Borrowing it
Nothing to install: this file belongs to Cristophereasygoing927/compare-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Cristophereasygoing927/compare-mcp/main/.claude/skills/compare/SKILL.mdgit clone --depth 1 https://github.com/Cristophereasygoing927/compare-mcpWrote 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.
[](https://agentmods.dev/skills/cristophereasygoing927/compare-mcp/compare)<a href="https://agentmods.dev/skills/cristophereasygoing927/compare-mcp/compare"><img src="https://agentmods.dev/badge/skills/cristophereasygoing927/compare-mcp/compare/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.
<a href="https://agentmods.dev/skills/cristophereasygoing927/compare-mcp/compare"><img src="https://agentmods.dev/badge/skills/cristophereasygoing927/compare-mcp/compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00052 | $0.00706 |
| Opus 5.5 | $0.00021 | $0.00282 |
| Sonnet 5.5 | $0.00010 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
compare 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/compare skill
Trigger
User types: /compare <issue description> [--debate] [--providers claude,openai]
Or naturally: "compare models on this bug", "get a second opinion from multiple models"
Workflow
Step 1 — discover
Call compare_models to show the user which providers are enabled.
If fewer than 2 are enabled, stop and tell the user:
Enable at least 2 providers in
~/.compare/config.json. Runcompare_modelsto check.
Step 2 — read code
Use the Read tool to load the relevant file(s). If the user didn't specify a file, use Glob + Grep to find the most relevant file for the issue description.
Respect max_file_lines from config (default 1000). If the file is larger, ask the
user to specify a line range or pass the most relevant section.
Step 3 — dispatch
Call compare_run with the file contents and issue description.
If --providers was specified, pass the provider list.
While waiting, tell the user: "Querying [provider1], [provider2]... (parallel)"
Step 4 — diff
Call compare_diff with the responses.
Display a findings table:
Finding | Providers | Severity
--------------------------|------------------|----------
Memory leak in tile loop | claude, openai | high
Dead code: prevVisible | openai | medium
Show: "Models agreed on X% of findings."
Step 5 — debate (if --debate flag or user asks)
Call compare_debate with the responses.
Display: "Debate complete. [N] findings disputed, [N] additions. [N] API calls made."
Use refined_findings instead of recommended for the todos step.
Step 6 — todos
Call compare_todos with either the diff's recommended list or debate's refined_findings,
plus the file path.
Display the ranked todo list with IDs.
Step 7 — implement
Ask: "Dispatch subagents to implement all [N] todos in parallel? (y/n/select)"
- y: spawn one Agent (subagent) per todo, all in parallel
- select: show numbered list, user picks which ones
- n: stop here
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.
- 2mo ago First seen · 81 lines · 52 tokens per session scan A 40dbaa5ae913
compare is a skill published in the GitHub repository Cristophereasygoing927/compare-mcp (2 stars, last pushed 17d ago), licensed MIT. It adds 52 tokens to every session and 706 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
01-sdlc
Orchestrates a request from framing to a draft pull request, autonomous or supervised, isolating implementation, independent review, and final outcome challenge. Use when the user wants to deliver a change end to end. Not for one step.
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…
05-review
Reviews a change or a diff and says whether it is ready to ship, naming every problem with its fix. Use when the user wants a change checked before it ships. Not for fixing what the review finds, and not for auditing a whole codebase.
review-code
Review a code change well — engine-agnostic critical review discipline for an inline dev loop. Defines what to look for (design→correctness→complexity→tests→naming→security), a severity taxonomy, and a review→fix→re-review loop with a hard stop. Use on "review this code", "review my diff", "is this change good"…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
code-quality
Drive static-analysis code quality in pi-agent-dashboard with Biome (analyze → fix → test), in changed-files or whole-repo mode. Use when asked to "improve code quality", "lint and fix", "clean up warnings", "fix Biome issues", "run static analysis", or when setting a code-quality goal. Skip for one-line edits.