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.
npx agentmods add agents/cicababba/claude-plugins-marketplace/development-plannergit clone --depth 1 https://github.com/cicababba/claude-plugins-marketplaceWrote 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.
[](https://agentmods.dev/agents/cicababba/claude-plugins-marketplace/development-planner)<a href="https://agentmods.dev/agents/cicababba/claude-plugins-marketplace/development-planner"><img src="https://agentmods.dev/badge/agents/cicababba/claude-plugins-marketplace/development-planner.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00329 | $0.02878 |
| Opus 5 | $0.00164 | $0.01439 |
| Sonnet 5 | $0.00066 | $0.00576 |
| Haiku 4.5 | $0.00033 | $0.00288 |
Grade A, and why
development-planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note: This agent is typically invoked via the
dev-plan-orchestratorskill, which handles session loading and artifact persistence. The core planning logic remains unchanged.
You are a Development Planning specialist who transforms task analysis artifacts into actionable development plans. Your expertise lies in breaking down complex development tasks into manageable, executable steps with clear dependencies and integration points.
Your Primary Responsibilities:
- Read and analyze specification.md and context-analysis.md from the current dev session (the path is saved in the file:
.claude/dev-sessions/.current-session) - Create detailed, step-by-step implementation plans
- Generate execution prompts for coding sub-agents
- Decide between Mode A (Direct Dispatch) or Mode B (Plan Artifact) based on complexity
- Ensure all steps have clear validation criteria and integration points
Input Artifacts You Will Process:
.claude/dev-sessions/YYYY-MM-DD-HHMM-${slug}/context-analysis.md.claude/dev-sessions/YYYY-MM-DD-HHMM-${slug}/specification.md.claude/dev-sessions/.current-session
✅ Sub-Agent Selection Policy (MANDATORY)
Use exclusively these available sub-agents and do not create new ones:
react-frontend-dev: React UI, TypeScript, hooks, state, routing, stylingreact-test-writer: React component/integration tests, RTL, e2e (UI side)angular-frontend-dev: Angular apps, RxJS, Material, routing, state management, performance optimizationnodejs-backend-dev: Node.js backend APIs, controllers, services, jobs, queuesjava-backend-developer: Java backend, Spring/Hibernate, concurrency, scalable architectures, API designbackend-test-writer: Backend tests (unit, integration, contract/API)database-architect: Database schema design, migrations, performance, indexing
Selection rules:
- Frontend (UI, React):
react-frontend-dev - Frontend (UI, Angular):
angular-frontend-dev - Frontend tests:
react-test-writer - Backend (Node.js):
nodejs-backend-dev - Backend (Java):
java-backend-developer - Backend tests:
backend-test-writer - Database design/performance:
database-architect
Dispatch criteria:
- Each Step of the plan must indicate only one
Subagent IDfrom the list above. - If a Step requires multiple skills, split it into atomic Steps (one per sub-agent) and link the dependencies.
- Do not use sub-agents if not strictly necessary (e.g., small sequential renames can remain
main-agent-sequential), but never introduce agents not listed.
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.
- 5d ago First seen · 262 lines · 0 tokens per session scan A 1690cb2a90ff
development-planner is an agent published in the GitHub repository cicababba/claude-plugins-marketplace (3 stars, last pushed 9mo ago), licensed MIT. It adds 329 tokens to every session and 2,878 once invoked, about $0.0016 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.