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/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/heimdall)<a href="https://agentmods.dev/plugins/ancplua/ancplua-claude-plugins/heimdall"><img src="https://agentmods.dev/badge/plugins/ancplua/ancplua-claude-plugins/heimdall/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/ancplua/ancplua-claude-plugins/heimdall"><img src="https://agentmods.dev/badge/plugins/ancplua/ancplua-claude-plugins/heimdall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
heimdall 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": "heimdall",
"version": "0.2.1",
"description": "Watchman of the model-routing Bifröst. /heimdall reports which model actually served each turn (ground truth from the session transcript's message.model), flags silent Opus↔Fable fallback swaps, and shows provider/region/auth routing context. session-inspect.sh adds the extended read: advisorModel, service_tier, speed, inference_geo, cache hit rate, and cache-miss reasons with re-charged token counts. A passive Stop hook (model-drift-net) notices once when the served model changes mid-session. Answers 'am I still on Opus?' — and 'why did I pay for that cache miss?' — with evidence, not a guess.",
"author": {
"name": "ANcpLua",
"url": "https://github.com/ANcpLua"
},
"repository": "https://github.com/ANcpLua/ancplua-claude-plugins",
"license": "MIT",
"keywords": [
"model-routing",
"fallback-model",
"opus",
"fable",
"model-identity",
"which-model",
"transcript",
"served-model",
"model-drift",
"silent-swap",
"observability",
"cache-hit-rate",
"cache-miss",
"service-tier",
"advisor-model",
"token-usage",
"provider-routing",
"bedrock",
"vertex",
"deterministic",
"no-llm"
]
}
What it installs
The manifest is a name and a version. 1 command travel with it, and installing the plugin installs all of them — 49 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 36 lines scan A 706b9ffc7a3f
heimdall is a plugin published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 3d 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 2026-10-01.
heimdall compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| heimdallANcpLua/ancplua-claude-plugins | Plugin | 6 | 3d ago | MIT | A | — | Claude Code |
| humanizerblader/humanizer | Plugin | 68k | 2d ago | MIT | A | — | Claude Code |
| claude-plugins-official marketplaceanthropics/claude-plugins-official | Plugin | 47k | yesterday | Apache-2.0 | A | — | Claude Code |
| nextjsvercel/next.js | Plugin | 143k | today | MIT | A | — | Claude Code |
| themes-examplegoogle-gemini/gemini-cli | Plugin | 109k | today | Apache-2.0 | A | — | Gemini CLI |
| knowledge-work-plugins marketplaceanthropics/knowledge-work-plugins | Plugin | 35k | yesterday | Apache-2.0 | A | — | Claude Code |
| code-modernizationanthropics/claude-plugins-official | Plugin | 47k | yesterday | Apache-2.0 | A | — | Claude Code |