gstack integrates with OpenClaw as a methodology source, not a ported codebase. OpenClaw's ACP runtime spawns Claude Code sessions natively. gstack provides the planning discipline and methodology that makes those sessions better.
This is a lightweight protocol encoded as prompt text. No daemon. No JSON-RPC. No compatibility matrices. The prompt is the bridge.
OpenClaw gstack repo
───────────────────── ──────────────
Orchestrator: messaging, Source of truth for
calendar, memory, EA methodology + planning
│ │
├── Native skills (conversational) ├── Generates native skills
│ office-hours, ceo-review, │ via gen-skill-docs pipeline
│ investigate, retro │
│ ├── Generates gstack-lite
├── sessions_spawn(runtime: "acp") │ (planning discipline)
│ │ │
│ └── Claude Code ├── Generates gstack-full
│ └── gstack installed at │ (complete pipeline)
│ ~/.claude/skills/gstack │
│ └── docs/OPENCLAW.md (this file)
└── Dispatch routing (AGENTS.md)
OpenClaw decides at spawn time which tier of gstack support to use:
| Tier | When | Prompt prefix |
|---|---|---|
| Simple | One-file edits, typos, config changes | No gstack context injected |
| Medium | Multi-file features, refactors | gstack-lite CLAUDE.md appended |
| Heavy | Specific gstack skill needed | "Load gstack. Run /X" |
| Full | Complete features, objectives, projects | gstack-full pipeline appended |
| Plan | "Help me plan a Claude Code project" | gstack-plan pipeline appended |
- Can it be done in <10 lines of code? -> Simple
- Does it touch multiple files but the approach is obvious? -> Medium
- Does the user name a specific skill (/cso, /review, /qa)? -> Heavy
- Is it a feature, project, or objective (not a task)? -> Full
- Does the user want to PLAN something for Claude Code without implementing yet? -> Plan
The complete ready-to-paste section lives in openclaw/agents-gstack-section.md.
Copy it into your OpenClaw AGENTS.md.
Key behavioral rules (these go ABOVE the dispatch tiers):
- Always spawn, never redirect. When the user asks to use ANY gstack skill, ALWAYS spawn a Claude Code session. Never tell the user to open Claude Code.
- Resolve the repo. If the user names a repo, set the working directory. If unknown, ask which repo.
- Autoplan runs end-to-end. Spawn, let it run the full pipeline, report back in chat. User should never have to leave Telegram.
When spawning Claude Code in a repo that already has a CLAUDE.md, APPEND gstack-lite/full as a new section. Do not replace the repo's existing instructions.
All artifacts live in the openclaw/ directory and are generated by
bun run gen:skill-docs --host openclaw:
openclaw/gstack-lite-CLAUDE.md — ~15 lines of planning discipline:
- Read every file before modifying
- Write a 5-line plan: what, why, which files, test case, risk
- Resolve ambiguity using decision principles
- Self-review before reporting done
- Completion report: what shipped, decisions made, anything uncertain
A/B tested: 2x time, meaningfully better output.
openclaw/gstack-full-CLAUDE.md — chains existing gstack skills:
- Read CLAUDE.md and understand the project
- Run /autoplan (CEO + eng + design review)
- Implement the approved plan
- Run /ship to create a PR
- Report back with PR URL and decisions
openclaw/gstack-plan-CLAUDE.md — full review gauntlet, no implementation:
- Run /office-hours to produce a design doc
- Run /autoplan (CEO + eng + design + DX reviews + codex adversarial)
- Save the reviewed plan to
plans/<project-slug>-plan-<date>.md - Report back: plan path, summary, key decisions, recommended next step
The orchestrator persists the plan link to its own memory store (brain repo, knowledge base, or whatever is configured in AGENTS.md). When the user is ready to build, spawn a FULL session that references the saved plan.
Published to ClawHub. Install with clawhub install:
gstack-openclaw-office-hours— Product interrogation (6 forcing questions)gstack-openclaw-ceo-review— Strategic challenge (10-section review, 4 modes)gstack-openclaw-investigate— Operational debugging (4-phase methodology)gstack-openclaw-retro— Operational retrospective (weekly review)
Source lives in openclaw/skills/ in the gstack repo. These are hand-crafted
adaptations of the gstack methodology for OpenClaw's conversational context.
No gstack infrastructure (no browse, no telemetry, no preamble).
When Claude Code runs inside a session spawned by OpenClaw, the OPENCLAW_SESSION
environment variable should be set. gstack detects this and adjusts:
- Skips interactive prompts (auto-chooses recommended options; destructive or irreversible options are never auto-chosen — the conservative choice wins and gets recorded in the completion report)
- Suppresses interactive-onboarding instruction blocks at emission (upgrade checks, telemetry prompts, feature discovery, routing injection, tips), so one-time prompts survive intact for the next human session
- Suppresses the Conductor prose signal (
CONDUCTOR_SESSION: true) — a spawned session inside a Conductor workspace auto-chooses instead of rendering prose to nobody - Focuses on task completion and prose reporting
Set the env var in sessions_spawn: env: { OPENCLAW_SESSION: "1" }
GSTACK_SESSION_KIND=spawned is the explicit per-command marker for the same
classification, outranking every ambient env marker (including
OPENCLAW_SESSION and GSTACK_HEADLESS). It exists because Claude Code
subagents inherit the parent session's env byte-for-byte (#2733) — a
dispatching skill marks its subagent by prefixing the preamble invocation on
the same command line:
GSTACK_SESSION_KIND=spawned "$_SS" --skill "document-release" ...gstack itself uses this: /ship Step 18 dispatches the /document-release
subagent with this prefix so its interactive gates auto-choose instead of
prose-stopping. Deliberately narrow: only spawned is honored — headless
already has GSTACK_HEADLESS, and letting an env var force interactive
over CI markers would be a misclassification footgun. Empty or other values
are reserved and ignored (fall through to ambient detection). Note that hook
processes inherit the harness env, so a per-command prefix never reaches
PreToolUse/PostToolUse hooks — the hook texts carry a spawned escape sentence
for that topology (hosts/claude/hooks/spawned-directive.ts).
Tamper visibility. Any mechanism that injects session-wide env (a cloned
repo's .claude/settings.json env block, direnv, a CI wrapper) could set
GSTACK_SESSION_KIND=spawned for a real human's session and silently flip
its confirmation gates to auto-choose. When the env override drives the
classification, the preamble emits a loud SPAWNED_OVERRIDE: env status line
so the transcript shows WHY the session is spawned — audit
.claude/settings.json env blocks in untrusted repos (/cso covers this).
For OpenClaw users: tell your OpenClaw agent "install gstack for openclaw."
The agent should:
- Install gstack-lite CLAUDE.md into its coding session templates
- Install the 4 native methodology skills
- Add dispatch routing to AGENTS.md
- Verify with a test spawn
For gstack developers: ./setup --host openclaw outputs this documentation.
The actual artifacts are generated by bun run gen:skill-docs --host openclaw.
- No dispatch daemon (ACP handles session spawning)
- No Clawvisor relay (no security layer needed)
- No bidirectional learnings bridge (brain repo is the knowledge store)
- No JSON schemas or protocol versioning
- No SOUL.md from gstack (OpenClaw has its own)
- No full skill porting (coding skills stay native to Claude Code)