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/inite-ai/inite-brain-serviceWrote 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/inite-ai/inite-brain-service/gemini-extension)<a href="https://agentmods.dev/plugins/inite-ai/inite-brain-service/gemini-extension"><img src="https://agentmods.dev/badge/plugins/inite-ai/inite-brain-service/gemini-extension/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/inite-ai/inite-brain-service/gemini-extension"><img src="https://agentmods.dev/badge/plugins/inite-ai/inite-brain-service/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
inite-brain 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 11d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
51 files beside gemini-extension.json 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.
- examples/reference-indexer.ts 5.6 KB runs code
- examples/sdk-quickstart/index.ts 3.4 KB runs code
- examples/sdk-quickstart/package.json 415 B
- examples/sdk-quickstart/README.md 4.8 KB
- examples/sdk-quickstart/tsconfig.json 309 B
- scripts/backfill-lang-attribution.ts 7.0 KB runs code
- scripts/bench-chat-router.ts 4.4 KB runs code
- scripts/build-openapi.ts 157 KB runs code
- scripts/build-skill-versions.ts 2.2 KB runs code
- scripts/bump-skill-versions.ts 5.0 KB runs code
- scripts/capture-decisions.ts 5.5 KB runs code
- scripts/ci/await-ci.mjs 6.7 KB runs code
- scripts/ci/battery-summary.mjs 11 KB runs code
- scripts/ci/change-buckets.mjs 4.5 KB runs code
- scripts/ci/classify-changes.mjs 1.2 KB runs code
- scripts/ci/gate.mjs 4.7 KB runs code
- scripts/ci/read-deploy-manifest.mjs 2.2 KB runs code
- scripts/ci/smoke.mjs 7.7 KB runs code
- scripts/ci/strip-view-data.mjs 1.5 KB runs code
- scripts/eval-analysis/beam-mcnemar.py 2.3 KB runs code
- scripts/eval-analysis/beam-summary.py 505 B runs code
- scripts/eval-analysis/locomo-mcnemar.py 2.8 KB runs code
- scripts/eval-baseline-diff.ts 9.3 KB runs code
- scripts/fetch-beam-dataset.py 5.8 KB runs code
- scripts/fetch-wikidata-directory.ts 4.3 KB runs code
- scripts/generate-flexible-reconcile.ts 788 B runs code
- scripts/index-repo.ts 6.5 KB runs code
- scripts/init-pack.ts 6.4 KB runs code
- scripts/install-pack.ts 3.8 KB runs code
- scripts/label-commitpackft.ts 4.8 KB runs code
- scripts/label-decisions.ts 3.8 KB runs code
- scripts/locomo-compare.ts 3.7 KB runs code
- scripts/locomo-fullcontext-baseline.ts 10 KB runs code
- scripts/mri-record-suite.ts 9.4 KB runs code
- scripts/mri-report.ts 2.9 KB runs code
- scripts/offline-nugget-score.ts 7.8 KB runs code
- scripts/offline-ordering-score.ts 2.9 KB runs code
- scripts/package-skills.ts 1.6 KB runs code
- scripts/publish-pack.ts 2.2 KB runs code
- scripts/run-beam.ts 8.3 KB runs code
- scripts/run-locomo.ts 13 KB runs code
- scripts/run-longmemeval.ts 5.8 KB runs code
- scripts/scan-hnsw-parity.ts 8.2 KB runs code
- scripts/search-registry.ts 2.1 KB runs code
- scripts/seed-registry.ts 2.2 KB runs code
- scripts/sign-pack.ts 1.4 KB runs code
- scripts/submit-awesome.sh 20 KB runs code
- scripts/sync-plugin-skills.ts 2.1 KB runs code
- scripts/train-decision-gate.ts 7.6 KB runs code
- scripts/validate-anchors.ts 2.8 KB runs code
- scripts/validate-pack.ts 1.2 KB runs code
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.
- 11d ago Changed 1819f321c891
- 1mo ago First seen · 15 lines scan A 46339616537a
inite-brain is a plugin published in the GitHub repository inite-ai/inite-brain-service (43 stars, last pushed today), licensed AGPL-3.0. 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 2026-09-12.
Other plugins, from other repositories
keymem
Associative long-term memory — recall by key-graph association, plus passive memory surfacing on every prompt.
pensyve
Universal memory runtime — ambient working-memory substrate for Claude Code. Memory is not a feature you invoke — it's the substrate the agent operates on.
aionforge-memory
Agent skills for using an externally configured Aionforge Memory MCP server as durable project memory.
hippo-memory
Make your agent's memory work like a brain. Hippo is long-term memory for coding agents.
honcho
Persistent memory for Cursor and Grok Bot, powered by Honcho. Remembers who you are, what you prefer, and what you were working on across sessions, projects, and Bots.
engraphis-memory
Give agents durable, scoped, explainable memory across sessions and repos via the Engraphis MCP tools. Use when you learn something worth keeping, need prior context before acting, or ask why/how a fact changed. Covers remember/recall, why/timeline, forget/pin/correct, sessions, and code search.