Borrowing it
Nothing to install: this file belongs to adobecom/da-express-milo. 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/adobecom/da-express-milo/stage/.claude/skills/comparison/SKILL.mdgit clone --depth 1 https://github.com/adobecom/da-express-miloWrote 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/adobecom/da-express-milo/comparison)<a href="https://agentmods.dev/skills/adobecom/da-express-milo/comparison"><img src="https://agentmods.dev/badge/skills/adobecom/da-express-milo/comparison/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/adobecom/da-express-milo/comparison"><img src="https://agentmods.dev/badge/skills/adobecom/da-express-milo/comparison.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 | $0.00125 | $0.02508 |
| Opus 5.5 | $0.00050 | $0.01003 |
| Sonnet 5.5 | $0.00025 | $0.00502 |
| Haiku 4.5 | $0.00013 | $0.00251 |
Grade A, and why
comparison 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 1mo 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comparison Skill
Backed by .claude/tools/comparison/compare-branches.mjs (lives in this
repo, not globally), which is independently invokable by any skill/agent. It
calls .claude/tools/qa-worktree/qa-worktree.mjs twice — once per ref, run
CONCURRENTLY (distinct worktree names and ports; both refs are fetched once
up front so the two calls never race on git fetch) — then diffs the
results.
Workflow
-
Get the block name and branch from the invocation args (e.g.
/comparison grid-marquee my-feature-branch). Both are required — ask if either is missing. The branch must already exist onorigin.Watch for swapped/misordered args: if the named "block" produces zero matches when checked (the tool will report
pagesFound: 0), but the named "branch" happens to be a real block name (or vice versa), the user likely gave them in the wrong order — infer the correct assignment rather than failing, and say so. -
Get the baseline (optional). Default is
stage. Override with--baseonly if the user wants to compare two feature branches instead of branch-vs-stage.--baseand--branchmust differ. -
Run the tool (resolve the repo root first — this tool lives inside the checkout, so don't assume cwd is the repo root):
ROOT="$(git rev-parse --show-toplevel)" node "$ROOT/.claude/tools/comparison/compare-branches.mjs" \ --block="<name>" --branch="<branch>" [--base="<base>"]Options worth knowing about:
--mode=<element|full|both>— defaultelement(just the block, not the whole page — full-page screenshots of a long page are slow to render/encode/write and mostly irrelevant to "did this block change"). Use--mode=fullor--mode=bothonly when the user specifically wants to see how the block affected surrounding page layout.--selector="<css>"— override the auto-derived.<block-slug>selector, e.g. when the block's root class doesn't match its name.--concurrency=<n>— pages captured in parallel, per side. Default 6.--timeout=<seconds>— dev-server readiness window per side.--locale=<key>(repeatable) /--all-locales— compare other locales too, not justen(the default). Passed to both sides so page sets match. A locale requested explicitly via--localethat has no local content checkout is an error;--all-localesskips it instead (seelocalesSkipped) — sync locales first withnode .claude/tools/sync-locale-content.mjs --locale=<key>(or--allfor every locale;--listshows what's already synced). Comparing--all-localeson a widely-used block is meaningfully slower — it's still one worktree/dev-server pair per side, but N times the page count, so mention that to the user before running it.
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.
- 1mo ago First seen · 175 lines · 125 tokens per session scan A a80c544edbfe
comparison is a skill published in the GitHub repository adobecom/da-express-milo (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 125 tokens to every session and 2,508 once invoked, about $0.0005 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 2026-09-10.
comparison compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| comparisonadobecom/da-express-milo | Skill | 6 | yesterday | Apache-2.0 | A | 125 | Claude Code |
| ui-ux-architectralvarezdev/ralvaskills | Skill | 2 | 7d ago | GPL-3.0 | A | 77 | Claude Code, Codex |
| accesslint-diffLiHongwei-cn/lihongwei-cn | Skill | 5 | 29d ago | MIT | A | 68 | Claude Code |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |
| prowler-commitprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 20 | Claude Code, Codex |
| prototype-webnexu-io/html-anything | Skill | 9.4k | 25d ago | Apache-2.0 | A | 24 | Claude Code, Codex |