dev

A development workflow that implements tasks already described in a plan. It uses test-driven development, or TDD, which means writing a failing test before the code that makes it pass.

In plain words
What is it for?
Use it to read task and design documents, implement each task, run the test-first loop, record decisions, and pass completed work to validation.
Why use it?
It provides staged reviews and evidence checks while turning planned work into tested code, reducing gaps between the plan and the implementation.

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

Made for: Claude Code, Codex.

Per session 221 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,913 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 $0.00221 $0.02913
Opus 5 $0.00111 $0.01456
Sonnet 5 $0.00044 $0.00583
Haiku 4.5 $0.00022 $0.00291

Measured yesterday against content hash d78d4df0d4a3, 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 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.

.agents/skills/dev/SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement each task from the /plan task list using a subagent-driven loop: implementer → spec compliance reviewer → code quality reviewer per task.

Dev

Chain (HARD-GATE): the ONLY skill you invoke after dev is validate. Never open a PR straight from dev.

This skill reads the task list created by /plan and implements each task using a three-stage subagent loop. TDD is enforced inside each implementer subagent.

Usage

/dev

Setup

Step 1: Load context

# Find task list and design doc
ls docs/work/

Read:

  • Task list: docs/work/YYYY-MM-DD-<slug>/tasks.md — extract ALL task text upfront
  • Design doc: docs/work/YYYY-MM-DD-<slug>/plan.md — including ambiguity policy section

Step 2: Create decisions log

Create an empty decisions log at the start of every /dev session:

# docs/work/YYYY-MM-DD-<slug>/decisions.md

Format for each entry:

## Decision N
**Date**: YYYY-MM-DD
**Task**: Task N — <title>
**Gap**: [what the spec didn't cover]
**Score**: [filled checklist total]
**Route**: PROCEED / SPEC-REVIEWER / BLOCKED
**Choice made**: [if PROCEED: what was decided and why]
**Status**: RESOLVED / PENDING-DEVELOPER-INPUT

Step 3: Pre-flight checks

<HARD-GATE: /dev start>
Do NOT write any code until ALL confirmed:
1. git branch --show-current output is NOT main or master
2. git worktree list shows the worktree path for this feature
3. Task list file confirmed to exist (use Read tool — do not assume)
4. Decisions log file created
</HARD-GATE>

Multi-developer conflict check (soft block)

Before starting the per-task loop, check for cross-developer conflicts:

# Auto-sync to get latest team state (non-blocking)
forge sync || true

# Check for conflicts with the current Forge issue
bash scripts/conflict-detect.sh --issue <forge-id>

If exit code 2 (validation error): show error message, abort — do not show conflict prompt.

If exit code 1 (conflicts found):

  • Display the conflict output to the developer
  • Ask: "Other developers are working in overlapping areas. Proceed anyway? (y/n)"
  • If n: exit cleanly, no side effects
  • If y: log override via forge comment <id> "Conflict override: proceeding despite overlap with <conflicting-issues>", then continue to Per-Task Loop
  • Audit: record conflict override per OWASP A09

Read the full file on GitHub · 346 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 346 lines · 221 tokens per session scan A d78d4df0d4a3

Subscribe to this mod's changes

dev is a skill published in the GitHub repository harshanandak/forge (4 stars, last pushed 2d ago), licensed MIT. It adds 221 tokens to every session and 2,913 once invoked, about $0.0011 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