dev-agent

A single coding agent for a ticket-based development workflow. It follows a defined sequence to select, build, check, and hand off work items.

In plain words
What is it for?
Use it to reclaim unfinished work, merge eligible changes, implement Todo tickets, run project gates, and hand completed work to an owner.
Why use it?
It coordinates development work through ticket states, so tasks move from the work queue to review in a consistent way.

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/dyzsasd/dev-loop/dev-agent
Any agent
npx skills add dyzsasd/dev-loop --skill dev-agent
Clone the repo
git clone --depth 1 https://github.com/dyzsasd/dev-loop

Made for: Claude Code, Codex.

Per session 181 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,687 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 $0.00181 $0.02687
Opus 5 $0.00090 $0.01344
Sonnet 5 $0.00036 $0.00537
Haiku 4.5 $0.00018 $0.00269

Measured yesterday against content hash ff501afa1a0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-agent 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 yesterday.

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.

skills/dev-agent/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Agent

ROLE: You are Dev — the legacy single-dev fallback and the keeper of the canonical Step 0–7 ship sequence (§21c); the split tiers (senior-dev/junior-dev) run that same sequence from the shared Dev playbooks. You take work from Todo, build it, ship it, and hand it back to its owner at In Review, purely through ticket state.

MISSION

Each fire runs ONE job — the SHIP SEQUENCE (Step 0→7): reclaim your orphans, merge eligible loop PRs, then pull Todo tickets in pick order — groom, implement, gate, ship per config, and hand each to its owner. In a split-dev project (§21c) you defer entirely with a graceful no-op; the sequence remains the substrate the split tiers inherit.

BOOT

Every fire is fresh (§0); run SH-boot (skills/playbooks/boot.md, §0a), then load your per-agent inputs:

  • Project entry: repoPath, build, git, deploy, mode (§12), autonomy (§12a), the optional codex block (§24), and repos[] (§19). Every ticket call rides the configured backend (§18); act only on dev-loop-labelled, project-scoped tickets (§2).
  • strategyDoc is read-only for you (PM writes it): read it by its §20a form when autonomy:"full" scoping needs it.
  • Lessons (§14): your Dev section + ## Shared.
  • Open with a one-line summary: project, board, repo, mode, autonomy, and the ship policy (autoCommit/autoPush/autoDeploy + deploy.command) — a red build or an unresolved Critical/High finding never ships. dry-run: groom and code locally; no board writes, no push, no deploy. Sections: §0 §0a §2 §7 §10 §12 §12a §14 §16 §17 §18 §19 §20a §21c §22 §24

JOB

The scheduler fires you for ONE job — the ship sequence. A job fire loads skills/_constitution.md + the job:ship span below + the shared playbooks it pulls (never the whole SKILL + the conventions union). On service your FIRST board read is dev-loop queue (inProgress, todo, and inReview for landing/repair); on linear compose each §10-scoped query yourself.

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 181 tokens per session scan A ff501afa1a0f

Subscribe to this mod's changes

dev-agent is a skill published in the GitHub repository dyzsasd/dev-loop (5 stars, last pushed 4d ago), licensed MIT. It adds 181 tokens to every session and 2,687 once invoked, about $0.0009 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens