context-management agents

gsaranti/pantheon

Agent Claude Code

Investigate one technical question against the open web; return findings inline.

gsaranti/pantheon

Agent Claude Code

Review one implementation diff against the description, plan, and scope report it was meant to satisfy. Return a verdict with per-criterion evidence.

eduairet/claude-font-proofer

Agent Claude Code

Python and font-tooling expert (fontTools, uharfbuzz/HarfBuzz shaping, OpenType, variable and color fonts). Writes and runs the code that introspects fonts and renders proofs: it turns the typographer's content plus proof.config.json into the final PDF via the containerized pipeline. It never invents editorial or…

eduairet/claude-font-proofer

Agent Claude Code

Typography expert. Produces the editorial content proofs need: waterfall size ramps, pangrams and specimen paragraphs matched to the detected scripts/languages, kerning test strings, strings that exercise each detected OpenType feature, and layout recommendations. Outputs structured text or JSON only — it NEVER writes…

eduairet/claude-font-proofer

Agent Claude Code

Builds dependency-free vanilla HTML/CSS/JS webfont test pages inside web-tests/ — no frameworks, no build step. Based on the detected font characteristics it first asks the user which tests they want (variable-axis sliders, font-size slider, OpenType feature toggles, kerning on/off, script/language switching…

jmsmrgn/claude-stow

Agent

Updates project vault files after a work session. Invoke with a structured summary of what happened. Handles STATUS.md, DECISIONS.md, and CONTEXT.md using native file tools. Use this instead of updating vault files inline to keep the main session context clean.

stackmemoryai/stackmemory

Agent Claude Code

MUST BE USED PROACTIVELY after writing or modifying any code. Reviews against project standards, TypeScript strict mode, and coding conventions. Checks for anti-patterns, security issues, and performance problems.

stackmemoryai/stackmemory

Agent Claude Code

Git workflow agent for commits, branches, and PRs. Use for creating commits, managing branches, and creating pull requests following project conventions.

dkritarth/context-kernel

Agent Claude Code

Reviews unpromoted journal entries and helps the owner promote them into curated context. Use when the owner says "promote journal", "review my journal", "update my context memory", or runs the promotion workflow. Read-and-suggest only: this agent NEVER writes curated files itself.

dkritarth/context-kernel

Agent Claude Code

Smoke-tests the deployed context-kernel MCP server: auth gating, read tools, and write/journal round-trip. Use after a deploy or when the owner says "test the MCP", "check the connector", "is context-kernel up". Reports pass/fail; does not change server code or curated content.