sdlc

sdlc is a skill for Claude Code from artemnovichkov/skills. It costs 85 tokens per session (1,201 once invoked), scanned A, original, MIT.

A skill for managing software work as a chain of Markdown documents: an idea, requirements, implementation plan, verification, review, and monitoring. Each stage is committed to Git, a system for tracking file changes and versions, before the next stage begins.

In plain words
What is it for?
Use it to capture an idea or bug, write a specification, plan code changes, verify a diff, define review rules, evaluate agent configuration, or connect production metrics to new work.
Why use it?
It keeps decisions and handoffs visible in the repository instead of leaving them only in chat. It also makes planned behaviour available for checking after implementation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the sdlc plugin — 1 skill, 8 commands, 1 agent, 1 hook shipped together

Good fit Use it to capture an idea or bug, write a specification, plan code changes, verify a diff, define review rules, evaluate agent configuration, or connect production metrics to new work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/artemnovichkov/skills/sdlc
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 artemnovichkov/skills --skill sdlc
Clone the repo
git clone --depth 1 https://github.com/artemnovichkov/skills

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 1 agent, 1 hook.

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 sdlc

README.md
[![agentmods](https://agentmods.dev/badge/skills/artemnovichkov/skills/sdlc/github.svg)](https://agentmods.dev/skills/artemnovichkov/skills/sdlc)
Your own site
<a href="https://agentmods.dev/skills/artemnovichkov/skills/sdlc"><img src="https://agentmods.dev/badge/skills/artemnovichkov/skills/sdlc/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.

agentmods 80×15 button for sdlc

Your own site · 80×15
<a href="https://agentmods.dev/skills/artemnovichkov/skills/sdlc"><img src="https://agentmods.dev/badge/skills/artemnovichkov/skills/sdlc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,201 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 $0.00085 $0.01201
Opus 5 $0.00043 $0.00600
Sonnet 5 $0.00017 $0.00240
Haiku 4.5 $0.00009 $0.00120

Measured yesterday against content hash 9ba02ac2d85f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sdlc 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.

The scan reads SKILL.md. This mod also ships 1 executable file (hooks/scripts/guard-tests.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/sdlc/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sdlc

Turns an idea into shipped, verified code through six stages. Each stage produces one markdown artifact in sdlc/, committed to git. The artifact is the handoff: no stage starts until the previous one's artifact exists and the user has accepted it.

Adapted from Anthropic's AI-Native SDLC Playbook, trimmed for a solo developer. The org-scale layer (separation of duties, policy owners, leading/lagging metrics) lives in references/governance.md and is opt-in.

When to Use

Activate when the user asks to:

  • Capture an idea, feature, or bug as a written intent before building
  • Turn an intent into a requirements/design spec
  • Plan an implementation before writing code
  • Set up a verification loop so changes check themselves before review
  • Define review policy (REVIEW.md) or run policy-driven review
  • Add regression evals for agent configuration (CLAUDE.md, skills, hooks)
  • Wire production metrics back into the planning loop

Also activate when a repo already has an sdlc/ directory and the user references an artifact in it.

The Artifact Chain

sdlc/intent/<slug>.md   -> what problem, why now, constraints, open questions
sdlc/spec/<slug>.md     -> requirements + design, concerns flagged
sdlc/plan/<slug>.md     -> files to change, work order, tests required
<diff> + tests          -> verified before a human looks
PR + REVIEW.md passes   -> reviewed against the spec and plan
production signal       -> new sdlc/intent/<slug>.md, loop restarts

One <slug> runs through all three files. That slug is the audit trail — git log sdlc/*/<slug>.md shows the whole decision history for a change.

Commands

Command Stage Produces
/sdlc:init setup sdlc/ scaffold, REVIEW.md, CLAUDE.md sections
/sdlc:intent 1. Plan sdlc/intent/<slug>.md
/sdlc:spec 2. Design sdlc/spec/<slug>.md
/sdlc:plan 3. Build sdlc/plan/<slug>.md
/sdlc:verify 4. Test verification report, optional test-file lock
/sdlc:evals 4. Test evals/ suite + CI workflow
/sdlc:review 5. Deploy REVIEW.md, then delegates to /code-review
/sdlc:bands 6. Maintain sdlc/bands.yaml + watcher script

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 85 tokens per session scan A 9ba02ac2d85f

Subscribe to this mod's changes

sdlc is a skill published in the GitHub repository artemnovichkov/skills (36 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 1,201 once invoked, about $0.0004 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 2026-09-07.

Related

Other skills, from other repositories

parallel-orchestrator

Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…

jimmc414/claude-code-plugin-marketplace · 78 tokens

kanban-dev-lane

Use when a Hermes Kanban worker wants to run an autonomous implementation delegation lane with a 3-tier fallback chain across claudy -> codex (--yolo) -> agyd (agy --dangerously-skip-permissions) -> Hermes direct on quota exhaustion.

epicsagas/plugins · 58 tokens

survey

A project-discovery workflow that creates `.claude/context.md`, a shared file describing the project's purpose, design, constraints, and measures of success.

tomoking2004/claude-plugins · 55 tokens

flow-next-plan

Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).

gmickel/flow-next · 36 tokens

project

A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.

modu-ai/moai-cowork · 475 tokens

hr-performance-review

A skill for designing and running employee performance reviews. It covers MBO, OKRs, KPIs, 360-degree feedback, review guides, and feedback conversations; OKRs set goals and measurable results, while KPIs track ongoing performance.

modu-ai/moai-cowork · 97 tokens