A skill that collects recent ideas from selected developers and turns useful ones into concrete repository items, such as skills, hooks, settings, or rules.

Use it to fetch recent posts, create a digest, review sources without feeds, and record promising tooling ideas.

It reduces the effort of monitoring many feeds and deciding which ideas are worth adding to a codebase.

agent-ideas — Skill for Claude Code and Codex by bendrucker: A skill that collects recent ideas from selected developers…

Install

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.

agentmods

npx agentmods add skills/bendrucker/claude/agent-ideas

Any agent

npx skills add bendrucker/claude --skill agent-ideas

Clone the repo

git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/agent-ideas.svg)](https://agentmods.dev/skills/bendrucker/claude/agent-ideas)

Your own site

<a href="https://agentmods.dev/skills/bendrucker/claude/agent-ideas"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/agent-ideas.svg" alt="Measured on agentmods" height="20"></a>

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,778 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00013	$0.01778
Opus 5	$0.00006	$0.00889
Sonnet 5	$0.00003	$0.00356
Haiku 4.5	$0.00001	$0.00178

Measured 5d ago against content hash 82418da1c270, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-ideas 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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/fetch.test.ts, scripts/fetch.ts, sources.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/agent-ideas/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Ideas

Harvest agent-tooling ideas from a curated list of thinkers and map them to concrete artifacts in this repo (a skill, hook, setting, or rule). The harvest runs in two phases: a feed pass that fetches, mines, and delivers a digest, and a local pass that fills the X-only gap and files the keepers. As the weekly routine these run headless-then-local, bridged by a teleport doorway item. Run on-demand at your own terminal, they collapse into one pass with no doorway (see Deliver the Doorway Item).

Sources

sources.ts is the prunable core: a version-controlled list of thinkers, each with a feed URL, or marked x-only when no usable feed exists. Edit it directly to add, drop, or retune sources. Keep it small and high-signal; a source earns its place by regularly producing ideas that map to artifacts in this repo.

Fetch

Pull the last 8 days of posts across all feed sources:

bun ${CLAUDE_SKILL_DIR}/scripts/fetch.ts > tmp/agent-ideas-posts.json

Each result is {source, sourceType, feedUrl, posts:[{title,url,date,excerpt}], error?}. Sources with error set could not be fetched; note them but don't block. x-only sources are absent here by design (the local phase handles them after teleport).

Narrow to specific sources or widen the window with flags:

bun ${CLAUDE_SKILL_DIR}/scripts/fetch.ts --days 14 --source simon --source mario

Mine

Turn posts into repo-mappable idea cards. The bar is high: a card must name a real surface in this repo it would refine, or make a clear case for a net-new artifact. See references/mining.md for the card schema, the proven heuristics (per-source cap by depth, auto-demote 404 sources, dedupe against existing repo surfaces), and the fan-out flow.

Fan out one mining Agent call per source (batch thin sources together). Give each the source's posts, the schema, the heuristics, and a read-only view of the repo so it can fill repoOverlap and dedupe. Collect the cards, verify each sourceUrl resolves (demote 404s), then dedupe across agents.

Read the full file on GitHub · 111 lines

Files

What ships with it

6 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.

Changes

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.

5d ago First seen · 111 lines · 13 tokens per session scan A 82418da1c270

Subscribe to this mod's changes

agent-ideas is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,778 once invoked, about $0.0001 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.

Building agents claude-code claude-code-plugin

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

agent-ideas