Turn your AI coding agent into a local delivery workflow.
Nanostack helps an agent challenge scope, plan the change, build, review, audit, test, and ship with a record of what happened. Use the default sprint, or build your own workflow stack on top.
Plain text skills. Local artifacts. No Nanostack cloud. No build step.
What is it ·
Profiles ·
Install ·
The Sprint ·
Know-how ·
Extend ·
Español
Inspired by gstack from Garry Tan. Nanostack ships 13 built-in skills, a seven-phase default sprint, and a framework for adding your own skills or workflow stacks. No Nanostack cloud. No build step.
Verified adapters today: Claude Code, Cursor, OpenAI Codex, OpenCode, and Gemini CLI. The skill files are plain text, so other agents may load them, but only those five have a verified adapter and capability declaration in adapters/.
What is Nanostack?
Your agent can already write code. Nanostack gives it delivery structure.
The default sprint turns a vague request into a scoped, reviewed, audited, tested change with a PR and a sprint journal. Each phase reads the artifact the previous phase wrote, so context does not vanish between steps. On Claude Code the pipeline is enforced via PreToolUse hooks: git commit is blocked until /review, /security, and /qa produce fresh artifacts. On other agents the same workflow runs as guided instructions; see What enforces on which agent for the per-host capability table.
The framework layer lets you add your own phases. Custom skills write artifacts, read upstream context, appear in journals and analytics, and can be scheduled by the conductor. See Build on Nanostack.
The built-in sprint is the default stack:
| Step | What the specialist does |
|---|
| 01 | /think | Challenges scope. Finds the smallest thing worth building. |
| 02 | /nano | Plans the implementation. Names every file and every risk. |
| 03 | build | You or the agent writes the code. |
| 04 | /review | Two-pass code review. Scope drift detection. Auto-fixes the mechanical. |
| 05 | /security | OWASP A01-A10 audit + STRIDE threat modeling. Graded A-F. |
| 06 | /qa | Tests the thing. Browser, API, CLI, or root-cause debug. |
| 07 | /ship | PR creation, CI verification, release notes, sprint journal. Production deployment stays explicit and user-controlled. |
Two profiles, same rigor
Nanostack adapts the explanation, not the standard.
| Profile | What changes |
|---|
| Guided | Plain language, one next action, safer defaults, no hidden jargon. |
| Professional | Denser output, deeper tradeoffs, explicit files, commands, and risks. |
Local mode uses Guided language by default. A git project can still use Guided if the user wants simpler explanations.
The wording rules live in reference/plain-language-contract.md. The session fields that select the profile live in reference/session-state-contract.md.
What is enforced depends on your agent
Nanostack is agent-agnostic, but agent hosts do not expose the same control points. The adapter files in adapters/ are the source of truth for each host.