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.
git clone --depth 1 https://github.com/AratKruglik/claude-sdlcWrote 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/plugins/aratkruglik/claude-sdlc/sdlc)<a href="https://agentmods.dev/plugins/aratkruglik/claude-sdlc/sdlc"><img src="https://agentmods.dev/badge/plugins/aratkruglik/claude-sdlc/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.
<a href="https://agentmods.dev/plugins/aratkruglik/claude-sdlc/sdlc"><img src="https://agentmods.dev/badge/plugins/aratkruglik/claude-sdlc/sdlc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "sdlc",
"version": "2.2.0",
"description": "Universal SDLC orchestrator with stack provider auto-discovery. Owns the pipeline; framework plugins register themselves via stack.md profiles. Git-flow aware: detects the project's branching model and branch-naming convention, classifies the task type, proposes a branch, and targets the PR at the right base. Includes 5 cost-tiered default agents (BA Opus, Dev Sonnet, QA Sonnet with iteration cap, Sec Opus, Docs Haiku). Slash command: /sdlc:start \"<feature>\".",
"author": {
"name": "Oleksii Kruhlyk",
"url": "https://github.com/AratKruglik"
},
"license": "MIT",
"homepage": "https://github.com/AratKruglik/claude-sdlc",
"keywords": [
"sdlc",
"orchestrator",
"pipeline",
"git-flow",
"ai-assisted-engineering"
],
"userConfig": {
"noninteractive": {
"type": "boolean",
"title": "Non-interactive (headless) mode",
"description": "Run /sdlc:start without interactive prompts (branch gate auto-resolves, policy failures become machine-readable output). The SDLC_NONINTERACTIVE environment variable, when set, wins over this option.",
"default": false
},
"default_cost_cap_usd": {
"type": "number",
"title": "Default cost cap (USD)",
"description": "Runaway guard applied to every run whose workflow recipe declares no caps.max_total_cost_usd. 0 disables it. The recipe value, when present, wins.",
"default": 0,
"min": 0
},
"stack_cache_ttl_hours": {
"type": "number",
"title": "Stack-detection cache TTL (hours)",
"description": "How long /sdlc:start trusts the SessionStart-hook stack-detection cache before re-scanning installed plugins. Lower it on machines where plugins change often.",
"default": 6,
"min": 1,
"max": 168
},
"post_check_fix_attempts": {
"type": "number",
"title": "Post-pipeline check fix attempts",
"description": "When a post-pipeline cheWhat it installs
The manifest is a name and a version. 3 skills, 5 commands, 5 agents travel with it, and installing the plugin installs all of them — 1,268 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill pipeline-orchestrator A 132 tokens
- Skill batch-pipeline A 164 tokens
- Skill architect-conventions A 64 tokens
- Command start A 34 tokens
- Command security-init A 43 tokens
- Command batch A 26 tokens
- Command list-stacks A 26 tokens
- Command doctor B 38 tokens
- Agent security-analyst A 167 tokens
- Agent document-writer A 138 tokens
- Agent qa-engineer A 163 tokens
- Agent business-analyst A 152 tokens
- Agent developer A 121 tokens
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.
- 2d ago Changed 4707212c0ad4
- 11d ago Changed 1608f2b7b75f
- 1mo ago Changed · +34 lines 8222aa3931b0
- 1mo ago Changed c63107a7d37e
- 1mo ago First seen · 19 lines scan A 99f36cb9cf19
sdlc is a plugin published in the GitHub repository AratKruglik/claude-sdlc (53 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
fuse-rules
Global rules for all Claude Code sessions: APEX workflow, SOLID/DRY enforcement, project detection, agent delegation, frontend/git standards.
lanes-bridges
Bridge Lanes with GitHub and Linear: import issues, batch-spawn a session per ticket, and post results back upstream. Split out of lanes-desktop in 0.7.0.
workbench
Ticket-to-PR development workflow: triage, plan with verified citations, implement inside the plan, review, commit, PR. Pluggable issue trackers (Jira, Azure DevOps, GitHub Issues) or a backlog in the repo, so it works with no tracker at all.
gh-cli
GitHub CLI integration with focused skills for pull requests, stacked pull requests, issues, GitHub Actions, and viewing GitHub file URLs.
tgc-skills
A shipping pipeline for Claude Code: orchestrate a locked plan with fresh-context agents, polish the diff, ship it to a reviewed PR, run an agent review-fix loop until clean, and clean up after merge.
github
Drive PRs to merge-ready with gh: fix CI and review-bot feedback, plus bulk merge, close, and label.