dev-cycle

dev-cycle is a skill for Claude Code from ToruAI/toru-claude-agents. It costs 34 tokens per session (1,532 once invoked), scanned A, original, MIT.

A guided workflow for taking a software feature from codebase discovery through planning, review, and implementation. It saves progress in session files so work can continue after a terminal closes.

In plain words
What is it for?
Use it to explore an unfamiliar repository, decide the work scope and branch, plan a feature, build it, and check whether it is complete. It can also involve a specialist when the task includes data, analytics, or numbers.
Why use it?
It prevents important context, decisions, and unfinished tasks from being lost between sessions. It also separates exploration, planning, building, and completion checks into clear phases.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the toru-claude-agents plugin — 15 skills, 7 agents, 1 MCP server shipped together

Good fit Use it to explore an unfamiliar repository, decide the work scope and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toruai/toru-claude-agents/dev-cycle
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 ToruAI/toru-claude-agents --skill dev-cycle
Clone the repo
git clone --depth 1 https://github.com/ToruAI/toru-claude-agents

Made for: Claude Code.

Or install toru-claude-agents, the plugin that ships this one along with the rest of its 15 skills, 7 agents, 1 MCP server.

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 dev-cycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/toruai/toru-claude-agents/dev-cycle.svg)](https://agentmods.dev/skills/toruai/toru-claude-agents/dev-cycle)
Your own site
<a href="https://agentmods.dev/skills/toruai/toru-claude-agents/dev-cycle"><img src="https://agentmods.dev/badge/skills/toruai/toru-claude-agents/dev-cycle.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,532 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 $0.00034 $0.01532
Opus 5 $0.00017 $0.00766
Sonnet 5 $0.00007 $0.00306
Haiku 4.5 $0.00003 $0.00153

Measured 7d ago against content hash 018436a451dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dev-cycle 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 7d 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/dev-cycle/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Cycle - Development Session Manager

Orchestrated development workflow: Discovery → Planning → Review → Build

Agent Roles

  • Scout: Codebase Explorer - explores before planning (haiku, fast, cheap)
  • Bob: Technical Builder - builds code, ensures quality
  • Garry: Chief of Staff - validates completion, checks alignment
  • Arlo: Pattern Whisperer - involved when data/analytics/numbers are part of the work

Session State

Sessions are stored in ~/.claude/dev-cycles/active/ and ~/.claude/dev-cycles/completed/

Starting a Session

1. Check for Active Session

ls ~/.claude/dev-cycles/active/ | grep "$(basename $(pwd))"

If active session exists for this project:

  • Read the session file
  • Show current status (phase, completed tasks, blockers)
  • Ask: "Continue this session or start new?"

2. Start New Session

Ask these questions in order:

  1. Branch: "Work on existing branch, create new, or no branch?"

    • If existing: git branch -a to show options
    • If new: Ask for branch name (follow branch-workflow conventions)
    • If none: Work on current branch
  2. Scope: "What are we building?"

    • Get clear description
    • For small tasks: Can collapse Discovery+Planning
  3. Create session file:

~/.claude/dev-cycles/active/{project-name}--{YYYYMMDD-HHMMSS}.md

Session File Format

# Dev Cycle: {description}

## Meta
- **Project**: {project-name}
- **Branch**: {branch-name or "none"}
- **Started**: {timestamp}
- **Phase**: discovery | planning | review | building | blocked
- **Involves Data/Analytics**: yes | no

## Discovery
{Requirements, context, decisions made during discovery}

## Plan
{Tasks with checkboxes, phases, acceptance criteria}

## Progress
- [x] Task 1 - completed
- [ ] Task 2 - current
- [ ] Task 3 - pending

## Blockers
{Any blockers encountered - stop and ask the user}

## Batched Questions
{Easy questions to ask after build is done}

## Decisions
{Key decisions made during this session}

Read the full file on GitHub · 242 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. 7d ago First seen · 242 lines · 34 tokens per session scan A 018436a451dd

Subscribe to this mod's changes

dev-cycle is a skill published in the GitHub repository ToruAI/toru-claude-agents (15 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,532 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 2026-08-30.

Related

Other skills, from other repositories

ln-51-opportunity-evaluator

Evaluates new product opportunities using demand, channels, competition, and economics. Not for committed-backlog or implementation planning.

levnikolaevich/claude-code-skills · 32 tokens

log

Capture front door. Logs 1..N observations as card files at docs/work/{ID}.md (BUG / DEBT / GAP), gateway-inline — no dispatch. Use when the user says "log this", "track that", "note this down", or types /super-bootstrap:log — and when Claude needs to file its own findings (out-of-scope findings from a review, audit…

RockyHong/super-bootstrap · 164 tokens

triage

Read-only grounding phase for a card — every card's pickup. /super-bootstrap:triage {ID} dispatches the triage subagent (Opus) to ground the card cold — premise verify, aim validate, blast collect — and append a Verdict block — ## Verdict — auto-fix · {date} (Fix-shape / Probe-deps / Execution tags) or ## Verdict …

RockyHong/super-bootstrap · 159 tokens

drain

Parallel-worktree auto-drain of the board. One /super-bootstrap:drain turn = scan the pipeline sources (specs/plans/backlog, plus the scale module's test queue when present) → keep only admissible items → relation-analyze into a conflict-free wave → confirm with the user → spawn one isolated git worktree + headless…

RockyHong/super-bootstrap · 200 tokens

issue-triage

Triage and categorize GitHub issues with priority labels. Use when user says "triage issues", "check issues", "review open issues", or during regular maintenance of GitHub issue backlog.

decebals/claude-code-java · 44 tokens

memstack-business-client-onboarding

Use this skill when the user says 'client onboarding', 'new client', 'onboard client', 'kickoff meeting', 'intake form', 'welcome email', or needs welcome sequences, questionnaires, and setup checklists for new clients. Do NOT use for contracts or invoicing.

cwinvestments/memstack · 65 tokens