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.
npx skills add Jarroslav/agentic-os --skill sdlc-directgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/skills/jarroslav/agentic-os/sdlc-direct)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/sdlc-direct"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/sdlc-direct/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/skills/jarroslav/agentic-os/sdlc-direct"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/sdlc-direct.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.04901 |
| Opus 5.5 | $0.00000 | $0.01960 |
| Sonnet 5.5 | $0.00000 | $0.00980 |
| Haiku 4.5 | $0.00000 | $0.00490 |
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 2mo 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 — 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:
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.
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.
- 2mo ago First seen · 391 lines · 0 tokens per session scan A 32a9cd4843db
sdlc-direct is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,901 tokens. 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.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…