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/algolia/skillsWrote 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/algolia/skills/algolia-implementation)<a href="https://agentmods.dev/plugins/algolia/skills/algolia-implementation"><img src="https://agentmods.dev/badge/plugins/algolia/skills/algolia-implementation/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/algolia/skills/algolia-implementation"><img src="https://agentmods.dev/badge/plugins/algolia/skills/algolia-implementation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
algolia-implementation 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
{
"name": "algolia-implementation",
"description": "Implementation-planning suite that spans the full Algolia lifecycle: discovery and phase planning, data modeling, index configuration, UI library selection, InstantSearch and Autocomplete readiness, events/Insights instrumentation, NeuralSearch and Agent Studio rollout, and release QA. Use when planning, building, migrating, auditing, or validating an Algolia implementation end to end — it sequences the work, makes data/event contracts explicit, and routes live operations to algolia-cli, algolia-mcp, algobot-cli, and code-level work to instantsearch. Install as a bundle: algolia-discovery-planning is the entry point for builds and algolia-audit for reviewing existing implementations; each loads the companion skills per phase. Do NOT use for direct account operations or as the source of truth for current framework APIs — the official skills above own those.",
"source": "./",
"strict": false,
"skills": [
"./skills/algolia-discovery-planning",
"./skills/algolia-audit",
"./skills/algolia-search-implementation",
"./skills/algolia-data-modeling",
"./skills/algolia-index-configuration",
"./skills/algolia-ui-libraries",
"./skills/algolia-instantsearch-ui",
"./skills/algolia-autocomplete",
"./skills/algolia-events-insights",
"./skills/algolia-neuralsearch",
"./skills/algolia-agent-studio",
"./skills/algolia-release-qa"
]
}What it installs
The manifest is a name and a version. 12 skills travel with it, and installing the plugin installs all of them — 1,994 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill algolia-discovery-planning A 223 tokens
- Skill algolia-data-modeling A 204 tokens
- Skill algolia-events-insights A 163 tokens
- Skill algolia-agent-studio A 137 tokens
- Skill algolia-autocomplete A 185 tokens
- Skill algolia-index-configuration A 158 tokens
- Skill algolia-instantsearch-ui A 198 tokens
- Skill algolia-release-qa A 135 tokens
- Skill algolia-neuralsearch A 128 tokens
- Skill algolia-audit A 193 tokens
- Skill algolia-search-implementation A 119 tokens
- Skill algolia-ui-libraries A 151 tokens
What ships with it
1 file beside marketplace.json#algolia-implementation in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +1 lines a0cbe7d66c45
- 2mo ago First seen · 19 lines scan A 06da05af373b
algolia-implementation is a plugin published in the GitHub repository algolia/skills (12 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 2026-09-03.
algolia-implementation compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| algolia-implementationalgolia/skills | Plugin | 12 | today | MIT | A | — | Claude Code |
| svixsvix/ai | Plugin | 18 | today | MIT | A | — | Claude Code |
| supabasejawwadfirdousi/agent-skills | Plugin | 15 | 3mo ago | none | A | — | Claude Code |
| integration-architectpongsatorna/integration-architect-agent | Plugin | 1 | 4mo ago | none | A | — | Claude Code |
| humanizerblader/humanizer | Plugin | 67k | 13d ago | MIT | A | — | Claude Code |
| claude-plugins-official marketplaceanthropics/claude-plugins-official | Plugin | 47k | today | Apache-2.0 | A | — | Claude Code |
| nextjsvercel/next.js | Plugin | 143k | today | MIT | A | — | Claude Code |