kelp

kelp/webdown

Command Claude Code

Run all code quality checks and tests for the webdown project using the make all-checks target, which includes.

kelp/webdown

Command Claude Code

Update CHANGELOG.md with changes since the last version increase. Check our README.md for any necessary changes. Check the scope of changes since the last release and increase our version number as apropraite.

kelp/webdown

Instructions file

Instructions for kelp/webdown, covering webdown development guide, working with claude, version management (semantic versioning), modern python development setup (python 3.10+) and build & testing commands.

kelp/agent-plugins

Plugin Claude Code

Plugin marketplace listing 8 plugins: zig-claude-kit, tiger-style, tdd-pipeline, cross-review, codex-pair.

kelp/agent-plugins

Instructions file

Instructions for kelp/agent-plugins, covering claude.md, what this repo is, repository structure, key conventions and plugin variables.

kelp/agent-plugins

Plugin Claude Code

Pair programming with a persistent Codex partner. Claude drives and edits files while Codex navigates and reviews in a read-only sandbox, all through one long-lived thread that survives restarts. The GPT side is set by your codex install; override per pair with the wrapper's --model flag. A Fable judge rules on…

kelp/agent-plugins

Skill Claude CodeCodex

Pair program with a persistent Codex partner (model set by your Codex install; --model overrides per pair). One pinned Codex thread holds the whole conversation, so the partner keeps full context across the session. Use when the user wants to pair with Codex, get iterative review from Codex, iterate on a design to…

kelp/agent-plugins

Plugin Claude Code

Multi-model code review with cross-validation. Orchestrates Claude and GPT-5.5 reviews, validates findings against each other, outputs merged fix list. Pass --model to set the Claude-side model.

kelp/agent-plugins

Agent

Adversarial code review role for the cross-review plugin. Finds material issues — expensive, dangerous, or hard-to-detect failures — and returns them in a fixed schema. Not for direct user invocation; dispatched by the cross-review orchestrator.

kelp/agent-plugins

Agent

Cross-validation role for the cross-review plugin. Checks findings produced by another model against the actual code and marks each as CONFIRMED, DISPUTED, or UNCERTAIN. Not for direct user invocation; dispatched by the cross-review orchestrator.

kelp/agent-plugins

Skill Claude CodeCodex

Multi-model code review with cross-validation. Orchestrates independent Claude and GPT-5.5 reviews, cross-validates findings, outputs merged fix list. Use when reviewing code changes, auditing files, or wanting a second opinion. Triggers on: "cross-review", "multi-model review", "review with codex", "get a second…

kelp/agent-plugins

Plugin Claude Code

Rules and procedure for running agent fleets: context-handoff, prompt-cache, and model-tier rules for fanning out many subagents, plus a two-lead operating procedure for long-running fleets with unit claiming, heartbeats, and restart from a ledger.

kelp/agent-plugins

Skill Claude CodeCodex

Context-handoff, prompt-cache, and model-tier rules for fanning out many subagents. Read BEFORE launching 3+ parallel agents, writing a Workflow script, or running audits, migrations, or multi-stage pipelines across many files. Every agent dispatch names its model explicitly.

kelp/agent-plugins

Skill Claude CodeCodex

Run a two-lead agent fleet against one repo: a drive lead that claims work units, commits and opens PRs, and a gate lead that watches CI, drains review comments, and restarts the drive lead when it stalls. Read when starting or joining a fleet, claiming or releasing a unit, or when a unit has gone quiet. Covers unit…

kelp/agent-plugins

Plugin Claude Code

Cross-session routing and capture for a three-layer personal knowledge base. /kb-research-policy teaches the index-first retrieval policy. /kb-capture files notes into the right wiki bucket with correct frontmatter.

kelp/agent-plugins

Skill Claude CodeCodex

Capture the current conversation, a source, or a synthesis into your personal knowledge base as a well-formed wiki note. Writes correct frontmatter with today's date, picks the right bucket (sources/external, reports/, concepts/, questions/), cites existing source IDs, and runs just refresh to reindex afterward. Use…

kelp/agent-plugins

Skill Claude CodeCodex

Download an external documentation site into your personal knowledge base as a doc pack and source note. Use when the user says "/kb-ingest ", "ingest these docs", "add these docs to the KB", or "download reference docs". Runs webdown crawl via the knowledge repo's ingest-pack recipe, then creates a MANIFEST.md and…

kelp/agent-plugins

Skill Claude CodeCodex

Routing and retrieval policy for your personal knowledge base at /code/knowledge (or the knowledge-base: path in the active project CLAUDE.md). Use when the user asks about past research, prior notes, captured sources, topics they have studied, or anything that might live in a personal wiki of synthesized notes.…

kelp/agent-plugins

Plugin Claude Code

Land one TODO.md PR slice: choose the next slice, review the plan to consensus, implement with red-green TDD, open a draft pull request, and drain review comments until CI is green.

kelp/agent-plugins

Skill Claude CodeCodex

Add Next TODO binding to this project's CLAUDE.md. Run this to set up the next-todo plugin for a new project.

kelp/agent-plugins

Skill Claude CodeCodex

Land one TODO.md PR slice: choose the next slice, write a plan, review the plan (three axes, or Sol only for a non-behavior exception), implement with red-green TDD, open a draft pull request, and drain review comments until CI is green and no threads remain. Use when starting a TODO slice, landing the next milestone…

kelp/agent-plugins

Plugin Claude Code

Language-agnostic TDD pipeline with test-first agents, review loops, and verify gates. Agents inherit the session model, or pin one per run with --model.

kelp/agent-plugins

Agent

Implementation-review role for the tdd-pipeline plugin. Reads code written by the implementer agent, checks correctness, resource management, and quality, and reports findings. Does not write code. Dispatched by tdd-orchestrate; not for direct user invocation.

kelp/agent-plugins

Agent

Implementation role for the tdd-pipeline plugin. Writes ONLY the source file to make existing tests pass — never modifies tests or build files. Dispatched by tdd-orchestrate; not for direct user invocation.