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/hashgraph-online/hol-cigarWrote 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/hashgraph-online/hol-cigar/claude-code)<a href="https://agentmods.dev/plugins/hashgraph-online/hol-cigar/claude-code"><img src="https://agentmods.dev/badge/plugins/hashgraph-online/hol-cigar/claude-code/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/hashgraph-online/hol-cigar/claude-code"><img src="https://agentmods.dev/badge/plugins/hashgraph-online/hol-cigar/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cigar 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 1mo 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "cigar",
"displayName": "CIGAR",
"version": "0.9.4",
"description": "Deterministic, inspectable, governed context for Claude Code through public hooks and MCP.",
"author": {
"name": "CIGAR contributors"
},
"homepage": "https://github.com/CIGAR/cigar",
"repository": "https://github.com/CIGAR/cigar",
"license": "Apache-2.0",
"keywords": [
"context",
"governance",
"mcp",
"replay"
]
}
What it installs
The manifest is a name and a version. 5 skills, 3 agents, 18 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 194 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill why A 27 tokens
- Skill compile A 24 tokens
- Skill effect A 24 tokens
- Skill checkpoint A 22 tokens
- Skill handoff A 21 tokens
- Agent context-curator A 23 tokens
- Agent effect-reviewer A 29 tokens
- Agent handoff-curator A 24 tokens
- Hook SessionStart A not measured
- Hook PostCompact A not measured
- Hook InstructionsLoaded A not measured
- Hook PostToolBatch A not measured
- Hook PostToolUse A not measured
- Hook PostToolUseFailure A not measured
- Hook PreToolUse A not measured
- Hook TaskCompleted A not measured
- Hook UserPromptSubmit A not measured
- Hook WorktreeRemove A not measured
- Hook SubagentStart A not measured
- Hook SubagentStop A not measured
- Hook TaskCreated A not measured
- Hook CwdChanged A not measured
- Hook PreCompact A not measured
- Hook SessionEnd A not measured
- Hook Stop A not measured
- Hook StopFailure A not measured
- MCP server cigar 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.
- 1mo ago First seen · 20 lines scan A 0e93ca66c65d
cigar is a plugin published in the GitHub repository hashgraph-online/hol-cigar (8 stars, last pushed 17d ago), licensed Apache-2.0. 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
aria-knowledge
ARIA — Applied Reasoning and Insight Architecture. Persistent human-governed knowledge for Claude Code via a five-phase lifecycle: capture → govern → promote → apply → refresh. Stages session insights/decisions/feedback into review backlogs, promotes approved items to a tag-indexed markdown base, and applies them via…
aria-cowork
Knowledge management for Claude Cowork — capture, organize, and apply durable knowledge across your work, available in any project workspace via a persistent folder grant. Companion to aria-knowledge for Claude Code; both share one knowledge folder so insights flow between conversational and engineering work. Default…
titen-memory
Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.
axme-code
(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.
governed-context
Governed memory (explicit states, fail-closed sensitivity gates, quarantine-only writes) as a dependency-free MCP server, plus a blind-evaluation protocol skill for honest A/B comparisons.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.