sdlc-direct

sdlc-direct is a skill for Claude Code from Jarroslav/agentic-os. It costs 191 tokens per session (4,901 once invoked), scanned A, original, Apache-2.0.

A lightweight workflow for small, clearly defined software tasks. SDLC means software development life cycle; this workflow still includes codebase research, a clarity check, planning, and human approval points.

In plain words
What is it for?
Handling quick fixes and other unambiguous tasks while researching the repository first and flagging broader scope or risk keywords.
Why use it?
It provides a documented path for simple changes without requiring the full process used for larger or riskier work.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions subagents; names the TodoWrite tool.

Part of the agentic-sdlc plugin — 27 skills, 5 agents shipped together

Good fit Handling quick fixes and other unambiguous tasks while researching the repository first and flagging broader scope or risk keywords.

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

Made for: Claude Code.

Or install agentic-sdlc, the plugin that ships this one along with the rest of its 27 skills, 5 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.

agentmods badge for sdlc-direct

README.md
[![agentmods](https://agentmods.dev/badge/skills/jarroslav/agentic-os/sdlc-direct.svg)](https://agentmods.dev/skills/jarroslav/agentic-os/sdlc-direct)
Your own site
<a href="https://agentmods.dev/skills/jarroslav/agentic-os/sdlc-direct"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/sdlc-direct.svg" alt="Measured on agentmods" height="20"></a>
Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,901 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 $0.00191 $0.04901
Opus 5 $0.00096 $0.02450
Sonnet 5 $0.00038 $0.00980
Haiku 4.5 $0.00019 $0.00490

Measured 7d ago against content hash 32a9cd4843db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sdlc-direct 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 7d 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.

plugins/agentic-sdlc/skills/sdlc-direct/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sdlc-direct

Minimum-ceremony SDLC flow for work the user has already declared simple and clear. No spec document, no complexity scoring, no brainstorming session — just a mandatory research pass, a bounded clarity check, and straight into planning. Human-in-the-loop at every judgment gate, always.

When to invoke

Trigger on direct asks for the lightest flow: "just do this quickly," "small fix, skip the ceremony," "simple task, no spec needed," "run sdlc-direct on ." Do not invoke when:

Situation Use instead
Ticket-sized, ambiguity expected, full audit trail sdlc-guided
Ticket-sized, low-touch automation, audit trail sdlc-auto
User pre-classified task size XS/S/M sdlc-brief
Simple/clear, research-first, no spec sdlc-direct (this skill)

If Stage 1 research turns up broad scope, or the task description contains risk keywords (security, auth, migration, breaking), print the relevant nudge below and proceed anyway — sdlc-direct never refuses, it only flags.

Inputs

Field Type Default Notes
task_description free text required
mode main | sync main sync re-enters an existing maintenance-phase task
slug string kebab-case of task_description, truncated to 50 chars task directory suffix
ui boolean false gates whether acceptance-check can run at Stage 8

Directory and state contract

Every run lives under a single task directory, no worktree, no meta.json:

docs/superpowers/tasks/YYYY-MM-DD-<slug>/

YYYY-MM-DD is the UTC date of the initial Stage 1 invocation. All reads and writes into this tree go through the Read/Write/Edit tools — never shell redirection.

One state file per run, <task-dir>/.state.json. Initial write at Stage 1:

{"schema": 1, "flow": "sdlc-direct", "slug": "<slug>", "branch": "<current branch>", "phase": "main", "started_at": "<ISO>"}

Full schema, including the fields Stage 10 and sync mode add:

Read the full file on GitHub · 391 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 391 lines · 0 tokens per session scan A 32a9cd4843db

Subscribe to this mod's changes

sdlc-direct is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 191 tokens to every session and 4,901 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens