Mechanical rename produced by scripts/msd-rename.cjs: gsd/Gsd/GSD -> msd/Msd/MSD across contents and paths, upstream package/repo coordinates -> @golem15/msd-core and golem15com/msd-core. Deep links into upstream history, sibling upstream packages, the GSD-2 import feature, CHANGELOG.md and .changeset/ are kept as-is. Hand edits on top: MSD block-letter banner and logos, LICENSE copyright line, package/plugin identity, regenerated lockfile, install-tree fixtures, derived registries and benchmark baseline; migration checksum baseline re-locked (MSD keeps its own install state, so no install had applied the old sums); sort-order and regex-escaped expectations in tests adjusted.
7.7 KiB
How to run phases autonomously
Run all remaining phases — or a bounded range of them — unattended, so MSD moves through discuss → plan → execute for each phase without you driving every step.
For background on what the phase loop is doing during an autonomous run, see The phase loop.
Prerequisites
- An active project with
.planning/ROADMAP.mdand.planning/STATE.md - All phases you want to run must be in a state that autonomous mode can drive (pending or in-progress; not already complete)
- Any design decisions you care about should already be in
PROJECT.mdor captured via a prior/msd-discuss-phase— autonomous mode can surface grey areas interactively only when you use--interactive
Run all remaining phases
/msd-autonomous
MSD reads ROADMAP.md, discovers every incomplete phase in numeric order, and runs discuss → plan → execute on each one. After all phases complete it automatically runs the milestone lifecycle: audit → complete → cleanup.
Run a specific range of phases
Use --from and --to to bound the run. Both flags accept decimal phase numbers (e.g. 3.1).
/msd-autonomous --from 3 # phases 3, 4, 5 … (skip already-done phases 1 and 2)
/msd-autonomous --to 5 # phases up to and including 5
/msd-autonomous --from 3 --to 5 # exactly phases 3, 4, and 5
When --to is reached the lifecycle step is skipped, because not all milestone phases are done. The completion banner tells you how to resume:
Resume with: /msd-autonomous --from 6
Run a single phase
To run exactly one phase without triggering the milestone lifecycle, use --only N:
/msd-autonomous --only 4
If the phase is already complete, autonomous mode exits immediately with a message rather than re-running it.
Run with plan convergence
Use --converge when you want each phase to run the plan-review convergence loop before execution. Both /msd-autonomous and /msd-progress --next --auto support this flag.
# Needed only for /msd-progress --next --converge and standalone /msd-plan-review-convergence
# (/msd-autonomous --converge overrides the gate for its own run):
msd config-set workflow.plan_review_convergence true
# Via autonomous (multi-phase or single-phase):
/msd-autonomous --only 4 --converge
/msd-autonomous --from 3 --to 5 --converge --all --max-cycles 5
# Via progress --next --auto (step-chaining with convergence):
/msd-progress --next --auto --converge
/msd-progress --next --auto --converge --codex --max-cycles 4
--cross-ai is accepted as an alias for --converge. Reviewer flags supported by /msd-plan-review-convergence pass through unchanged, including --codex, --claude, --opencode, --ollama, --lm-studio, --llama-cpp, --all, and --max-cycles N.
An explicit --converge on /msd-autonomous overrides the gate for that run: convergence runs even when workflow.plan_review_convergence is false, and without the flag autonomous plans with msd-plan-phase. The gate still governs /msd-progress --next --converge and standalone /msd-plan-review-convergence, which stop with the enable command when it is not enabled.
Run with interactive discuss
By default, autonomous mode answers discuss questions automatically using smart discuss (batch table proposals). If you want to answer design questions yourself while keeping plan and execute out of the main context:
/msd-autonomous --interactive
In interactive mode:
/msd-discuss-phaseruns inline and waits for your answers- On runtimes that support nested background dispatch, planning and execution are dispatched as background agents so you can discuss the next phase while the current one builds; on Claude Code, planning and execution run inline (the next phase's discuss does not overlap)
- The main context stays lean — only discuss conversations accumulate (on runtimes with background dispatch; on Claude Code, inline plan/execute also accumulate)
Run on a non-Claude runtime
To run autonomously on a runtime that does not support the AskUserQuestion tool (for example Codex CLI or Antigravity), add --text:
/msd-autonomous --text
/msd-autonomous --from 3 --text
All interactive prompts become plain numbered lists; type the choice number to respond. When combined with --converge, --text is also forwarded to the convergence loop via CONVERGENCE_ARGS so reviewer prompts inside plan-review convergence use the same plain-text mode.
What safety gates still apply
Autonomous mode does not bypass MSD's quality pipeline. Each phase still:
- Runs the plan-checker before execution
- Reads
VERIFICATION.mdafter execution and routes on the result - Pauses and asks you what to do when verification status is
human_neededorgaps_found - Stops and presents options (fix and retry, skip phase, or stop) if any step fails
The only difference from manual execution is that passed verification advances automatically — you are not prompted between phases unless a decision is required.
The package legitimacy gate also remains active. If a plan includes a checkpoint:human-verify task for a suspicious package, the executor will stop and surface the checkpoint. Autonomous mode will not silently install flagged packages.
When not to use autonomous mode
Do not use /msd-autonomous when:
-
Phases have unsettled design decisions. If you have not run
/msd-discuss-phaseand yourPROJECT.mddoes not capture your preferences, smart discuss will make autonomous choices you may not agree with. Run discuss interactively first, or use--interactive. -
You need fine-grained control over a single phase. For one phase,
/msd-execute-phase Ngives you step-by-step output and lets you react before continuing. Use--only Nif you want the autonomous quality pipeline on a single phase but do not need step-by-step interaction. -
The phase has novel or high-risk work. Autonomous mode skips pauses unless it hits a blocker. On a phase where you expect surprises, stay in the loop with manual execution.
-
You are mid-phase with partial execution. Autonomous mode picks up incomplete phases but it does not resume a partially-executed wave. Use
/msd-execute-phase Nto finish a phase that is already in progress.
If a run stops partway through, see Debug a failed execution for how to diagnose what went wrong.
Checking progress during a run
Autonomous mode prints a progress banner before each phase:
MSD ► AUTONOMOUS ▸ Phase 3/7: Auth Middleware [████░░░░] 28%
If you need to check where the run stands mid-session, open another terminal and run:
/msd-progress
Resuming after a stop
If autonomous mode stops — whether you chose "Stop autonomous mode" from the blocker prompt, or the session was interrupted — resume from where it left off:
/msd-autonomous --from 4 # replace 4 with the first incomplete phase number
MSD skips already-complete phases automatically, so it is safe to re-run from an earlier phase number if you are not sure where the run stopped.
If a prior run recorded a Deferred Verification entry in STATE.md, later /msd-autonomous reruns skip that phase instead of re-entering the same deferral prompt. Resume deferred work with the exact command shown in the table:
/msd-verify-work 4 # for verification_deferred_human
/msd-plan-phase 6 --gaps # for verification_deferred_gaps