A command that compares skills and other files in their source location with the copies installed for different AI tools.

It helps inspect all differences, compare one target, view file-level statistics, or print a complete unified diff.

It shows what has changed, what is missing, and which local copies may differ before you sync anything.

diff — Command by runkids

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/runkids/skillshare/diff

Clone the repo

git clone --depth 1 https://github.com/runkids/skillshare

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,525 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01525
Opus 5	$0.00000	$0.00763
Sonnet 5	$0.00000	$0.00305
Haiku 4.5	$0.00000	$0.00153

Measured yesterday against content hash 4fe4fbe649d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

website/docs/reference/commands/diff.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

diff

Show differences between source and targets.

skillshare diff              # All targets (interactive TUI)
skillshare diff claude       # Specific target
skillshare diff agents       # Agent targets only
skillshare diff --stat       # File-level changes
skillshare diff --patch      # Full unified diff

diff demo

Interactive TUI

On a TTY, diff launches an interactive TUI with a left-right panel layout:

Left panel — Target list with status icons (✓ synced, ! has diffs, ✗ error)
Right panel — Detail view for the selected target (mode, filters, categorized diffs)
Press Enter to expand file-level diff for a skill
Press / to filter targets, Ctrl+d/u to scroll detail, q to quit

Use --no-tui for plain text output, or pipe to disable TUI automatically.

When to Use

See exactly what's different between source and a target before syncing
Find skills that exist only in a target (local-only, not yet collected)
Identify local copies that could be replaced by symlinks
Inspect file-level changes with --stat or full text diff with --patch

Example Output

claude
  + New 2 skills:
      missing-skill
      another-skill
  ! Local Override 1 skill:
      local-copy
  ← Local Only 1 skill:
      my-local-skill

  2 new, 1 local override, 1 local only

cursor: fully synced

Grouped Multi-Target Output

When multiple targets have identical diff results, they are grouped into a single block to reduce noise:

claude, agents
  + New 2 skills:
      skill-1
      skill-2

cursor
  + New 1 skill:
      skill-1

codex, copilot: fully synced

Targets with different results (e.g. due to include/exclude filters) are still shown separately.

Symbols

Symbol	Label	Meaning	Action
`+`	New	In source, missing in target	`sync` will add it
`+`	Restore	Was in target, deleted	`sync` will restore it
`~`	Modified	Content changed (copy mode)	`sync` will update it
`!`	Local Override	Local copy instead of symlink	`sync --force` to replace
`-`	Orphan	In manifest but not in source	`sync` will prune it
`←`	Local Only	Only in target, not in source	`collect` to import

Read the full file on GitHub · 242 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.

yesterday First seen · 242 lines · 0 tokens per session scan A 4fe4fbe649d9

Subscribe to this mod's changes

diff is a command published in the GitHub repository runkids/skillshare (2,597 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,525 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 2026-08-30.

Writing and docs ai cli codex cursor skills team-management

diff

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

diff

Interactive TUI

When to Use

Example Output

Grouped Multi-Target Output

Symbols

What this file has done since we first saw it

Other commands, from other repositories

constraints

webperf

spec

plan

pm-arch

pm-done