Token-optimized codebase context. Retrieves only the relevant source code for a question instead of reading whole files. Bundles the fittok MCP server (model-invoked) and a UserPromptSubmit hook that auto-injects the relevant context (deterministic).
★not rated 3 2mo agoA
tokens not measured
originalMIT
Install and connect Firekeep — one self-hosted Keep that carries knowledge, working context, coordination, and evidence across AI agents — then verify it with the product's own doctor.
pi-coding-agent running in a container: interactive shell, one-shot exec, an HTTP REST API, an OpenAI-compatible chat endpoint, an MCP server, a Telegram bot, and a cron scheduler, all on one image.
★not rated 3
changed 26d agoA
tokens not measured
WTFPL
Japanese stock market data via J-Quants API v2, for Claude Code. 55 tools covering equities, financials, indices, derivatives, margin/short-selling data, market-wide screeners, technical indicators, and JSON chart data, backed by a local SQLite cache. Zero-config on a machine that already runs jquants-api-client (auto.
★not rated 3 17d agoA
tokens not measured
originalMIT
Drive the iOS Simulator like a human, from an agent: read the screen via the accessibility tree or on-device OCR, tap/type/swipe/pinch/rotate/drag-drop with real HID events, control the device environment (push, location, biometry, appearance), and replay saved .flow files deterministically in CI. Bundles the testa…
★not rated 3
changed 1mo agoA
tokens not measured
originalMIT
Ship store-ready App Store screenshots in minutes from your coding agent. Shots researches competing listings, then generates, revises, and translates screenshots and icons from your real app context.
★not rated 3 29d agoA
tokens not measured
originalMIT
Answer WhatsApp messages faster: paste a conversation or a screenshot and get a reply drafted in your voice, a quick read of the lead and a suggested next step. Nothing is sent on your behalf.
★not rated 3
changed 17d agoA
tokens not measured
originalApache-2.0
32 production-ready templates as Claude Code skills. Landing pages, dashboards, UI components, project setup, dev methodology, refactoring checklists. Type /templateclaw to scaffold any project.
★not rated 3 7mo agoA
tokens not measured
originalMIT
Comptabilite, fiscalite, financement et epargne en France. Quatre roles : Comptable (/comptable) pour l entreprise ; Impots (/impots) pour le particulier ; Financement (/financement) pour l argent de l activite - banque et droit au compte, credit et rupture de credit, caution du dirigeant, tresorerie, mediation du…
★not rated 3 2mo agoA
tokens not measured
originalMIT
LSP-backed code intelligence for Claude Code via MCP and native LSP - navigate definitions, references, call hierarchies, type hierarchies, and diagnostics across codebases.
★not rated 3 1mo agoA
tokens not measured
originalApache-2.0
Full catalog of AdMob, Google Publisher, and Google Play ads policy violations with the concrete Android code fix for each: Modified ad behavior, accidental clicks, unexpected interstitials, ad density, inventory value, rewards user choice, invalid traffic, refresh rate limits, incentivized clicks, app-ads.txt, EU…
★not rated 3 3mo agoA
tokens not measured
originalMIT
Founder brand is a four-pillar rotation. Pillar, Proof, Process, Person: written in the founder's voice. It refuses thought-leader cadence, engagement bait, and AI-detection filler.
★not rated 3
changed 24d agoA
tokens not measured
originalMIT
FOSS-first investigative analysis toolkit. Turn FOIA releases and data dumps into findings you can stand behind: counted, cited to the exact page, swept for PII, and filed as linked notes, all locally in your own Claude Code session. Covers structured-data analysis, document ingest, redaction checks, and opt-in entity.
★not rated 3 1mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: