skill-diff

A comparison command for checking the same coding skill in Claude, Codex, Copilot, and Cursor. It shows where the skill exists and how the versions differ.

In plain words
What is it for?
Use it to compare a named skill across coding tools, review changes between versions, and find out which tools provide it.
Why use it?
It removes the need to inspect each tool's skill files separately. You can quickly see whether versions match or have different instructions, metadata, or sizes.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/athola/skrills/skill-diff
Clone the repo
git clone --depth 1 https://github.com/athola/skrills
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 245 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00245
Opus 5 $0.00009 $0.00122
Sonnet 5 $0.00004 $0.00049
Haiku 4.5 $0.00002 $0.00024

Measured 2d ago against content hash 69795bcbf231, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-diff 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 2d 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.

plugins/skrills/commands/skill-diff.md · 30 lines

What it actually says

Skill Diff

Compare skill versions across CLIs using the skrills MCP server.

Use the mcp__plugin_skrills_skrills__skill-diff tool with:

  • name: Skill name to compare (e.g., "commit", "review-pr")
  • context_lines: Number of context lines around differences (default: 3)

Parse $ARGUMENTS for:

  • First positional argument: Skill name (required)
  • --context <n> or -C <n>: Context lines to show

Report comparison results including:

  • Which CLIs have the skill
  • Unified diff between versions
  • Frontmatter differences
  • Token count differences
  • Whether versions are identical

Handle errors:

  • If skill name missing: Prompt for skill name
  • If skill not found in any CLI: Report and suggest search command
  • If skill exists in only one CLI: Report single-source state
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. 2d ago First seen · 30 lines · 18 tokens per session scan A 69795bcbf231

Subscribe to this mod's changes

skill-diff is a command published in the GitHub repository athola/skrills (69 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 245 once invoked, about $0.0001 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 2026-08-30.