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/cdeust/CortexWrote 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/cdeust/cortex/gemini-extension)<a href="https://agentmods.dev/plugins/cdeust/cortex/gemini-extension"><img src="https://agentmods.dev/badge/plugins/cdeust/cortex/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/cdeust/cortex/gemini-extension"><img src="https://agentmods.dev/badge/plugins/cdeust/cortex/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cortex 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 29d 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": "cortex",
"version": "4.23.5",
"description": "Persistent local-first memory MCP server: remember/recall with thermodynamic heat and decay, knowledge graph, autonomous wiki, local SQLite store by default. Requires uv (uvx) on PATH; hooks-based auto-capture is Claude Code-only — on Gemini CLI memory is manual-tool-driven.",
"mcpServers": {
"cortex": {
"command": "uvx",
"args": ["--from", "hypermnesia-mcp[sqlite]", "hypermnesia-mcp"]
}
}
}
What ships with it
60 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.
- assets/badge-license.svg 1.3 KB
- assets/badge-mcp-toplist.svg 1.8 KB
- assets/badge-python.svg 1.3 KB
- assets/badge-references.svg 1.3 KB
- assets/badge-tests.svg 1.3 KB
- assets/badge-version.svg 1.3 KB
- assets/banner.svg 5.0 KB
- assets/how-cortex-works.svg 5.2 KB
- scripts/aggregate_hook_timings.py 7.6 KB runs code
- scripts/backfill_wiki_titles_2026_07_14.py 5.1 KB runs code
- scripts/backfill_write_class.py 5.7 KB runs code
- scripts/badge_render.py 4.1 KB runs code
- scripts/bench_variance.sh 1.4 KB runs code
- scripts/campaign_guards/i6d5_measure_reheat_ranks.py 3.3 KB runs code
- scripts/check_ci_file_count.py 1.1 KB runs code
- scripts/check_ci_gate_complete.py 9.1 KB runs code
- scripts/check_ci_gate_results.py 4.7 KB runs code
- scripts/check_craftsmanship.py 7.7 KB runs code
- scripts/check_doc_claims.py 7.5 KB runs code
- scripts/check_marketplace_pins.py 5.5 KB runs code
- scripts/check_no_deps_invariant.py 4.2 KB runs code
- scripts/check_project_wiki.py 1013 B runs code
- scripts/check_venv_lock_parity.py 5.8 KB runs code
- scripts/check_version_surfaces.py 8.6 KB runs code
- scripts/collect_response_budget_payloads.py 8.7 KB runs code
- scripts/com.cortex.scheduled-groomer.plist 2.8 KB
- scripts/cortex_ingest.py 6.1 KB runs code
- scripts/craftsmanship_baseline.py 4.6 KB runs code
- scripts/craftsmanship_constants.py 4.0 KB runs code
- scripts/craftsmanship_decisions.py 3.4 KB runs code
- scripts/craftsmanship_git.py 5.0 KB runs code
- scripts/craftsmanship_imports.py 3.2 KB runs code
- scripts/craftsmanship_layer_table.py 6.0 KB runs code
- scripts/craftsmanship_rules.py 4.5 KB runs code
- scripts/decision_migration_io.py 2.7 KB runs code
- scripts/dev_run_ingest.py 902 B runs code
- scripts/doc_claim_scan.py 2.5 KB runs code
- scripts/doc_claim_sources.py 4.6 KB runs code
- scripts/doc_claim_structural.py 6.3 KB runs code
- scripts/docker_smoke_client.py 7.0 KB runs code
- scripts/docker_smoke.sh 909 B runs code
- scripts/dump_snapshot.py 1.5 KB runs code
- scripts/embedding_prefix_fixtures.py 1.5 KB runs code
- scripts/embedding_prefix_model_measure.py 3.1 KB runs code
- scripts/generate_repo_badges.py 9.3 KB runs code
- scripts/groomer.py 13 KB runs code
- scripts/init_plugin.py 4.9 KB runs code
- scripts/install_e2e/evidence.py 4.2 KB runs code
- scripts/install_e2e/host.py 5.2 KB runs code
- scripts/install_e2e/mcp_session.py 5.7 KB runs code
- scripts/install_e2e/run.py 11 KB runs code
- scripts/install_hooks.py 2.7 KB runs code
- scripts/install-plugin.sh 13 KB runs code
- scripts/launcher_backend.py 7.4 KB runs code
- scripts/launcher_base_job.py 8.5 KB runs code
- scripts/launcher_capture.py 1.8 KB runs code
- scripts/launcher_cleanup_fs.py 5.2 KB runs code
- scripts/launcher_cleanup_registry.py 4.2 KB runs code
- scripts/launcher_cleanup.py 5.9 KB runs code
- scripts/launcher_deps_fs.py 12 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.
- 29d ago Changed c546128b8108
- 1mo ago Changed 64958270dc2d
- 1mo ago Changed 773dfdd1c9ce
- 1mo ago Changed ec1d46b52fb6
- 1mo ago Changed 385c4f269bdd
- 1mo ago Changed 3ae3974a2f71
- 1mo ago First seen · 12 lines scan A 25851dd9079b
cortex is a plugin published in the GitHub repository cdeust/Cortex (75 stars, last pushed yesterday), 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 2026-09-06.
Other plugins, from other repositories
prism-coder
Your coding agent forgets everything between sessions. Prism gives it a memory that sticks: your decisions, open TODOs, and changed files, restored the moment you return. It goes past a notes store — associative recall surfaces related past work, drift detection catches a long session wandering off-goal, and an…
papi
Persistent project management inside your AI coding tool. PAPI plans what to build next, tracks every decision, and keeps projects coherent across sessions — so a new session starts where the last one left off instead of from nothing.
inspeximus
Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.
mnemo-mcp
Persistent AI memory — store, search, and recall knowledge across sessions.
synapse-mcp
Persistent AST knowledge graph and safe writes for AI coding agents across 50+ languages. 100% local — no cloud indexing, no telemetry.
stickies
A persistent sticky-note layer for Claude Code. Claude writes durable facts (decisions, blockers, preferences, context, todos) during a session; they survive resets and are injected back into context on the next start.