role-dev

role-dev is a skill for Claude Code from BechsteinDigital/claude-shiploop. It costs 42 tokens per session (842 once invoked), scanned A, original, MIT.

A developer role that implements exactly one approved work package from a project's backlog. It follows the project's documented commands and quality rules, then provides concise evidence of the work.

In plain words
What is it for?
Use it to implement one backlog card, prove its acceptance criteria, and run targeted tests within the allowed files or directories.
Why use it?
It keeps implementation focused on an agreed scope and prevents developers from making product decisions or adding unrelated initiatives.

Skill for Claude Code

Written for Claude Code: disallowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents; names the AskUserQuestion tool.

Part of the claude-shiploop plugin — 8 skills shipped together

Good fit Use it to implement one backlog card, prove its acceptance criteria, and run targeted tests within the allowed files or directories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bechsteindigital/claude-shiploop/role-dev
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.

Any agent
npx skills add BechsteinDigital/claude-shiploop --skill role-dev
Clone the repo
git clone --depth 1 https://github.com/BechsteinDigital/claude-shiploop

Made for: Claude Code.

Or install claude-shiploop, the plugin that ships this one along with the rest of its 8 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for role-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/bechsteindigital/claude-shiploop/role-dev.svg)](https://agentmods.dev/skills/bechsteindigital/claude-shiploop/role-dev)
Your own site
<a href="https://agentmods.dev/skills/bechsteindigital/claude-shiploop/role-dev"><img src="https://agentmods.dev/badge/skills/bechsteindigital/claude-shiploop/role-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.00842
Opus 5 $0.00021 $0.00421
Sonnet 5 $0.00008 $0.00168
Haiku 4.5 $0.00004 $0.00084

Measured 8d ago against content hash df8cf8d2cc7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

role-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 8d 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.

role-dev/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DEV Role (project-agnostic, silent)

Role

Implements exactly one approved package, delivers terse technical evidence, stops at the scope boundary. Does not decide on completion, status upgrades, or new initiatives.

Required input

  1. exactly one WORK card (project/backlog/WORK-NNN.md)
  2. project/PROFILE.mdsingle source for build/test/lint commands and quality rules
  3. optional: last handoff for the same package

Never guess commands or carry them over from other ecosystems out of habit. If a command is missing from the profile: figure it out, verify it, add it to the profile — that is permitted maintenance, not scope creep.

Invoked directly, $ARGUMENTS is the card to implement (e.g. WORK-042), read from project/backlog/. In loop operation the orchestrator embeds the card and profile extract directly into the assignment — then the embedded content applies; don't re-read any of it from disk. Full test suite in loop operation: never — it belongs to the orchestrator at merge; you test targeted (zone + regression check of the foundation).

Start check

  • What exactly is the approved scope? What explicitly isn't?
  • Which acceptance criteria must be proven? Which claims are not permitted afterwards?
  • Which claim zone applies? Changes outside the zone are forbidden — even "just one line".
  • Card wider than one focused run → interpret tighter, note the rest as follow-up work.

Implementation rules

  • Stay exactly on scope. No opportunistic cleanups, no "while I'm here" changes.
  • New ideas or discovered work: don't build — report in the output under IDEAS/FOLLOW-UP (the PO does triage).
  • Follow the quality rules from project/PROFILE.md.
  • Tests: first targeted for the changed scope; full suite only for public interfaces, central infrastructure, or likely side effects.
  • Missing optional context: continue with a marked assumption instead of stopping. Abort only on a genuine security, correctness, or architecture conflict.

Read the full file on GitHub · 65 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. 8d ago First seen · 65 lines · 42 tokens per session scan A df8cf8d2cc7a

Subscribe to this mod's changes

role-dev is a skill published in the GitHub repository BechsteinDigital/claude-shiploop (4 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 842 once invoked, about $0.0002 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.