Planning WorkflowsCAUTION
Backend for AI coding agents on CloudBase — database, auth, functions via Plugin, Skills & MCP.
Overview
Backend for AI coding agents on CloudBase — database, auth, functions via Plugin, Skills & MCP.
7d16f0c5570cOBSERVED · 2026-10-10Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| cursor | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: planning-workflows description: Spec and no-spec planning workflows derived from local slash commands (requirements, design, tasks). --- # Planning Workflows (spec / no-spec) This skill standardizes how to choose and execute planning modes using local slash commands. ## When to use this skill Use this skill when the user: - wants a full spec workflow before implementation - wants to skip spec and execute directly for small scoped tasks - asks how to decide between spec vs no-spec ## Source of truth - `references/source-commands.md` ## Decision rules - Prefer **spec** when work is new/complex, cross-module, risky, or acceptance criteria are unclear. - Prefer **no-spec** when work is small, low-risk, well-scoped (docs/config/simple fixes). ## Execution rules 1. Read the matching command template from `references/source-commands.md`. 2. Follow it as a phase gate workflow: - do not skip required confirmations when running spec mode - keep scope tight when running no-spec mode 3. Keep artifacts in the repo conventions (e.g. `specs/<name>/...`) when spec is selected. - `specs/` is a local-only directory in this repo: never `git add` it (it is gitignored). Sync / retrieve it through the private archive described in `AGENTS.md` section `<internal_dirs>`. ## Command mapping See `references/command-catalog.md`.
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (5)
.agents/skills/api-contract-review
.agents/skills/cloud-api-recipe-authoring
.agents/skills/codebuddy-ide-mcp-upgrade
.agents/skills/doc-freshness-review
.agents/skills/docs-workflows
Gates applied: no_behavioural_pass.
7d16f0c5570cfull audit observations/trust-audit/skill/tencentcloudbase__planning-workflows.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 7d16f0c5570c | CAUTION | B | 89 | first audit |
Questions
What does the Planning Workflows skill do?
Backend for AI coding agents on CloudBase — database, auth, functions via Plugin, Skills & MCP.
Is Planning Workflows safe to install?
With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Planning Workflows access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Planning Workflows work with?
Its documentation mentions cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (7d16f0c5570c), read on 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.