A planning command for starting a software feature from an initial description. It runs a product-planning interview, divides the work into slices, writes planning documents, and creates one Linear issue per slice.

Use it for requests such as adding a login page or building a reporting dashboard. It produces a grill summary, product requirements document, scope.json, and tracked work issues.

It gives a feature a documented plan before implementation starts. This reduces uncertainty about requirements, responsibilities, and the order of the work.

sdlc-plan — Command for Claude Code by saitarrun/Devforge-ai

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/saitarrun/Devforge-ai

agentmods

npx agentmods add commands/saitarrun/devforge-ai/sdlc-plan

Made for: Claude Code.

Or install devforge-ai, the plugin that ships this one along with the rest of its 48 skills, 17 commands, 10 agents.

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/saitarrun/devforge-ai/sdlc-plan/github.svg)](https://agentmods.dev/commands/saitarrun/devforge-ai/sdlc-plan)

Your own site

<a href="https://agentmods.dev/commands/saitarrun/devforge-ai/sdlc-plan"><img src="https://agentmods.dev/badge/commands/saitarrun/devforge-ai/sdlc-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/saitarrun/devforge-ai/sdlc-plan"><img src="https://agentmods.dev/badge/commands/saitarrun/devforge-ai/sdlc-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 676 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	$0.00031	$0.00676
Opus 5.5	$0.00012	$0.00270
Sonnet 5.5	$0.00006	$0.00135
Haiku 4.5	$0.00003	$0.00068

Measured 1mo ago against content hash 656d55535de8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdlc-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.

commands/sdlc-plan.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdlc-plan — Phase 1: Plan

Conduct the grill-me interview, emit grill-summary.md + scope.json, publish a PRD, and create one issue per slice. Uses exactly 1 agent: product-manager.

Usage

/sdlc-plan "add a login page"
/sdlc-plan "build a reporting dashboard"

EXECUTION

STEP 1: Invoke product-manager

Spawn: Agent({
  name: "product-manager",
  description: "Product Manager — grill-me interview + slice decomposition",
  prompt: "Feature request: <user's feature description>

  Conduct the full grill-me interview (Phase A–D). Do not skip any phase.
  After the interview resolves:
  1. Write ./projects/<feature-name>/grill-summary.md with the full interview transcript
  2. Decompose the feature into tracer bullet slices
  3. Write ./projects/<feature-name>/scope.json with capability_flags + slices array

  The first slice must always be type: prefactor (project scaffold + health check).
  Subsequent slices are type: feature named from the user's perspective.
  layers are derived from grill-me answers (has_ui → include 'ui', etc.)."
})

Wait for product-manager to complete. Verify:

./projects/<feature-name>/grill-summary.md exists
./projects/<feature-name>/scope.json exists and is valid JSON

STEP 2: Wait for product-manager to complete PRD + issues

The product-manager agent handles the PRD gate, synthesis, and issue creation directly (Steps 5–6 in its process). Wait for it to complete.

Verify on completion:

./projects/<feature-name>/docs/01-prd.md exists
scope.json has linear_id or issue_ref on every slice

STEP 3: Prompt — Ready to start Build?

✅ PRD published! [N] issues created.

Ready to start Build?
→ This will run /handoff (creating handoffs/plan-handoff.md) then invoke /sdlc-build.
→ Reply "yes" to proceed or "no" to pause here.

On confirm:

Run /handoff — stores compressed context at ./projects/<feature-name>/handoffs/plan-handoff.md
Invoke /sdlc-build

Read the full file on GitHub · 83 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 · 83 lines · 31 tokens per session scan A 656d55535de8

Subscribe to this mod's changes

sdlc-plan is a command published in the GitHub repository saitarrun/Devforge-ai (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 676 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 2026-08-31.

Claude Code Planning Project management agentic-ai ai-agents automation claude-code-plugin codex-plugin

poam-review

Review and manage Plan of Action & Milestones (POA&M).

GRCEngClub/claude-grc-engineering · 14 tokens

g-forge

G-Forge workflow commands. Subcommands — help, status, resume, doctor, audit, init, kickoff, onboard, brief, roadmap, intake, plan, forecast, blast-radius, execute, review, doc-review, align, afk, specialize, update, skill-design, skill-validate, adr, docs, wiki, patterns, telemetry, identity, retro, listen, optimize…

onlygian/G-Forge · 93 tokens

sdlc-plan