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-request-skill-updategit 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-request-skill-update)<a href="https://agentmods.dev/skills/anthropics/claude-plugins-community/tres-request-skill-update"><img src="https://agentmods.dev/badge/skills/anthropics/claude-plugins-community/tres-request-skill-update.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00248 | $0.02630 |
| Opus 5 | $0.00124 | $0.01315 |
| Sonnet 5 | $0.00050 | $0.00526 |
| Haiku 4.5 | $0.00025 | $0.00263 |
Grade A, and why
tres-request-skill-update 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 8d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TRES Plugin Feedback
Guide the user through submitting clear, actionable feedback about the TRES Claude plugin
and save it via the save_ai_conversation_feedback TRES MCP tool. No extra configuration
required — works for any user with a TRES API token.
This skill operates in two modes:
- Explicit feedback — the user asks to submit feedback, report a bug, etc. Run the full guided flow starting at Step 1.
- End-of-conversation prompt — the conversation is wrapping up. Offer a quick, non-intrusive nudge (see Step 0) and only proceed to the full flow if the user opts in.
Step 0 — End-of-Conversation Prompt
When the conversation appears to be ending (the user says "thanks", "that's all", "looks good", etc.) and this skill is triggered proactively:
Ask casually:
Before you go — any feedback on how this session went? Bugs, ideas, or things that could be better? Happy to log it for the team in 30 seconds.
- If the user declines ("no", "I'm good", "nah") — say "No worries, have a great day!" and stop. Do NOT push further.
- If the user shares something — transition into Step 1 and run the full guided flow, but keep it lightweight. Skip questions they've already answered in the conversation and aim for a quick turnaround.
- Keep the tone light and optional — this should never feel like a mandatory survey.
Step 1 — Identify Submitter
-
Call
get_viewer(TRES MCP, no arguments) to identify the submitter.- Extract the organization name from the response.
- If
get_viewerfails, use"Unknown org"as the submitter and continue.
-
Get the user's git identity for the feedback record:
git config user.name && git config user.emailUse line 1 as
agent_nameand line 2 asagent_email. If git is not available, use the system username and leave email empty.
Tell the user: "You're connected as {orgName}. What feedback would you like to share?"
Step 2 — Understand the Feedback
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.
- 8d ago First seen · 263 lines · 248 tokens per session scan A ef5afb6a4349
tres-request-skill-update is a skill published in the GitHub repository anthropics/claude-plugins-community (3,605 stars, last pushed 13d ago), licensed Apache-2.0. It adds 248 tokens to every session and 2,630 once invoked, about $0.0012 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…