Skip to content
Agentmart
Submit a tool

spae-check

Per-task verification gate for SPAE.

Skill by mystilleef

IndexedMIT★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mystilleef-spae-check

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Per-task verification gate for SPAE. Compares active task Intent, Acceptance, and Verification against repo evidence; routes gaps to /fix or advances a clear task.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/spae-check

What's inside

Skill name
spae-check
Description
Per-task verification gate for SPAE. Compares active task Intent, Acceptance, and Verification against repo evidence; routes gaps to /fix or advances a clear task.
License
MIT
Instructions
210 lines in SKILL.md · view on GitHub

Files (6)

  • SKILL.md
  • FIX.md · references/
  • STATE.md · references/
  • cleanup-guide.md · references/
  • prose-protocol.md · references/
  • shell-command-guide.md · references/

SKILL.md (first lines)

# Check (`SPAE`)

## When to use

- `STATE.json` reports `phase: check`.
- Cursor names active task.

## Goal

- Compare active task implementation against PLAN.md Intent, Acceptance,
  and Verification.
- Route gaps to /fix or advance clear task.

## Input

Read:

- `.spae/current/STATE.json` (consult `references/STATE.md` for field
  reference, directives, and phase snapshots)
- Active task section from `.spae/current/PLAN.md` (`Intent`,
  `Acceptance`, `Verification`)
- Source files and test logs scoped to active task

## Workflow

1. **GATE**—Read `.spae/current/STATE.json`; confirm `phase: check` and
   `active_task_id`. Self-heal metadata: inject missing `version`
   (`"1.0"`), `workstream` (from symlink or directory path), and
   `status` (`"active"`). Self-heal state drift: if
   `tasks[`active_task_id`]` reads `"todo"` or lacks an entry, set it to
   `"in_progress"` and write `STATE.json` before proceeding. Halt on
   state drift: if `tasks[`active_task_id`]` reads `"done"`, halt. Read
   active `PLAN.md` task section; confirm title, `Intent`, `Acceptance`,
   `Verification`. Halt on _unparseable_ JSON, unrecognized phase, or
   active task absent from `PLAN.md`; report and make no changes.
2. **ORIENT**—Verify active task; hand off to `/fix`, `/build`, or
   `/verify`. Leave source, tests, `config`, docs, `PLAN.md`, `SPEC.md`,
   task scope, and `workstream` completion untouched.
3. **PLAN**—List active-task `Acceptance` outcomes and `Verification`
   steps. Map evidence for declared `Intent`; scope source/test reads to
   active task. Never read `SPEC.md`.
4. **ACT**—Execute:
   - Run active-task verification steps and project checks. Without
     automation, inspect source, logs, or scripted probes for observable
     behavior.
   - Confirm every `Acceptance` outcome and `Intent` against evidence.
   - Label findings with exactly two tags:
     - **Gap**: unmet `Acceptance`, failed `Verification`, `Intent`
       mismatch, speculative abstraction, _unrequested_ complexity,
       defensive bloat beyond task `Scope`, or a task-introduced cleanup
       violation within declared task scope per
       `references/cleanup-guide.md`. Include unmet item, file:line,
       expected vs actual, reproducible evidence. Blocks a clear result.
       Never flag pre-existing uncommitted files or edits outside task
       scope as gaps.
     - **Observation**: minor concern outside task scope, `unrequested`
       edge-case coverage, theoretical risk, or pre-existing uncommitted
       files outside task scope. Report only; never write to `FIX.md` or
       affect the verdict.
   - Draft gaps per `references/FIX.md` schema; consult
     `references/prose-protocol.md`.
5. **VERIFY**—Reconcile every `Acceptance`, `Verification`, and `Intent`
   against evidence. Clear verdict only with zero gaps. Confirm drafted
   `FIX.md` matches `references/FIX.md` structure.
6. **PERSIST**—Apply one verdict:
   - **Gap found**: create/overwrite `.spae/current/FIX.md` per
     `references/FIX.md`. Write `STATE.json`: `phase: fix`; preserve
     status, cursor, task registry, version, workstream. Active task
     stays `in_progress`.
   - **Task clear, tasks remain**: write `STATE.json`: mark active task
     `done`, advance cursor to next `"todo"` task, `phase: build`.
   - **Final task clear**: write `STATE.json`: mark active task `done`,
     retain cursor active task ID, `phase: verify`.
   - **All branches**: re-read `STATE.json` after writing; on a field
     mismatch, rewrite and re-read before `REPORT`.
7. **REPORT**—Emit result per directives. Template B after gap, D after
   clear _nonfinal_ task, E after clear final task. Observations under
   Findings only.

## Directives

- Optimize for agent, token, and context efficiency.
- Consult `references/shell-command-guide.md` for command safety,
  timeouts, redirects, and environment directives.
- Consult `references/cleanup-guide.md` for self-introduced-artifact
  scope, checklist, and uncommitted working-tree safety directives.
- Follow canonical `SPAE` Step 5 `/check` contract on conflicts.
- Focus on active-task evidence; prefer existing project checks.
- Treat pre-existing uncommitted files and modifications outside active
  task scope strictly as external baseline.
- Enforce `KISS` and `YAGNI`; flag `Intent` mismatches over speculative
  scope or defensive bloat.
- Ground bloat findings in the diff; never flag hypothetical future
  risk, stylistic preference, or _unshipped_ edge case.
- Relegate `unrequested` edge-case coverage, theoretical risks, and
  defensive bloat suggestions to observations; forbid writing them to
  `FIX.md`.
- Refine and optimize `FIX.md` for agent consumption: agents read it for
  varied purposes, with no memory of this run; keep it self-contained,
  explicit, and token-dense.
- Keep gaps concrete, reproducible, enough to close without `PLAN.md`.
- Preserve task-plan wording verbatim in `FIX.md` `## Intent`.
- Write only current actionable gaps to `FIX.md` per
  `references/FIX.md`; report observations in summary only.
- Consult `references/prose-protocol.md` before drafting `FIX.md`.

## Constraints

- Read source, tests, `config`, docs, logs only; write only
  `.spae/current/FIX.md` and `.spae/current/STATE.json`.
- Never read/edit `.spae/current/SPEC.md`; never edit
  `.spae/current/PLAN.md`.
- Never edit source, tests, `config`, docs, or non-`SPAE` project files.
- Never flag, write to `FIX.md`, or request deletion of pre-existing
  uncommitted files outside active-task scope.
- Never claim `workstream` completion (only `/verify` holds that
  authority).
- Never add artifacts beyond canonical `SPAE` files or fields beyond
  `STATE.json` schema.

From mystilleef/spae-framework, MIT.

More from mystilleef/spae-framework

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Oct 23, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from mystilleef

Cite this page

spae-check skill. Agent Mart. https://agentmart.dev/skills/mystilleef-spae-check (last updated 2026-10-24)