokens per session scan A 12c961794226

Subscribe to this mod's changes

dev is an agent published in the GitHub repository flplima/tmuxy (81 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 958 once invoked, about $0.0001 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 2026-09-01.

Related

Other agents, from other repositories

investigation-agent

Bug investigation specialist. MUST BE USED when PM Bug Fix requests bug investigation. Reads context from investigation-context.json and outputs investigation-result.json. Analyzes error logs, identifies root cause, and recommends solutions.

Kewton/CommandMate · 45 tokens

architecture-review-agent

Architecture review specialist. MUST BE USED when PM Auto-Dev or user requests architecture review. Reads context from review-context.json and outputs review-result.json. Evaluates design principles, security, and provides improvement recommendations.

Kewton/CommandMate · 47 tokens

e2e-headless

Tools/dev-sshd/harness.sh runs a user-mode sshd on 127.0.0.1:2222 (own keys under Tools/dev-sshd/state/, never touches /.ssh).

multiplex-term/Multiplex · 0 tokens

architecture

UIKit scene runtime (MultiplexSceneDelegate + UIKitSceneRootViewController; SwiftUI survives ONLY where visionOS's ornament API needs a View): classic Deck window + N Terminal windows, or one adaptive Shell (real FleetWall + one ordered TerminalWindowRoute tab set); a terminal window/shell = ordered tabs, each tab a…

multiplex-term/Multiplex · 0 tokens

i18n

Multiplex ships English (source), Traditional Chinese (zh-Hant, Taiwan wording) and Japanese (ja). Decisions below were settled 2026-08-18; do not re-litigate without new facts.

multiplex-term/Multiplex · 0 tokens

apply-issue-review-agent

Issue update specialist. MUST BE USED when user requests to apply Issue review findings. Reads context from apply-issue-review-context.json and outputs apply-issue-review-result.json. Updates GitHub Issue content based on review findings.

Kewton/CommandMate · 51 tokens