power-skills-diff

A command for comparing two versions of a coding-agent skill, showing how its instructions changed over time.

In plain words
What is it for?
Use it to compare current, previous, or named versions, optionally side by side or limited to a particular section.
Why use it?
It makes it easier to review updates, investigate regressions, compare project and shared copies, or prepare a rollback.

Command

Part of the fire-flow plugin — 44 commands, 15 agents shipped together

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/thierryn/fire-flow/fire-skills-diff
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow

Or install fire-flow, the plugin that ships this one along with the rest of its 44 commands, 15 agents.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,151 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00012 $0.03151
Opus 5 $0.00006 $0.01576
Sonnet 5 $0.00002 $0.00630
Haiku 4.5 $0.00001 $0.00315

Measured 3d ago against content hash 32c1011c0cbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

power-skills-diff scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

v1_content=$(cat ~/.claude/plugins/dominion-flow/skills-library/{category}/{skill-name}.md)
commands/fire-skills-diff.md · 507 lines

How it starts

The opening of the file, as written. The whole thing — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fire-skills-diff - Compare Skill Versions

Compare two versions of a skill to see what changed between them.

Purpose

  • Understand how a skill evolved
  • Review changes before rollback
  • Compare project vs global versions
  • Audit skill modifications
  • Learn from skill improvements

Arguments

Argument Required Default Description
skill Yes - Skill path: {category}/{skill-name}
v1 No current First version (base)
v2 No previous Second version (compare)

Usage Examples

# Compare current with previous version
/fire-skills-diff database-solutions/n-plus-1

# Compare two specific versions
/fire-skills-diff database-solutions/n-plus-1 1.0.0 2.0.0

# Compare current with specific version
/fire-skills-diff security/jwt-auth current 1.2.0

# Compare project vs global version
/fire-skills-diff api-patterns/pagination project global

# Side-by-side output
/fire-skills-diff performance/caching 1.0.0 2.0.0 --side-by-side

# Show only specific sections
/fire-skills-diff testing/snapshot --section "Code Example"

Process

Determine which versions to compare:

Default behavior:

  • v1 = current (HEAD)
  • v2 = previous (HEAD~1)

Special keywords:

  • current or head = Latest version
  • previous or prev = One version before current
  • project = Version in project library
  • global = Version in global library
  • X.Y.Z = Specific semantic version
  • {commit-hash} = Specific git commit
# Resolve v1
if v1 == "current" or v1 == "head":
    v1_ref = "HEAD"
elif v1 == "project":
    v1_ref = "HEAD" (in project library)
elif v1 == "global":
    v1_ref = "HEAD" (in global library)
else:
    v1_ref = find_commit_for_version(skill, v1)

# Resolve v2 similarly

Fetch content for both versions:

cd ~/.claude/plugins/dominion-flow/skills-library

# Get v1 content
v1_content=$(git show {v1_ref}:{category}/{skill-name}.md)

# Get v2 content
v2_content=$(git show {v2_ref}:{category}/{skill-name}.md)

# For project vs global comparison
v1_content=$(cat ~/.claude/plugins/dominion-flow/skills-library/{category}/{skill-name}.md)
v2_content=$(cat ~/.claude/fire-skills-global/{category}/{skill-name}.md)

Read the full file on GitHub · 507 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. 3d ago First seen · 507 lines · 12 tokens per session scan B 32c1011c0cbd

Subscribe to this mod's changes

power-skills-diff is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 21d ago), licensed MIT. It adds 12 tokens to every session and 3,151 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.