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 skills/llmtooling/cloudscraper-mcp-server/ruff-devnpx skills add LLMTooling/cloudscraper-mcp-server --skill ruff-devgit clone --depth 1 https://github.com/LLMTooling/cloudscraper-mcp-serverWhat 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 | $0.00129 | $0.01808 |
| Opus 5 | $0.00064 | $0.00904 |
| Sonnet 5 | $0.00026 | $0.00362 |
| Haiku 4.5 | $0.00013 | $0.00181 |
Grade A, and why
ruff-dev 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files 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.
- references/configuration.md 28 KB
- references/contributing.md 45 KB
- references/editors/features.md 3.8 KB
- references/editors/migration.md 5.6 KB
- references/editors/overview.md 1.6 KB
- references/editors/settings.md 20 KB
- references/editors/setup.md 15 KB
- references/faq.md 30 KB
- references/formatter/black.md 22 KB
- references/formatter/overview.md 19 KB
- references/INDEX.md 2.9 KB
- references/installation.md 2.6 KB
- references/integrations.md 5.3 KB
- references/linter.md 17 KB
- references/preview.md 3.4 KB
- references/ruff.md 5.1 KB
- references/rules/abstract-base-class-without-abstract-method.md 1.7 KB
- references/rules/access-annotations-from-class-dict.md 2.7 KB
- references/rules/airflow-dag-no-schedule-argument.md 1.5 KB
- references/rules/airflow-variable-name-task-id-mismatch.md 1.1 KB
- references/rules/airflow3-moved-to-provider.md 1.2 KB
- references/rules/airflow3-removal.md 1.0 KB
- references/rules/airflow3-suggested-to-move-to-provider.md 1.6 KB
- references/rules/airflow3-suggested-update.md 1.3 KB
- references/rules/ambiguous-class-name.md 880 B
- references/rules/ambiguous-function-name.md 883 B
- references/rules/ambiguous-unicode-character-comment.md 1.6 KB
- references/rules/ambiguous-unicode-character-docstring.md 1.6 KB
- references/rules/ambiguous-unicode-character-string.md 1.6 KB
- references/rules/ambiguous-variable-name.md 1.2 KB
- references/rules/and-or-ternary.md 1.3 KB
- references/rules/any-eq-ne-annotation.md 2.0 KB
- references/rules/any-type.md 1.7 KB
- references/rules/argument-default-in-stub.md 1.6 KB
- references/rules/assert-false.md 1.2 KB
- references/rules/assert-on-string-literal.md 846 B
- references/rules/assert-raises-exception.md 1.1 KB
- references/rules/assert-tuple.md 1021 B
- references/rules/assert-with-print-message.md 1.6 KB
- references/rules/assert.md 1.1 KB
- references/rules/assignment-default-in-stub.md 1.5 KB
- references/rules/assignment-in-assert.md 1.5 KB
- references/rules/assignment-to-os-environ.md 1.5 KB
- references/rules/async-busy-wait.md 1.3 KB
- references/rules/async-function-with-timeout.md 2.5 KB
- references/rules/async-zero-sleep.md 1.3 KB
- references/rules/asyncio-dangling-task.md 1.9 KB
- references/rules/avoidable-escaped-quote.md 1.2 KB
- references/rules/await-outside-async.md 1.3 KB
- references/rules/bad-dunder-method-name.md 1.7 KB
- references/rules/bad-exit-annotation.md 1.2 KB
- references/rules/bad-file-permissions.md 1.2 KB
- references/rules/bad-open-mode.md 1.4 KB
- references/rules/bad-quotes-docstring.md 1.4 KB
- references/rules/bad-quotes-inline-string.md 1.4 KB
- references/rules/bad-quotes-multiline-string.md 1.4 KB
- references/rules/bad-staticmethod-argument.md 1.2 KB
- references/rules/bad-str-strip-call.md 1.4 KB
- references/rules/bad-string-format-character.md 839 B
- references/rules/bad-string-format-type.md 853 B
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.
- yesterday First seen · 224 lines · 129 tokens per session scan A 3077192c036d
ruff-dev is a skill published in the GitHub repository LLMTooling/cloudscraper-mcp-server (1 stars, last pushed 3mo ago), with no licence file. It adds 129 tokens to every session and 1,808 once invoked, about $0.0006 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 skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
debugging-mutations
Verify what changed on a ServiceNow instance after a tool call — sysaudit inspection, syslog/transaction logs, session context, Flow Designer execution logs, outbound HTTP traces.
maya-shot-export
Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).