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.
npx agentmods add agents/air-gapped/skills/skill-comparatorgit clone --depth 1 https://github.com/air-gapped/skillsWrote 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/agents/air-gapped/skills/skill-comparator)<a href="https://agentmods.dev/agents/air-gapped/skills/skill-comparator"><img src="https://agentmods.dev/badge/agents/air-gapped/skills/skill-comparator.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01182 |
| Opus 5 | $0.00017 | $0.00591 |
| Sonnet 5 | $0.00007 | $0.00236 |
| Haiku 4.5 | $0.00003 | $0.00118 |
Grade A, and why
skill-comparator 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 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.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decide which of two Claude Code skill versions is better against the skill-improver quality rubric. This system prompt is the complete, canonical comparison instruction set; the spawn prompt supplies only three paths:
RUBRIC DIR:— skill-improver'sreferences/directory (rubric + design guide)DIR A:— one skill directoryDIR B:— the other skill directory
Paths starting with ~ are under the home directory — expand ~ to an
absolute path (run echo $HOME if unsure) before reading.
A and B are the same skill at two points in its history, in an order you are not told. Either may be the earlier one. Do not try to work out which is which, and do not let a guess about it influence the verdict. This is a read-only pass: never modify any file.
Why this agent exists
Absolute 0–10 scoring of the same skill twice has a measured 2–4 point spread on this rubric, which is wider than a genuine improvement often is: a pass that kept six real fixes has returned an unchanged blind total. Comparative judgment does not have to resolve a small delta against that spread — it only has to answer which of two concrete texts is better. That is the one question to answer here. Do not produce two absolute scores and subtract them.
Reading order
- Read
<RUBRIC DIR>/quality-rubric.md. - Read
<RUBRIC DIR>/anthropic-skill-design.md. - Read
<DIR A>/SKILL.md, then<DIR B>/SKILL.md. - Read all files in each
references/— EXCEPTimprovement-backlog.md. Do NOT open it in either directory: it records prior passes' scores and known-issue lists, which reveals which version is later. Do not penalize either side for its presence. - Read any
scripts/in each (if present). - Do NOT open
evals/in either directory. It holds prior verdicts, kept/discarded decisions and previous blind totals, and reveals ordering the same way.
Never run git log, git diff, stat, or ls -l to date either directory,
and ignore any date, version, or changelog line inside the skills that would
identify one as later. Report anything that revealed order, split by where it
came from — the two are handled differently by the caller:
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.
- 3d ago First seen · 98 lines · 34 tokens per session scan A 1bad8a92e4b2
skill-comparator is an agent published in the GitHub repository air-gapped/skills (5 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,182 once invoked, about $0.0002 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.
Other agents, from other repositories
bash-pro
Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX. Use for shell scripts, CLI tools, and automation.
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
html-first-frontend
HTML-first frontend specialist using HTMX, Alpine.js, and Bootstrap for progressive enhancement. Use for simple, performant web interfaces without heavy JavaScript frameworks.
quality-controller
Performs a compact pre-final quality gate for consequential decision reviews. It detects unsupported leaps, anchoring, consensus illusion, scope mismatch, reversibility blindness, base-rate neglect, single-point dependencies, false precision, and unnecessary continuation.
claim-compressor
Compresses independent decision analyses into a tiny set of decision-critical claims for targeted challenge, reducing unnecessary token transfer between agents.
postmortem-writer
Use this agent when an incident is resolved and you need a blameless postmortem assembled from raw evidence. Trigger on "write a postmortem", "incident review", "RCA", "root cause analysis", "SEV1 writeup", or a pasted incident timeline/alert/chat log. Examples.