workflow-status
Read-only workflow sensor: run the deterministic script, read the fixed machine envelope, interpret the recommendation. Never edits. Triggers: "workflow-status", "workflow status", "what can I build next".
How do I install this agent skill?
npx skills add https://github.com/gtrabanco/agentic-workflow --skill workflow-statusIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill is a read-only status sensor designed to track project progress, Git state, and GitHub activity. It provides a structured summary of the workflow without modifying any files. While it processes data from external sources like pull requests and roadmap files, it incorporates specific security best practices, such as using verified metadata labels instead of parsing untrusted text for status updates.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
Workflow Status (the orchestrator's sensor)
One read-only pass that answers, in a single fixed JSON envelope: what exists,
what is blocked on what, what is startable right now, and what the recommended
next command is. The script is the deterministic producer:
scripts/workflow-status.mjs executes the published SENSOR_CORE sequence
(steps 1–9 including 6a) and prints the envelope. This skill runs the script,
reads the JSON, interprets it against the references below, and prints the human
report — it never assembles the envelope by hand.
Turn contract — verify before ending the turn
✓ The script was RUN — `bun scripts/workflow-status.mjs [--json-only]
[--last-envelope <json|path>] [--compact]` (node is the fallback when bun is
absent, per the repository's runtime convention); the envelope is the script's
stdout, never assembled by the model
✓ Nothing was edited, committed, pushed, or created — read-only, always
✓ `next.recommended` is non-bare (carries the unit's slug/NN, never a bare
`/unit-lane`) AND the script computed it from the unit's resolved status:
`idea`/`defined` → `/unit-lane <slug>` (or `/unit-lane --fix <n>` for a fix);
`planned`/`in-progress` → `/execute-phase <NN>` (its triage block is the
authority; no separate plan-receipt currency check, step 6a)
✓ `detail.crash_recovery` carries a verdict from the decision table and the
envelope `state` matches it (CLEAN→OK, RESUMABLE→CONTINUE,
AMBIGUOUS→NEEDS_INPUT)
✓ Every `detail.design_candidates[].next` begins with `/unit-lane `
✓ Every degraded dimension is named in `detail.degradations` as
`unavailable-<source>-<cause>` — and, when `--last-envelope` was supplied, the
no-progress guard's `workflow_observations` note is present (never a silently
repeated bland recommendation)
✓ The envelope is emitted on **every** invocation, including a same-session
natural-language follow-up about state — never replaced by prose
✓ The human-readable summary is printed, then the machine envelope (the script's
JSON) is the ABSOLUTE last output
With --json-only, skip the human-readable summary: print the envelope alone.
Compact mode — --compact
--compact emits the same envelope with repository history dropped (~half the
bytes on a mature repo); the exact keep/drop set is in
envelope fields.
When to use
- Between orchestration steps: an external driver runs it to decide the next command and model tier without parsing prose.
- Before picking work manually: "what can I start right now?"
- Not for judging quality (
review-change/audit-pr) or product health (product-audit) — this skill reports state, it never judges.
Step 0 — Discover the project (always first)
Per the agent guide's Workflow conventions + documentation map. The
script reads what THIS skill needs (docs/features/ROADMAP.md, the fix index
docs/fix/README.md, every in-flight feature folder's TASKS.md +
progress.md + review-findings.md, and docs/workflow/REPOSITORY_STATE.md);
read them yourself only to interpret a field the script emitted.
Progressive loading — fixed sensor route
The reference allowlist is exactly the seven linked paths below. Never invent or
read another references/ path. This skill is a read-only sensor.
- sensor core — the sequence the script executes
- crash recovery
- envelope core
- envelope fields
- pre-execution evidence
- guardrails
Add sensor signals only when a unit, issue,
finding, or recommendation exists; an empty project skips that file but still
emits the empty shapes defined by envelope fields. Add
portability only when the platform actually lacks a
named primitive. --json-only does not skip any baseline file.
Portability
The sensor uses repository and forge commands only. When a named agent feature is unavailable, follow portability without changing the JSON contract.
Relationship to other skills
- The sensor counterpart to
advance's conductor: an external orchestrator (oradvanceitself) callsworkflow-status→ routes on the envelope → invokesunit-lane/execute-phase/review-change/audit-pr/triage-issuedirectly, choosing the model per step — the same loop without the in-agent autopilot. - Read-only sibling of
audit-docs(which judges coherence and can fix) andproduct-audit(which judges health): this one only reports state. - Schema owner:
orchestration-envelope(internal).
Done when
- The script ran and every claim in the report comes from its envelope — nothing inferred from memory, nothing assembled by hand.
detail.design_candidates,detail.features,detail.fixes,detail.startable_now,detail.blocked_units,detail.open_prs,detail.untriaged_issues,detail.urgent,detail.degradations, anddetail.crash_recoverywere read from the envelope, and the envelopestatematches the crash-recovery verdict.- With
--last-envelopesupplied: the no-progress guard ran — a stalled/unit-lanehint surfaces as aworkflow_observationsnote, never a silent bland repeat, with no new write path introduced. - The human summary (unless
--json-only) and the envelope are printed, envelope last. - Nothing was modified anywhere.
- When the envelope carries
next.continuation, the next-command echo quotes the emittednext.continuation(renderingfor display), never author exact command tokens; the human-facing prose→ Next:block below stays.
→ Next: the envelope's next.recommended command — it is computed from the
actual state, so it IS the recommendation
· a human overview → read the printed table
· orchestrating programmatically → parse the script's JSON
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/gtrabanco/agentic-workflow/workflow-status">View workflow-status on skillZs</a>