Plan Review
Review a dated plan under docs/specs/ for missing steps, wrong assumptions, or guideline violations before implementation begins.
Install
$ agentstack add skill-konh-claudetools-plan-review ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-konh-claudetools-plan-review) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Review the latest dated plan under docs/specs/ (or the plan file specified in $ARGUMENTS) for potential problems before implementation begins.
Plan Discovery
With $ARGUMENTS: resolve against docs/specs/ — look for docs/specs/_/plan.md using the full dated spec identifier.
Without $ARGUMENTS:
- List all
*/plan.mdfiles underdocs/specs/ - Extract the
YY_MM_DD_HHprefix from each folder - Use the file with the latest timestamp prefix
Rules
- Read the plan file first, then read relevant project rules (
CLAUDE.mdand any project rules directory) that apply to the plan's scope - Spawn a sub-agent to perform the review independently (it should re-read the plan and rules itself)
- The sub-agent must NOT modify any files — review only
- Present all concerns at once, then ask the user to approve all or indicate which to skip
- Keep each point short: state the problem, why it matters, and a concise fix — no nitpicking on style or naming
- Format proposed fixes as
diffblocks (lines removed prefixed with-, lines added prefixed with+) alongside the plain-text explanation - Focus on: missing steps, wrong assumptions, inconsistency with project guidelines, architectural mismatches, and anything likely to cause rework during implementation
- If no real concerns are found, say so briefly and stop
Sub-agent prompt template: > Review the plan at [plan path]. Read it in full, then read the relevant project rules for the plan's scope (check CLAUDE.md and any project rules directory for domain-specific guidance). Identify concerns — missing steps, wrong assumptions, guideline violations, architectural mismatches — that would cause problems during implementation. Return a numbered list of concerns, each with: problem, why it matters, proposed fix. For each fix, include a diff block showing the before/after lines (lines removed prefixed with -, lines added with +). Skip style/naming nitpicks. If there are no real concerns, say so.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: KonH
- Source: KonH/ClaudeTools
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.