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.
git clone --depth 1 https://github.com/anilcancakir/claude-codeWrote 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/anilcancakir/claude-code/ac)<a href="https://agentmods.dev/plugins/anilcancakir/claude-code/ac"><img src="https://agentmods.dev/badge/plugins/anilcancakir/claude-code/ac/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/anilcancakir/claude-code/ac"><img src="https://agentmods.dev/badge/plugins/anilcancakir/claude-code/ac.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ac 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 today.
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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "ac",
"version": "0.30.0",
"description": "Plans before it edits, routes each step to haiku, sonnet or opus by cost, and verifies four ways per wave. Ships tiered subagents, authoring skills, local MCP tools, and gated fail-open hooks.",
"author": {
"name": "Anilcan Cakir",
"email": "[email protected]"
},
"license": "MIT",
"homepage": "https://github.com/anilcancakir/claude-code",
"repository": "https://github.com/anilcancakir/claude-code",
"keywords": [
"claude-code",
"plan-then-execute",
"spec-driven",
"subagents",
"multi-agent",
"code-review",
"hooks",
"mcp"
]
}
What it installs
The manifest is a name and a version. 10 skills, 3 commands, 11 agents, 5 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 929 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill execute A 26 tokens
- Skill claude-md-rules-creator A 44 tokens
- Skill plan A 29 tokens
- Skill skill-creator A 27 tokens
- Skill agent-creator A 32 tokens
- Skill command-creator A 26 tokens
- Skill git-master A 30 tokens
- Skill qa A 70 tokens
- Skill auto C 37 tokens
- Skill prompt-writer C 35 tokens
- Command commit A 28 tokens
- Command init-project C 52 tokens
- Command install D 35 tokens
- Agent librarian A 55 tokens
- Agent plan-reviewer A 36 tokens
- Agent plan-worker-senior A 38 tokens
- Agent qa-tester A 51 tokens
- Agent plan-code-review A 36 tokens
- Agent plan-worker-junior-high A 38 tokens
- Agent plan-worker-quick A 30 tokens
- Agent explore A 60 tokens
- Agent oracle A 37 tokens
- Agent auto-verifier C 35 tokens
- Agent plan-worker-junior A 42 tokens
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
- Hook UserPromptSubmit A not measured
- Hook PostToolUse A not measured
- Hook Stop A not measured
- MCP server ac A not measured
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.
- today Changed f919e17fada9
- 3d ago Changed 8503ff27ea1d
- 5d ago Changed 68717d6bacae
- 15d ago Changed c0b681e52289
- 18d ago Changed 0da8be3f260e
- 21d ago Changed b6f3a62c7169
- 22d ago Changed 25dba7e46505
- 1mo ago Changed · +5 lines 64301b4ab8c3
- 1mo ago First seen · 19 lines scan A 65b009e66549
ac is a plugin published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed today), 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
hermitd-dev
Git safeguards, debugging, and merge-conflict resolution for your Hermit.
sre-bot
SRE triage assistant for plain-English production health and Kubernetes questions in Slack. One pinned upstream Kubernetes MCP connector exposes the core toolset: reads execute immediately, six mutations require a fresh human approval, and unmatched tools fail closed. Kubernetes RBAC limits writes to disposable…
test-writer-fixer
Use this agent when code changes have been made and you need to write new tests, run existing tests, analyze failures, and fix them while maintaining test integrity. This agent should be triggered proactively after code modifications to ensure comprehensive test coverage and suite health. Examples:\n\n \nContex.
perf
Rigorous performance investigation workflow with baselines, profiling, and evidence-backed decisions.
bug-fix
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.