claude-sdlc CLAUDE.md

claude-sdlc CLAUDE.md is an instructions file for coding agents from lantisprime/claude-sdlc. It costs 2,840 tokens per session, scanned A, original, MIT.

Guidance for developing a Claude Code plugin that enforces an eight-phase software-development workflow with human approval at each phase. The plugin uses instructions, hooks, templates, and agents rather than application code.

In plain words
What is it for?
Use it when changing or working in the SDLC plugin repository, especially when reviewing its workflow, approval gates, hooks, or supporting files.
Why use it?
It prevents automated agents from advancing work or approving changes without a human decision, while keeping the workflow clear.

Instructions file

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.

agentmods
npx agentmods add instructions/lantisprime/claude-sdlc/claude-md
Clone the repo
git clone --depth 1 https://github.com/lantisprime/claude-sdlc

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 claude-sdlc CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lantisprime/claude-sdlc/claude-md.svg)](https://agentmods.dev/instructions/lantisprime/claude-sdlc/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lantisprime/claude-sdlc/claude-md"><img src="https://agentmods.dev/badge/instructions/lantisprime/claude-sdlc/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,840 This file is loaded in full into every session.
When invoked 2,840 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02840 $0.02840
Opus 5 $0.01420 $0.01420
Sonnet 5 $0.00568 $0.00568
Haiku 4.5 $0.00284 $0.00284

Measured 5d ago against content hash 490f0c16ea5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

claude-sdlc CLAUDE.md 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.

CLAUDE.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Context for Claude Code sessions working on this repository — the SDLC plugin itself. This file is read on startup. Keep it short; keep it honest.

What this repo is

A Claude Code plugin that enforces an 8-phase SDLC workflow with human-in-the-lead discipline. It is not application code — it is instructions, hooks, templates, and agents that shape how other Claude Code sessions work in other repos.

Read README.md for the quick-start and docs/SDLC.md for the full phase reference before making substantive changes.

Design intent — read this before "improving" anything

These principles are essential. Changes that violate them usually feel like simplifications but aren't:

  1. Human in the lead, always. Every phase ends at a signed gate file. Subagents, hooks, and MCP connectors propose — humans approve. Do not add an "auto-approve" convenience. Do not let a subagent advance a phase. Do not let observation of past behavior substitute for a fresh human confirmation.

  2. Reduce cognitive load, always. The human is the bottleneck this plugin is designed to protect. Additions to artifacts, prompts, hook messages, and subagent output must make the human's decision easier — less to read, less to reconcile, clearer next step. If a change adds surface area without removing more elsewhere, it's the wrong change.

  3. Plan before code. plan-gate.sh blocks Edit/Write when no plan exists. This is the single most important rule in the plugin. If it seems to be firing "too often," the fix is better planning, not a looser hook.

  4. Surgical edits. Skills and hooks together enforce that only plan-listed files and functions are modified. Adjacent functions are never touched. "While I'm here" cleanups are a known failure mode, not a virtue.

  5. Work-item traceability. Every build references a REQ ID, an issue ticket, or a signed CR. Don't add a "quick fix" escape hatch that bypasses this.

  6. Graceful degradation. Missing Git? Missing ticket system? Missing observability platform? The plugin writes markdown/JSON artifacts locally and surfaces the gap. It never silently skips a check.

Read the full file on GitHub · 190 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. 5d ago First seen · 190 lines · 2,840 tokens per session scan A 490f0c16ea5d

Subscribe to this mod's changes

claude-sdlc CLAUDE.md is an instructions file published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 2,840 tokens to every session, about $0.0142 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.