claude-plugins-community is a read-only mirror of a marketplace listing community-contributed plugins for Claude Cowork and Claude Code. It is for discovering and installing plugins that extend those Claude products, while submissions are handled through Anthropic’s separate review process. Catalogue add-ons represent plugins, skills, and integrations associated with this marketplace.
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 anthropics/claude-plugins-community --skill tres-rollup-rulesgit clone --depth 1 https://github.com/anthropics/claude-plugins-communityWrote 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/anthropics/claude-plugins-community/tres-rollup-rules)<a href="https://agentmods.dev/skills/anthropics/claude-plugins-community/tres-rollup-rules"><img src="https://agentmods.dev/badge/skills/anthropics/claude-plugins-community/tres-rollup-rules/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/anthropics/claude-plugins-community/tres-rollup-rules"><img src="https://agentmods.dev/badge/skills/anthropics/claude-plugins-community/tres-rollup-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 216 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high System Prompt Leakage · line 287 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Excessive Agency · line 363 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00226 | $0.06288 |
| Opus 5 | $0.00113 | $0.03144 |
| Sonnet 5 | $0.00045 | $0.01258 |
| Haiku 4.5 | $0.00023 | $0.00629 |
Grade A, and why
tres-rollup-rules 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 10d 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 — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TRES Finance — Rollup Rules
Analyze an organization's sub-transaction patterns, identify groups of repetitive transactions, and propose rollup rules that consolidate them into a single entry per interval for cleaner ERP integration. This is a data-driven discovery flow — you find the candidates from the data, validate each against real transactions, then present and create them.
A rollup rule is keyed on FOUR dimensions that together define exactly which sub-transactions it claims: internalAccount (wallet) + asset KEY + platform + balanceFactor (direction). Optional discriminating filters (fees, methodIds, subtxType, amount bounds, counterparties) narrow it further. Everything you discover and propose must map onto this shape — see the Rule Field Reference at the bottom.
A rollup is non-destructive: the original raw sub-transactions are always preserved and visible in the Rollup Breakdown report.
All GraphQL runs through the TRES Finance MCP connector (execute tool; validate with
validate_query first when unsure). All variable keys and nested input fields MUST use
camelCase (e.g. internalAccountId, balanceFactor), NEVER snake_case.
Routing
- "Suggest / create / propose rollup rules", "too many transactions", "roll up X" → run the full discovery pipeline (Steps 0–6 below). This is the main flow.
- "Show / list my rollup rules" → Section A (List existing rules), then stop.
- "Delete a rollup rule" → Section C (Delete rules).
- "Review this specific rule" / "what would this rule match" → hand off to the tres-rollup-review skill.
Step 0 — Confirm Scope
Establish scope with the user, but keep it light — only the analysis is scoped, the rules themselves are usually open-ended.
Analysis window (OPTIONAL)
A period only narrows the discovery queries so you look at recent, representative activity. It is NOT required, and it is NOT the rule's date range.
- "Q1 2025" → start:
2025-01-01T00:00:00Z, end:2025-03-31T23:59:59Z - "last 3 months" → compute from today
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.
- 10d ago First seen · 510 lines · 226 tokens per session scan A a30935122269
tres-rollup-rules is a skill published in the GitHub repository anthropics/claude-plugins-community (3,663 stars, last pushed 14d ago), licensed Apache-2.0. It adds 226 tokens to every session and 6,288 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.