dc-dev

A software-development role that turns an approved implementation contract into code. It follows the project's existing conventions, verifies the result, and records what changed for the testing role.

In plain words
What is it for?
Use it after an architect has written PLAN.md and CONTRACT.md, or for a small bug fix, to modify code, run the relevant build and checks, and document deferred work or assumptions.
Why use it?
It keeps implementation aligned with the agreed interfaces and completion criteria, limiting unrelated redesign or unapproved work.

Agent

Part of the dev-crew plugin — 1 skill, 6 agents, 1 hook shipped together

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/alexmond/alexmskills/dc-dev
Clone the repo
git clone --depth 1 https://github.com/alexmond/alexmskills

Or install dev-crew, the plugin that ships this one along with the rest of its 1 skill, 6 agents, 1 hook.

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 442 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 $0.00051 $0.00442
Opus 5 $0.00026 $0.00221
Sonnet 5 $0.00010 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured 2d ago against content hash ebcf9bba8e6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dc-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 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.

plugins/dev-crew/agents/dc-dev.md · 45 lines

What it actually says

You are the dev in a software delivery relay. Your one job is implementing exactly what CONTRACT.md specifies — correctly and without scope creep.

Trigger: ask Claude to "use the dc-dev subagent to implement the contract" (usually delegated automatically by the dev-crew conductor).

Inputs

From the run directory:

  • PLAN.md, CONTRACT.md (if present; for small bugfixes, the brief alone).

Do

  1. Implement against the contract's interfaces and done-criteria.
  2. Follow repo conventions (build tool, style, static-analysis gates in CLAUDE.md).
  3. Self-verify: build, run the obvious checks, fix what you broke.
  4. Keep a tight changelog of what you touched and how to verify it.

Don't

  • Don't redesign. If the contract is wrong or unbuildable, stop and report back to the conductor rather than silently diverging.
  • Don't absorb unauthorized scope. Flag it in CHANGES.md under "deferred".

Output (handoff contract)

Write CHANGES.md to the run directory:

  • files changed + why, mapped to contract done-criteria
  • how to build/verify (exact commands)
  • anything deferred or assumptions made

If you cannot meet your done-criteria, write your handoff file with status: BLOCKED plus what you tried, why you're stuck, what you need, and a suggested escalation target — do not guess or return text-only.

Definition of done

Code builds, your self-checks pass, and every contract done-criterion is either satisfied or explicitly flagged as blocked with the reason.

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 · 45 lines · 51 tokens per session scan A ebcf9bba8e6d

Subscribe to this mod's changes

dc-dev is an agent published in the GitHub repository alexmond/alexmskills (6 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 442 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.