speq-plan — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited speq-plan (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill is a thin orchestrator. It conducts the clarifying interview, collects context, and then delegates the heavy planning work (spec delta authoring, test mapping, task decomposition) to the planner-agent sub-agent.
Why this split: Orchestration (asking questions, reading a few files, shepherding the workflow) does not need expensive reasoning. The actual planning — architectural tradeoffs, MECE decomposition, ADR authoring — does. Splitting the work concentrates reasoning on the step that benefits from it.
Invoke before starting:
/speq-cli — Spec discovery and searchThe planner-agent sub-agent invokes /speq-code-tools, /speq-ext-research, and /speq-cli itself.
Use speq CLI to understand what exists:
speq domain list
speq feature list
speq search query "<relevant terms>"This is lightweight — enough context to ask good clarifying questions, not a full exploration.
Apply the Socratic Method via AskUserQuestion — never assume. Decompose the problem space using MECE partitioning:
Record answers in a concise interview summary to pass to the sub-agent.
Pattern: <verb>-<feature-scope>[-<qualifier>]
| Verb | When |
|---|---|
add | New feature |
change | Modify existing |
remove | Deprecate/delete |
refactor | Restructure, same behavior |
fix | Bug or spec mismatch |
Spawn the planner sub-agent with everything it needs:
Task(
subagent_type="planner-agent",
description="Plan <plan-name>",
prompt="""
## Plan Name
<plan-name>
## User Intent
<1-3 sentence summary of what the user wants>
## Clarifying Interview Results
<verbatim Q&A from the AskUserQuestion exchanges>
## Existing Context
<output of relevant `speq search` / `speq feature get` calls>
## External Research
<any research already conducted, or "none — agent to research as needed">
## Your Task
Produce spec deltas and plan.md per the `planner-agent` workflow. Tag tasks
requiring deep reasoning with [expert] so the implementer orchestrator can
route them to implementer-expert-agent.
Return the list of files created and the validation result.
"""
)When the sub-agent returns:
speq plan validate <plan-name> passed (re-run if uncertain)/speq-implement <plan-name> to continue/clear to start implementing with a fresh context windowExitPlanMode and ask to proceed with cleared contextspecs/
├── <domain>/<feature>/spec.md # Permanent
├── _plans/<plan-name>/ # Active
└── _recorded/<plan-name>/ # Archived| Step | Performed by | Why |
|---|---|---|
| Discovery, interview, coordination | This skill (pins Sonnet) | Conversational, tool-call heavy |
| Spec delta authoring, ADR, task decomposition | planner-agent sub-agent | Reasoning-heavy; defect here compounds through implementation |
The sub-agent pins its own model and effort in its frontmatter, so planning quality is independent of the parent session's configuration.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.