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 skills add lttr/claude-marketplace --skill wrgit clone --depth 1 https://github.com/lttr/claude-marketplaceWrote 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/lttr/claude-marketplace/wr)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/wr"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/wr/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/lttr/claude-marketplace/wr"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/wr.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 | $0.00022 | $0.00929 |
| Opus 5.5 | $0.00009 | $0.00372 |
| Sonnet 5.5 | $0.00004 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
wr 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing
Rules for text that is easy to read and comprehend.
-
Get to the point early. In a doc or summary, put the main point near the top. A short answer doesn't need this, just answer naturally.
-
Prefer short sentences. Usually one idea per sentence. But don't chop everything into fragments either.
-
Keep paragraphs manageable. One topic in a few sentences. When it drifts into a second topic, start a new paragraph. Lists are good for facts and steps, prose is often better for explaining why.
-
Use plain words plus real terminology. Common English, plus the established terms of the domain. "Connection pool" and "refresh token" are correct words, not jargon. Avoid invented shorthand and metaphors the reader has to decode. Spell out an acronym the first time it appears, and when a term is unusual, give the plain-English idea first and the term after it.
-
Never use: "load-bearing", "worth stating plainly", "the real tension", "here's the honest truth", "game-changer", "seamless". No emoji, no exclamation marks.
-
Don't splice with em-dashes. Write two sentences instead, or use a colon or parentheses.
-
Vary sentence length. Mix short sentences with longer ones that carry a reason or qualification. Uniformly short prose reads monotone, and splitting a sentence usually deletes the "because" or "so" that carried the argument. The linter reports the spread.
-
Say things once. No closing recap, no restating the same fact in different words. If a rule needs more weight, make it more specific, not more frequent.
-
Know when to stop. A short text is complete when the point is made.
-
Explain, don't just reference. The text should make sense on its own, without opening links or files. Include exact commands or paths only when the reader will use them.
-
Say what a thing is, not what it isn't. Skip the negative setup: "not just a cache, but a lifecycle manager", "this isn't a rewrite, it's a refactor". The same move hides in a comma-joined pair whose second half only negates the first: "the judgement stays with the model, the detection does not". Describe the thing directly. A contrast is fine when the reader genuinely holds the wrong belief you are correcting.
-
Don't announce the point, make it. No "Here's the catch", "Here's the thing", "Turns out", "The punchline is". Write the sentence that was going to follow.
-
Vary the shape of neighbouring sentences. Consecutive sentences built on the same skeleton, or three in a row opening on the same word, read as generated. Also drop participle tails that add nothing: ", underscoring the value of the new cache". A colon opening onto three or four bare nouns is the same move: "Claude writes the text around a project now: commit messages, PR descriptions, README sections, notes". Name the ones that matter in a sentence instead.
-
Name the actor. Prefer active voice: say which component or person does the thing. Passive is fine when the actor is unknown or irrelevant, or when the object is the real topic.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 52 lines · 22 tokens per session scan A 8b78c8314dee
wr is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 14d ago), licensed MIT. It adds 22 tokens to every session and 929 once invoked, about $0.0001 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 2026-09-15.
Other skills, from other repositories
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
hook-factory
Generate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…