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/Clear-Capabilities/agentic-securityWrote 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/clear-capabilities/agentic-security/gemini-extension)<a href="https://agentmods.dev/plugins/clear-capabilities/agentic-security/gemini-extension"><img src="https://agentmods.dev/badge/plugins/clear-capabilities/agentic-security/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/clear-capabilities/agentic-security/gemini-extension"><img src="https://agentmods.dev/badge/plugins/clear-capabilities/agentic-security/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentic-security 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
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- data/cwe-explainer.json 24 KB
- examples/demo-app/ai-assistant.js 899 B runs code
- examples/demo-app/auth.js 1.0 KB runs code
- examples/demo-app/db.js 343 B runs code
- examples/demo-app/Dockerfile 331 B
- examples/demo-app/package.json 319 B
- examples/demo-app/README.md 1.6 KB
- examples/demo-app/report.py 511 B runs code
- examples/demo-app/server.js 1.3 KB runs code
- examples/haskell-app/fixed/app.cabal 433 B
- examples/haskell-app/fixed/src/Main.hs 1.8 KB
- examples/haskell-app/partial/app.cabal 248 B
- examples/haskell-app/partial/src/Gen.hs 517 B
- examples/haskell-app/vulnerable/app.cabal 401 B
- examples/haskell-app/vulnerable/src/Main.hs 1.4 KB
- examples/haskell-on-nix/vulnerable/app.cabal 253 B
- examples/haskell-on-nix/vulnerable/flake.nix 545 B
- examples/haskell-on-nix/vulnerable/src/Main.hs 494 B
- examples/nixos-host/fixed/configuration.nix 841 B
- examples/nixos-host/fixed/flake.lock 564 B
- examples/nixos-host/fixed/flake.nix 239 B
- examples/nixos-host/vulnerable/configuration.nix 929 B
- examples/nixos-host/vulnerable/flake.nix 239 B
- examples/polyglot-privacy/app.cabal 248 B
- examples/polyglot-privacy/assistant.py 426 B runs code
- examples/polyglot-privacy/module.nix 340 B
- examples/polyglot-privacy/src/Sync.hs 1.2 KB
- scripts/_compliance_lib.py 10 KB runs code
- scripts/apply-command-trim.mjs 16 KB runs code
- scripts/assurance-differentiation/test/capabilities.test.js 437 B runs code
- scripts/assurance-differentiation/test/deployment-graph.test.js 443 B runs code
- scripts/assurance-differentiation/test/documentation.test.js 444 B runs code
- scripts/assurance-differentiation/test/evaluation.test.js 433 B runs code
- scripts/assurance-differentiation/test/foundation.test.js 742 B runs code
- scripts/assurance-differentiation/test/invariants.test.js 431 B runs code
- scripts/assurance-differentiation/test/portfolio.test.js 428 B runs code
- scripts/assurance-differentiation/test/relay.mjs 8.8 KB runs code
- scripts/assurance-differentiation/test/release.test.js 475 B runs code
- scripts/assurance-differentiation/test/routing.test.js 422 B runs code
- scripts/assurance-differentiation/test/verification.test.js 437 B runs code
- scripts/assurance-review-example.mjs 7.0 KB runs code
- scripts/attest-fixture.mjs 7.7 KB runs code
- scripts/auto-update-check.js 2.5 KB runs code
- scripts/autopilot.mjs 14 KB runs code
- scripts/baseline-capture.mjs 5.0 KB runs code
- scripts/blocked-capability-example.mjs 3.3 KB runs code
- scripts/calibration-expand.mjs 6.1 KB runs code
- scripts/calibration-holdout-check.mjs 6.5 KB runs code
- scripts/capability-ledger/check.mjs 18 KB runs code
- scripts/capability-ledger/prd-snapshot.json 3.6 KB
- scripts/capture-language-examples.mjs 5.4 KB runs code
- scripts/check-assurance-docs.mjs 13 KB runs code
- scripts/check-bench-shas.mjs 2.5 KB runs code
- scripts/check-bundle-source.mjs 2.7 KB runs code
- scripts/check-doc-drift.mjs 18 KB runs code
- scripts/ci-templates/.circleci-config.yml 939 B
- scripts/ci-templates/.gitlab-ci.yml 661 B
- scripts/ci-templates/buildkite.yml 566 B
- scripts/ci-templates/cve-watch.github-actions.yml 2.5 KB
- scripts/ci-templates/Jenkinsfile 687 B
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 Changed 042fcf867032
- 2d ago Changed 1fde750245a6
- 3d ago Changed 2069e5f576a6
- 4d ago Changed 81093cb65864
- 5d ago Changed 90a4ba9cfecf
- 6d ago Changed 89e49d74125e
- 7d ago Changed 3784e3b3f4e8
- 8d ago Changed eaa6aa199c88
- 9d ago Changed 549adbbab463
- 10d ago First seen · 36 lines scan A 1479ec315875
agentic-security is a plugin published in the GitHub repository Clear-Capabilities/agentic-security (118 stars, last pushed yesterday), 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 2026-09-06.
Other plugins, from other repositories
arc-studio marketplace
Plugin marketplace listing 1 plugin: arcgentic.
arcgentic
Agentic harness for rigorous round-driven development with external audit, closeout gates, and V2 fixed-role session orchestration.
merismos
Take as yours a plan cutting one autonomous goal into units, each with its checks, accepted gaps, and held judgments — /apportion (μερισμός: an apportionment).
periagoge
Name what your cases share, say which cases it takes in and leaves out, and recognize it as serving your goal — /induce (περιαγωγή: turning-around).
maidan
Maidan MCP server - agent coordination for your own instance.
brana
AI development system — skills, agents, and hooks for systematic software engineering with Claude Code.