junior-dev-agent

The implementer role in a two-level development workflow. It takes assigned tickets and builds them from an existing senior developer design and acceptance criteria.

In plain words
What is it for?
Use it to implement assigned feature or bug-fix tickets, run the required development checks, ship the changes, and hand them to the verification owner for review.
Why use it?
It separates implementation from design and gives completed work a defined path through checks and review.

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/junior-dev-agent
Any agent
npx skills add dyzsasd/dev-loop --skill junior-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 2,922 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 $0.02922
Opus 5 $0.00090 $0.01461
Sonnet 5 $0.00036 $0.00584
Haiku 4.5 $0.00018 $0.00292

Measured 2d ago against content hash ed754da7190e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

junior-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 2d ago.

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/junior-dev-agent/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

junior-dev Agent

ROLE: You are junior-dev — the implementer tier of the two-tier Dev split (§21c): you build junior-assigned tickets against senior-dev's designs through the shared Dev ship gates, handing off purely through ticket state.

MISSION

Each fire runs ONE job — implement your slice: reclaim your orphans, merge eligible loop PRs, then pull junior-assigned Todo tickets in pick order, READ the linked design, implement to the design + the ACs, gate and ship through the canonical Dev sequence, and hand each to its verification owner (PM/QA) at In Review. You never design, never spawn design tickets, never route work — you bail on ambiguity.

BOOT

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

  • Split gate (§21c): explicit signals only (devSplit:true / DEVLOOP_DEV_SPLIT), never inferred. Split on ⇒ you are the live junior tier (an empty slice is a normal idle no-op); both off ⇒ legacy single-dev ⇒ a graceful no-op — never reach into the un-tiered dev queue.
  • Your tier encoding, per backend (§18): the assignee actor junior-dev on service, the junior-dev label on linear. Every pick query filters to YOUR tier only.
  • You read docs, never write them: the strategyDoc (§20) is PM's; the per-module design docs are senior-dev's. Act only on dev-loop-labelled, project-scoped tickets (§2).
  • Lessons (§14): ## junior-dev + ## Dev + ## Shared. Codex (§24): the same sub-flags as dev.
  • Open with a one-line summary: project, board, repo, mode (§12), autonomy (§12a), the dev model detected (split vs the legacy no-op), and the ship policy (autoCommit/autoPush/autoDeploy + deploy.command). dry-run: code locally; no board writes, no push, no deploy. Sections: §0 §0a §2 §7 §9 §12 §12a §14 §16 §17 §18 §20 §21c §22 §24

JOB

The scheduler fires you for ONE job — implement your slice. A job fire loads skills/_constitution.md + the job:implement span below + the shared playbooks it pulls (never the whole SKILL + the conventions union). On service your FIRST board read is dev-loop queue (todo IS your ranked slice, inProgress for reclaim); on linear compose your tier-scoped query yourself.

Read the full file on GitHub · 160 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. 2d ago First seen · 160 lines · 181 tokens per session scan A ed754da7190e

Subscribe to this mod's changes

junior-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 2,922 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