AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Refacil:status

skill-erikole21-refacil-sdd-ai-status · by Erikole21

Show which phase of the SDD-AI cycle a change is in and the exact command to resume it — use for "where am I?", "how is it going?", "status of the change", "resume", "where did I leave off". Distinct from /refacil:stats (which shows telemetry, token savings, and review metrics). Use /refacil:status to navigate the flow; use /refacil:stats for observability data.

No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-erikole21-refacil-sdd-ai-status

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-erikole21-refacil-sdd-ai-status)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Refacil:status? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

refacil:status — Current Phase and Resume

This skill answers: "In which phase of the SDD-AI cycle is this change, and what command do I run next?"

It is distinct from /refacil:stats:

  • /refacil:statusnavigation: current phase, next skill to run, resume a paused flow.
  • /refacil:statstelemetry: token savings, compact rewrites, CodeGraph calls, review history.

Prerequisites: sdd profile from refacil-prereqs/SKILL.md.

Activation phrases

Invoke this skill for expressions like: "¿en qué va?", "¿cómo voy?", "status del cambio", "retomar", "dónde quedé", "where did I leave off?", "resume", "what's the current state?", "what's next?".

Next-skill mapping

The following table maps each state to the recommended next skill in the normal flow and in the bug fix flow (fix-*):

| State | Normal flow next skill | Bug fix (fix-*) next skill | |-------------------|--------------------------|---------------------------| | proposed | /refacil:propose (approve or adjust) | — | | approved | /refacil:apply | /refacil:apply | | apply-in-progress | /refacil:apply | /refacil:apply | | applied | /refacil:test | /refacil:test | | tested | /refacil:verify | /refacil:review (bugs omit verify) | | verified | /refacil:review | — (n/a: bugs never reach verified) | | reviewed | /refacil:archive | /refacil:archive | | archived | /refacil:up-code | /refacil:up-code | | unknown | Run /refacil:propose to create artifacts | — |

Flow

Without argument — overview of all active changes

  1. Run refacil-sdd-ai sdd list --json to get all active changes.
  1. If the list is empty, inform the user:

`` No active changes found. Run /refacil:propose to start a new change. `` Stop.

  1. For each active change, run refacil-sdd-ai sdd status --json and collect:
  • currentState and stateInferred
  • tasks.done / tasks.total
  • reviewPassed
  1. Present a summary table:

``` === Active changes ===

Change Phase Next command ───────────────────────────────────────────────────────────────── (inferred?) ... ```

For each row, derive the next skill from the next-skill mapping above (use the normal flow unless the change name starts with fix-).

State history is shown only in the detail view — pass a change name as argument to see the full transition log.

With argument — detail for one change

  1. Use $ARGUMENTS as changeName.
  1. Run refacil-sdd-ai sdd status --json and parse the output.
  1. If the command exits 1 (change not found), inform the user and stop.
  1. Resolve currentState:
  • Use status.currentState from the JSON directly.
  • If stateInferred is true, note it as (inferred from artifacts).
  1. Parse stateHistory from memory (if available):
  • Run refacil-sdd-ai sdd get-memory --json.
  • Read the stateHistory array. Each entry is a pipe-separated string "||".
  • Parse each entry with entry.split('|')[state, iso, actor].
  • Show the last 5 entries (most recent last) as a compact history.
  1. Determine the next skill from the next-skill mapping table above.
  1. Present:

``` === Status: ===

Current phase: Last step: Touched files:

State history (last 5): — (by ) ...

Next command: ```

If the change is in archived state, add: `` This change is fully archived. Run /refacil:up-code to push and create the PR. ``

Rules

  • Read-only: this skill does not modify any file, branch, or memory.
  • Graceful degradation: if stateHistory is absent or get-memory fails, show the current state without history. Do not error.
  • Empty list behavior: if sdd list --json returns [], inform the user and stop without error.
  • Bug fix detection: if changeName starts with fix-, use the bug fix flow column in the next-skill table. The bug flow skips /refacil:verify: a tested fix goes straight to /refacil:review, and a fix never reaches the verified state.
  • Flow continuity: if the user confirms affirmatively ("yes", "ok", "go", "continue", etc.) after the status display and there is a single unambiguous next skill, immediately execute that skill. (See METHODOLOGY-CONTRACT.md §5.)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.