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.
/plugin marketplace add kelp/agent-pluginsnpx agentmods add plugins/kelp/agent-plugins/marketplacegit clone --depth 1 https://github.com/kelp/agent-pluginsGrade A, and why
agent-plugins 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 yesterday.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "agent-plugins",
"owner": {
"name": "Travis Cole",
"email": "[email protected]"
},
"metadata": {
"description": "Claude Code plugins by kelp",
"version": "1.0.0"
},
"plugins": [
{
"name": "zig-claude-kit",
"source": "./plugins/zig-claude-kit",
"description": "Corrective context for Zig 0.15.x that fixes Claude's outdated training data. Covers I/O (Writergate), build.zig, format strings, ArrayList, BoundedArray, and usingnamespace.",
"strict": true
},
{
"name": "tiger-style",
"source": "./plugins/tiger-style",
"description": "TigerBeetle's Tiger Style methodology for Zig: assertions (2+ per fn, paired positive/negative), bounded loops (no recursion), static memory after init, snake_case naming with unit suffixes, 70-line function limit, 100-column line limit, zig fmt. Auto-loads in Zig projects.",
"strict": true
},
{
"name": "tdd-pipeline",
"source": "./plugins/tdd-pipeline",
"description": "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.",
"strict": false
},
{
"name": "cross-review",
"source": "./plugins/cross-review",
"description": "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.",
"strict": false
},
{
"name": "codex-pair",
"source": "./plugins/codex-pair",
"description": "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 deadlocks when the two sides stop converging.",
"sWhat 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.
- yesterday First seen · 62 lines scan A 39c790700c65
agent-plugins is a plugin published in the GitHub repository kelp/agent-plugins (2 stars, last pushed 9d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
pm-skills
Structured AI workflows for better product decisions. 68 domain-specific skills and 42 chained workflows across 9 PM plugins — from discovery to strategy, execution, launch, growth, and shipping AI-built software.
aceternity-ui
100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.
handbook-agent-spec-kit
Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation.
handbook-discover
Discover and audit all plugins in a Claude Code marketplace with installation status, versions, and component breakdown.
reflect
Better alignment with LLMs.
sound
Code taste as installable rules. Probe a repo's stack, select only the rules its code shows a surface for (evidence-cited per rule), confirm, and scaffold a browsable .claude/sound/ rule map (surfaced by the sound:prime skill). Installed rules are user-owned; re-runs reconcile.