mcp-cli: Skill for Claude Code

.claude/skills/coherence-review/SKILL.md

coherence-review is a skill for Claude Code from theshadow27/mcp-cli. It costs 52 tokens per session (883 once invoked), scanned A, original, MIT.

A review workflow for comparing several related pull requests, which are proposed code changes, as one feature area.

In plain words
What is it for?
Use it after related pull requests are merged, or when a complex coding session suggests that changes may be heading in different directions. It can file issues for problems it finds.
Why use it?
It helps catch duplicated solutions, disconnected changes, and architectural disagreements before they spread through the project.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md.

This is theshadow27/mcp-cli's own configuration. It tells Claude Code how to work on mcp-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to theshadow27/mcp-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/theshadow27/mcp-cli/main/.claude/skills/coherence-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/theshadow27/mcp-cli

Made for: Claude Code.

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 coherence-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/theshadow27/mcp-cli/coherence-review.svg)](https://agentmods.dev/skills/theshadow27/mcp-cli/coherence-review)
Your own site
<a href="https://agentmods.dev/skills/theshadow27/mcp-cli/coherence-review"><img src="https://agentmods.dev/badge/skills/theshadow27/mcp-cli/coherence-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 883 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 $0.00052 $0.00883
Opus 5 $0.00026 $0.00441
Sonnet 5 $0.00010 $0.00177
Haiku 4.5 $0.00005 $0.00088

Measured 8d ago against content hash ec781d966b42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

coherence-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 8d 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.

.claude/skills/coherence-review/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coherence Review

Review a batch of related PRs for architectural consistency. Catches integration issues early — before multiple sessions build on top of a flawed foundation.

Input

A feature area description and/or PR numbers. Parse from: $ARGUMENTS

Examples:

  • /coherence-review auth overhaul PRs #301 #305 #310 #312
  • /coherence-review daemon session lifecycle
  • /coherence-review 350 351 352 353

When to Run

  • After every 3-4 issues in the same feature area merge
  • When a session's cost exceeds $15 (sign of complexity/struggle)
  • When you suspect related PRs may have diverged architecturally

Workflow

1. Gather Context

If PR numbers were provided, fetch each:

gh pr view <number> --json title,body,files,mergedAt
gh pr diff <number>

If only a feature area was provided, find recent merged PRs in that area:

gh pr list --state merged --limit 20 --json number,title,files,mergedAt

Filter to PRs that touch relevant files. Build a picture of what changed across the batch.

2. Review for Architectural Consistency

For each concern below, compare across all PRs in the batch:

Consistent patterns
  • Do the PRs use the same approach for the same problem? (e.g., error handling, logging, IPC patterns)
  • Are naming conventions consistent across the changes?
  • Do similar features follow the same structure?
Integration points
  • Do the PRs interact correctly where they touch shared code?
  • Are there missing integration points where PRs should connect but don't?
  • Did any PR change an interface that another PR depends on?
Duplicated work
  • Did multiple PRs implement the same or similar functionality?
  • Are there new utilities or helpers that overlap with existing ones?
  • Could shared abstractions reduce duplication?
Wrong directions
  • Does any PR introduce a pattern that contradicts the project's conventions?
  • Are there changes that will be painful to maintain or extend?
  • Did any PR optimize for the wrong thing (e.g., premature abstraction, unnecessary flexibility)?

Read the full file on GitHub · 106 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. 8d ago First seen · 106 lines · 52 tokens per session scan A ec781d966b42

Subscribe to this mod's changes

coherence-review is a skill published in the GitHub repository theshadow27/mcp-cli (2 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 883 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-31.