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 cembasaranoglu/crafting-system-claudenpx agentmods add plugins/cembasaranoglu/crafting-system-claude/coworkgit clone --depth 1 https://github.com/cembasaranoglu/crafting-system-claudeWrote 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.
[](https://agentmods.dev/plugins/cembasaranoglu/crafting-system-claude/cowork)<a href="https://agentmods.dev/plugins/cembasaranoglu/crafting-system-claude/cowork"><img src="https://agentmods.dev/badge/plugins/cembasaranoglu/crafting-system-claude/cowork.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
crafting-system 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 4d ago.
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.
What it actually says
{
"name": "crafting-system",
"version": "1.1.3",
"description": "Source-first engineering prompt system: prompt audit, risk gate, secret-aware execution, code review, ADR/RFC, refactoring, readiness gates, scheduled repository scoring (CI measures, Claude interprets), OSS packaging, and AI-context generation.",
"author": { "name": "Cem Basaranoglu" },
"license": "MIT"
}
What it installs
The manifest is a name and a version. 81 skills, 32 agents travel with it, and installing the plugin installs all of them — 3,169 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill code-review-quality-gate A 27 tokens
- Skill docs-oss-writer A 24 tokens
- Skill feature-inventory A 25 tokens
- Skill git-workflow A 29 tokens
- Skill hld-strict A 24 tokens
- Skill lld-strict A 25 tokens
- Skill mcp-tooling-readiness A 21 tokens
- Skill oss-release-readiness A 20 tokens
- Skill plugin-review A 44 tokens
- Skill product-vision-competitor A 28 tokens
- Skill prompt-audit A 41 tokens
- Skill readiness-gates A 30 tokens
- Skill refactor-strict A 26 tokens
- Skill security-supply-chain A 18 tokens
- Skill context-map A 39 tokens
- Skill eval-plan A 26 tokens
- Skill prompt-design A 38 tokens
- Skill risk-execution-control A 31 tokens
- Skill risk-gate A 34 tokens
- Skill secret-aware-runtime-credentials A 36 tokens
- Skill prompt-glossary-navigator A 35 tokens
- Skill scheduled-scoring A 94 tokens
- Skill code-authoring A 45 tokens
- Skill codebase-overview A 25 tokens
- Skill docs-writer A 23 tokens
- Skill project-glossary A 26 tokens
- Skill prompt-library A 77 tokens
- Skill refactoring-planner A 20 tokens
- Skill cursor-rules-compiler A 40 tokens
- Skill k8s-runtime-ops A 46 tokens
- Skill adr-rfc-writer A 44 tokens
- Skill ai-context-builder A 34 tokens
- Skill api-cli-docs-audit A 38 tokens
- Skill codebase-search-and-answer A 35 tokens
- Skill data-migration-safety A 32 tokens
- Skill executive-readiness-summary A 50 tokens
- Skill oss-ready-packager A 31 tokens
- Skill performance-readiness A 33 tokens
- Skill plugin-packager A 40 tokens
- Skill pr-merge-gate A 36 tokens
- Skill prompt-tuning-playbook A 31 tokens
- Skill release-notes-writer A 34 tokens
- Skill repo-intel-db A 39 tokens
- Skill source-analysis-pack A 41 tokens
- Skill testing-pyramid A 39 tokens
- Skill ai-context-compiler A 34 tokens
- Skill api-contract-readiness A 25 tokens
- Skill architecture-fitness A 21 tokens
- Skill code-quality-bar A 21 tokens
- Skill competitor-analysis A 28 tokens
- Skill compliance-evidence A 15 tokens
- Skill dependency-boundary-enforcer A 27 tokens
- Skill evidence-ledger A 17 tokens
- Skill failure-mode-auditor A 18 tokens
- Skill git-safety-automation A 17 tokens
- Skill golden-output-validator A 26 tokens
- Skill manifests-library A 55 tokens
- Skill mcp-permission-model A 17 tokens
- Skill multi-agent-orchestrator A 19 tokens
- Skill observability-readiness A 30 tokens
- Skill patch-diff-mode A 17 tokens
- Skill product-docs-generator A 18 tokens
- Skill prompt-compression A 24 tokens
- Skill prompt-conflict-detector A 27 tokens
- Skill prompt-test-harness A 19 tokens
- Skill readiness-aggregator A 20 tokens
- Skill release-deployment-readiness A 32 tokens
- Skill release-go-no-go A 24 tokens
- Skill repo-qa-knowledge-base A 18 tokens
- Skill risk-register A 28 tokens
- Skill runtime-drift-detector A 35 tokens
- Skill safe-refactoring-family A 15 tokens
- Skill unsupported-claim-detector A 31 tokens
- Skill well-architected-readiness A 31 tokens
- Skill adr-library A 41 tokens
- Skill diagrams-library A 32 tokens
- Skill examples-library A 45 tokens
- Skill policies-library A 46 tokens
- Skill schemas-library A 38 tokens
- Skill templates-library A 46 tokens
- Skill failure-modes-library A 28 tokens
- Agent git-release-operator A 45 tokens
- Agent documentation-dx-lead A 26 tokens
- Agent oss-governance-reviewer A 23 tokens
- Agent principal-architect A 25 tokens
- Agent product-market-analyst A 23 tokens
- Agent readiness-auditor A 23 tokens
- Agent strict-code-reviewer A 25 tokens
- Agent architecture-reviewer A 0 tokens
- Agent docs-writer A 0 tokens
- Agent refactoring-planner A 0 tokens
- Agent release-manager A 31 tokens
- Agent repository-analyst A 0 tokens
- Agent risk-gatekeeper A 28 tokens
- Agent adr-rfc-editor A 18 tokens
- Agent api-contract-reviewer A 17 tokens
- Agent cursor-context-architect A 23 tokens
- Agent docs-maintainer A 16 tokens
- Agent evidence-auditor A 17 tokens
- Agent plugin-reviewer A 29 tokens
- Agent product-analyst A 16 tokens
- Agent prompt-architect A 24 tokens
- Agent prompt-tuning-reviewer A 24 tokens
- Agent secret-boundary-reviewer A 26 tokens
- Agent security-reviewer A 15 tokens
- Agent kubernetes-runtime-agent A 19 tokens
- Agent oss-governance-agent A 18 tokens
- Agent refactoring-architect A 17 tokens
- Agent test-strategy-agent A 17 tokens
- Agent lead-orchestrator A 17 tokens
- Agent repo-cartographer A 16 tokens
- Agent supply-chain-agent A 17 tokens
- Agent performance-reviewer A 15 tokens
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.
- 4d ago First seen · 8 lines scan A 19677f61cb9f
crafting-system is a plugin published in the GitHub repository cembasaranoglu/crafting-system-claude (5 stars, last pushed 4mo 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
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
knowledge-work-plugins marketplace
Plugin marketplace listing 98 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
container
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS.
mattpocock-skills
Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.