Workflow status
Read-only dashboard of ai-sdlc-harness runs in this workspace. USER-ENTRY — invoke only when the user explicitly runs /workflow-status; never autonomously, never from a subagent (guard-enforced).From its SKILL.md
npx -y skills add MostAshraf/ai-sdlc-harness --skill workflow-statusAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 15 stars15 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.2 KB, as published. Nobody here has run it
workflow-status (read-only)
${CLAUDE_PLUGIN_ROOT}/bin/harness status— every run: cursor, mode, work item, task statuses, decided gates, flagged-event count, and ahealthverdict (HEALTHY|DEGRADED: did the run MACHINERY degrade — stalls, lost evidence; flagged events alone don't flip it, and neither do the several spawns a pipelineddevelopkeeps in flight — only one the run has moved PAST or launched in a round a gate has since closed out, whose evidence is never arriving). Anabortedfield marks a run ended by the abort verb (terminal); anerrorfield marks a run whose state failed integrity verification (itsremediationnames the reseal command) — the rest of the dashboard still renders.- Render it as a compact table for the user; for a run they ask about,
drill in with
${CLAUDE_PLUGIN_ROOT}/bin/harness show --run <run>— whoseoutstanding_spawnsnames each in-flight spawn's task, mode, agent id, launching step and launch time, so "which lane is still working" needs no ledger read (andlegacy_spawn_pendings, if non-empty, names spawns launched before an upgrade whose capture can no longer land) — plus the ledgers (events.ndjson— the "what happened" trail;tokens.ndjson— spend) and compose the per-task timeline: status + review rounds + stalls + flagged events + gate evidence. - Offer
${CLAUDE_PLUGIN_ROOT}/bin/harness metrics --run <run>— regeneratesreports/metrics.md, the human-readable table view of the same ledgers (run health, timings, tasks, verdicts, aggregated tokens, flagged events). Works at any live step, not just the terminal metrics step; it's a deterministic projection, so regenerating is always safe. - Otherwise STRICTLY read-only: no state changes, no cursor moves, no ledger writes — the report above is the one derived, regenerable output; everything else only reads what the authority already records.