A command that turns an approved specification into a technical design, implementation tasks, and an initial test-driven development state.

Use it to plan backend, frontend, or full-stack Spring and Angular features, including larger work split into smaller slices.

It breaks a feature into ordered work that developers can implement and track instead of starting from an unstructured request.

plan — Command for Claude Code by loiane

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.

Clone the repo

git clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angular

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/loiane/specs-driven-development-spring-angular/plan/github.svg)](https://agentmods.dev/commands/loiane/specs-driven-development-spring-angular/plan)

Your own site

<a href="https://agentmods.dev/commands/loiane/specs-driven-development-spring-angular/plan"><img src="https://agentmods.dev/badge/commands/loiane/specs-driven-development-spring-angular/plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/loiane/specs-driven-development-spring-angular/plan"><img src="https://agentmods.dev/badge/commands/loiane/specs-driven-development-spring-angular/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,063 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.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.01063
Opus 5.5	$0.00007	$0.00425
Sonnet 5.5	$0.00004	$0.00213
Haiku 4.5	$0.00002	$0.00106

Measured 1mo ago against content hash 962bf59c0619, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plan 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 1mo 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.

.claude/commands/plan.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/plan

Phase: 3 — plan Owning agent: .claude/agents/spring-architect.md Skills used: epic-slicing-planning, spring-task-decomposition, spring-boot-4-conventions, openapi-contract-first, flyway-or-liquibase-detection, archunit-rules, adr-authoring, performance-optimization

Stack routing

Feature scope	Agent
Backend-only or full-stack (Spring)	`spring-architect` (this agent)
Frontend-only (Angular)	`angular-architect`
Full-stack	Run both: `spring-architect` for backend tasks, `angular-architect` for frontend tasks

If the feature's 01-spec.md ACs reference only Angular/UI concerns (components, routes, templates, styles), delegate entirely to angular-architect. If ACs span both stacks, produce a unified 03-design.md but decompose 04-tasks.md into backend tasks (owned by spring-architect) and frontend tasks (owned by angular-architect).

Purpose

Translate a PASS-verdict spec into planning artifacts:

Non-Epic mode: 03-design.md + 04-tasks.md
Epic mode: 03-epic-design.md + 03a-epic-roadmap.md, then slice-level 03-design.md + 04-tasks.md

Then initialize .tdd-state.json.

Inputs

<feature-id>.
Optional --epic to force Epic mode.

Reads

01-spec.md, 02-spec-review.md (verdict must be PASS).
.specs/_stack.json.
.claude/templates/design.template.md, .claude/templates/tasks.template.md, .claude/templates/adr.template.md.
Epic mode: .claude/templates/epic-design.template.md, .claude/templates/epic-roadmap.template.md.
All design/architecture skills above.

Writes

.specs/<feature-id>/03-epic-design.md (Epic mode)
.specs/<feature-id>/03a-epic-roadmap.md (Epic mode)
.specs/<feature-id>/03-design.md
.specs/<feature-id>/04-tasks.md
.specs/<feature-id>/.tdd-state.json (initial: no active_task, every task phase: "pending")
.specs/<feature-id>/adr/ADR-NNN-*.md for any architecturally significant decision.

Process

Refuse if 02-spec-review.md is missing or its verdict is not PASS.
Refuse if 01-spec.md still has any Q-NNN.
Detect planning mode. Use Epic mode if --epic is present or the feature spans multiple vertical slices/shared cross-cutting decisions.
In Epic mode, write 03-epic-design.md and 03a-epic-roadmap.md first. Refuse to continue if either Epic artifact has unresolved Q-NNN.
Produce 03-design.md: module map, public API, REST contract sketch (or full OpenAPI), data model, migration plan (Flyway/Liquibase per _stack.json), error model, observability, security touch points, ArchUnit rule additions.
For each architecturally-significant choice, write an ADR.
Decompose into tasks T-001, T-002, ... Each task must list:
- id, title, acs_covered: [AC-NNN, ...], files_in_scope: [paths], depends_on, estimated_phases: [red, green, refactor, simplify].
- Tasks that touch src/main/** MUST list at least one file under src/test/** in files_in_scope.
Validate AC coverage: every AC from 01-spec.md must appear in at least one task. If not, FAIL the plan and surface the gap.

Initialize .tdd-state.json:

{ "active_task": null, "tasks": { "T-001": { "phase": "pending", "files_in_scope": [...], "acs_covered": [...] }, ... } }

Read the full file on GitHub · 73 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.

1mo ago First seen · 73 lines · 18 tokens per session scan A 962bf59c0619

Subscribe to this mod's changes

plan is a command published in the GitHub repository loiane/specs-driven-development-spring-angular (62 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 1,063 once invoked, about $0.0001 per session on Opus 5.5. 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.

Java Planning TDD angular github-copilot spec-driven-development spring-boot

plan

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/plan

Stack routing

Purpose

Inputs

Reads

Writes

Process

What this file has done since we first saw it

Other commands, from other repositories

spec-impl

benchmark

profile

update-issue

create-diagram

devkit.github.review-pr