npx skills add ...
npx skills add reason-machines/trending-skills --skill gsd-2-agent-framework
Meta-prompting, context engineering, and spec-driven development system for autonomous long-running coding agents
npx skills add reason-machines/trending-skills --skill gsd-2-agent-framework
Skill by ara.so — Daily 2026 Skills collection
GSD 2 is a standalone CLI that turns a structured spec into running software autonomously. It controls the agent harness directly — managing fresh context windows per task, git worktree isolation, crash recovery, cost tracking, and stuck detection — rather than relying on LLM self-loops. One command, walk away, come back to a built project with clean git history.
Requires Node.js 18+. Works with Claude (Anthropic) as the underlying model via the Pi SDK.
Iron rule: A task must fit in one context window. If it can't, split it into two tasks.
/gsd auto — Primary Autonomous ModeRun the full automation loop. Reads .gsd/STATE.md, dispatches each unit in a fresh session, handles recovery, and advances through the entire milestone without intervention.
/gsd init — Initialize a ProjectScaffold the .gsd/ directory from a ROADMAP.md and optional PROJECT.md.
Creates initial STATE.md, registers milestones and slices from your roadmap, sets up the cost ledger.
/gsd status — DashboardShows current position, per-slice costs, token usage, and what's queued next.
Output example:
/gsd run — Single Unit DispatchExecute one specific unit manually instead of running the full loop.
/gsd migrate — Migrate from v1Import old .planning/ directories from the original Get Shit Done.
/gsd costs — Cost ReportDetailed cost breakdown with projections.
ROADMAP.mdPROJECT.mdEach phase runs in a fresh session with context pre-inlined into the dispatch prompt:
| Phase | What the LLM receives | What it produces |
|---|---|---|
| Research | PROJECT.md, ROADMAP.md, slice description, codebase index | RESEARCH.md with findings, gotchas, relevant files |
| Plan | Research output, slice description, must-haves | PLAN.md with task breakdown, verification steps |
| Execute (task N) | Task plan, prior task summaries, dependency summaries, DECISIONS.md | Working code committed to git |
| Complete | All task summaries, slice plan | SUMMARY.md, UAT script, updated ROADMAP.md |
| Reassess | Completed slice summary, full ROADMAP.md | Updated roadmap with any corrections |
Every task plan includes must-haves — explicit, checkable criteria the LLM uses to confirm completion. Write them as shell commands or file existence checks:
The execute phase ends only when the LLM can check off every must-have.
GSD manages git automatically in auto mode:
Each task commits with a structured message. Each slice commits a summary commit. The milestone squash-merges to main as one clean entry.
GSD writes a lock file at .gsd/LOCK when a unit starts and removes it on clean completion. If the process dies:
The recovery briefing is synthesized from every tool call that reached disk — file writes, shell output, partial completions — so the resumed session has context continuity.
Set a budget ceiling to pause auto mode before overspending:
The cost ledger at .gsd/costs/ledger.json:
.gsd/DECISIONS.md is auto-injected into every task dispatch. Record architectural decisions here and the LLM will respect them across all future sessions:
If the same unit dispatches twice without producing its expected artifact, GSD:
GSD supports auto-detecting and installing relevant skills during the research phase. Create SKILLS.md in your project:
Skills are injected into the research and plan dispatch prompts, giving the LLM curated knowledge about your exact stack without burning context on irrelevant docs.
Three timeout tiers prevent runaway sessions:
| Timeout | Default | Behavior |
|---|---|---|
| Soft | 8 min | Sends "please wrap up" steering message |
| Idle | 3 min no tool calls | Sends "are you stuck?" recovery prompt |
| Hard | 15 min | Pauses auto mode, preserves all disk state |
Configure in .gsd/config.json:
GSD is built on the Pi SDK. You can extend it programmatically:
Inject custom context into any dispatch prompt:
Register in .gsd/config.json:
After each slice completes, GSD runs a reassessment pass that may:
The LLM edits ROADMAP.md in place. You can review diffs with:
To disable reassessment:
All slices in ROADMAP.md are marked [x]. Reset a slice: remove [x] from its entry and delete .gsd/milestones/M1/slices/S3/SUMMARY.md.
Check .gsd/sessions/ for the last session log. Common causes: must-have references wrong file path, or test command needs environment variable. Adjust must-haves in the task's PLAN.md and re-run with /gsd run --task M1/S3/T2.
The research phase on large codebases can be expensive. Set researchModel to a cheaper model in config, or reduce codebase index depth.
If .gsd/sessions/ grows large, GSD compresses sessions older than 24h automatically. Manual cleanup: