kc-em-plan-review

kc-em-plan-review is a skill for Claude Code, Codex from iamcxa/kc-claude-plugins. It costs 0 tokens per session (1,582 once invoked), scanned A, original, MIT.

A workflow for reviewing a teammate's implementation plan, project, issue, design document, or discussion before development begins.

In plain words
What is it for?
Use it to pressure-test plans, check for duplicate reviews, verify the critical technical assumption, and produce actionable feedback.
Why use it?
It checks the plan's key assumption against real code and looks for blockers that could otherwise fail silently.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also runs codex exec. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the kc-team-ops plugin — 8 skills, 3 agents shipped together

Good fit Use it to pressure-test plans, check for duplicate reviews, verify the critical technical assumption, and produce actionable feedback.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add iamcxa/kc-claude-plugins
Claude Code
/plugin install kc-team-ops

Made for: Claude Code, Codex.

Or install kc-team-ops, the plugin that ships this one along with the rest of its 8 skills, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for kc-em-plan-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-em-plan-review/github.svg)](https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-em-plan-review)
Your own site
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-em-plan-review"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-em-plan-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for kc-em-plan-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-em-plan-review"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-em-plan-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,582 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01582
Opus 5 $0.00000 $0.00791
Sonnet 5 $0.00000 $0.00316
Haiku 4.5 $0.00000 $0.00158

Measured 7d ago against content hash 03ffd7968430, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kc-em-plan-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

kc-team-ops/skills/kc-em-plan-review/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EM Plan Review

Review a teammate's plan BEFORE build starts, as the EM. The goal is not to list correct-sounding risks — it is to change the outcome: convert the load-bearing assumption from inherited to verified, find the blocker that would silently fail, and hand back a calibrated, actionable message.

Source of truth for the lenses = the user's current ~/.claude/CLAUDE.md (Conviction Calibration, Escalation Mantra, E2E-First Acceptance). This skill embeds a compact checklist; read ${CLAUDE_PLUGIN_ROOT}/reference/em-plan-review-lens.md for the full rubric and ${CLAUDE_PLUGIN_ROOT}/reference/venue-format-rules.md for delivery.

Pipeline (run in order)

digraph empr {
  rankdir=TB; node [shape=box];
  p0 [label="P0 Ingest (MAIN convo / MCP)"];
  p1 [label="P1 EM-lens review"];
  p2 [label="P2 Keystone verification (real code)"];
  p3 [label="P3 De-dup vs existing reviews"];
  p4 [label="P4 Cross-model pressure-test (codex)"];
  p5 [label="P5 Deliver (gated)"];
  p0 -> p1 -> p2 -> p3 -> p4 -> p5;
}

P0 — Ingest & context (MAIN CONVERSATION ONLY)

MCP tools cannot run inside a subagent — do P0 in the main conversation.

  • Pull the plan source in full:
    • Linear project → get_project (+ milestones, members) + list_issues + list_milestones + get_issue(includeRelations) on key issues to capture the dependency graph.
    • Also handle: a single Linear issue, a Slack thread, a design doc, a PR.
  • Also pull the originating discussion + any existing reviews/comments (e.g. the Slack thread that spawned the project, prior Linear comments). This input is what makes P3 possible — skip it and you will duplicate a teammate.
  • If you cannot retrieve the actual plan source (wrong Linear workspace, missing access, dead link, MCP pointed elsewhere), STOP and report it — never review an imagined plan reconstructed from the request summary. A review anchored to assumptions instead of the real artifact is theater, and it manufactures false confidence at exactly the wrong moment.

Read the full file on GitHub · 88 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 88 lines · 0 tokens per session scan A 03ffd7968430

Subscribe to this mod's changes

kc-em-plan-review is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,582 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.