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/rogermt/forgesyteWrote 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/rogermt/forgesyte/gemini-extension)<a href="https://agentmods.dev/plugins/rogermt/forgesyte/gemini-extension"><img src="https://agentmods.dev/badge/plugins/rogermt/forgesyte/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/rogermt/forgesyte/gemini-extension"><img src="https://agentmods.dev/badge/plugins/rogermt/forgesyte/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ForgeSyte 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 yesterday.
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
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
30 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.
- scripts/audit_plugins.py 9.1 KB runs code
- scripts/ci/test_schema_drift.py 2.2 KB runs code
- scripts/demo_video_yolo_ocr.sh 1.7 KB runs code
- scripts/diagnose_plugin_path.py 1.3 KB runs code
- scripts/env_check.py 2.5 KB runs code
- scripts/fix_schema.py 2.1 KB runs code
- scripts/forge-init.sh 954 B runs code
- scripts/phase6/phase6_actual_test_count.sh 246 B runs code
- scripts/phase6/phase6_actual_tests.sh 119 B runs code
- scripts/phase6/phase6_detect_partial_runs.sh 601 B runs code
- scripts/phase6/phase6_detect_skips.sh 367 B runs code
- scripts/phase6/phase6_diff_tests.sh 547 B runs code
- scripts/phase6/phase6_expected_test_count.sh 143 B runs code
- scripts/phase6/phase6_expected_tests.sh 975 B runs code
- scripts/phase6/phase6_verify_baseline.sh 2.9 KB runs code
- scripts/phase7/baseline-verify.sh 2.1 KB runs code
- scripts/phase7/forbidden-file-check.ts 1.7 KB runs code
- scripts/phase7/skipped-tests-check.ts 2.0 KB runs code
- scripts/remove-hardcoded-plugins.sh 1.1 KB runs code
- scripts/run_local_plugin_tests.py 1.9 KB runs code
- scripts/run-local-plugin-tests-override.sh 1.7 KB runs code
- scripts/run-local-plugin-tests.sh 841 B runs code
- scripts/scan_api_contracts.py 5.6 KB runs code
- scripts/scan_execution_violations.py 3.6 KB runs code
- scripts/smoke_test_video_batch.sh 1018 B runs code
- scripts/smoke_test.py 6.7 KB runs code
- scripts/start_worker.sh 3.0 KB runs code
- scripts/sync-fixtures.sh 6.9 KB runs code
- scripts/validate_phase15_video_pipeline.py 2.9 KB runs code
- scripts/verify_phase11.sh 577 B 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.
- yesterday First seen · 26 lines scan A 7202c98ed656
ForgeSyte is a plugin published in the GitHub repository rogermt/forgesyte (1 stars, last pushed 2d ago), with no licence file. 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 2026-09-20.
Other plugins, from other repositories
datalayer
Connect Claude Code to Datalayer Notebooks — always-on notebooks, durable execution, and your data, through the hosted Jupyter MCP Server.
neo4j-skills
Agent skills for Neo4j graph database — Cypher queries, graph modeling, drivers, imports, GraphRAG, GDS, vector indexes, and Aura provisioning.
knowledge-catalog
Connect to Knowledge Catalog to discover, manage, monitor, and govern data and AI artifacts across your data platform.
socrata-mcp-server
Search and query government open-data portals (Socrata SODA API) via MCP. STDIO or Streamable HTTP.
faos-ai-engineer
🤖 AI Engineer — AI Engineer + LLM Systems Specialist.
axon
Self-hosted RAG engine in Rust: crawl, scrape, ingest, embed, and query any source, with hybrid retrieval and cited LLM synthesis over MCP, CLI, and REST.