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.
npx skills add konstruktoid/hardened-images --skill github-repository-securitygit clone --depth 1 https://github.com/konstruktoid/hardened-imagesWrote 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/skills/konstruktoid/hardened-images/github-repository-security)<a href="https://agentmods.dev/skills/konstruktoid/hardened-images/github-repository-security"><img src="https://agentmods.dev/badge/skills/konstruktoid/hardened-images/github-repository-security/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/skills/konstruktoid/hardened-images/github-repository-security"><img src="https://agentmods.dev/badge/skills/konstruktoid/hardened-images/github-repository-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00153 | $0.04259 |
| Opus 5 | $0.00077 | $0.02129 |
| Sonnet 5 | $0.00031 | $0.00852 |
| Haiku 4.5 | $0.00015 | $0.00426 |
Grade C, and why
github-repository-security scanned grade C with 1 finding 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Vendored from https://github.com/konstruktoid/agent-instructions-skills skills/github/github-repository-security/SKILL.md Upstream ref: v0.1.0 Upstream commit: 994be479cf1d44d5ee69d0334da07e923d8dee2e Do not edit lo How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
github-repository-security
Purpose
Bring one repository's configuration to a state where the rules that matter are enforced by a mechanism, the access granted is the smallest that allows the work, and every claim about the repository can be shown from a read of its current state rather than from memory. This skill is a triage layer: it states the baseline every repository must meet, routes the change to the detail that applies, then holds the result to a bounded loop built on reading the applied state back.
A repository setting is a security control with no test suite. The API call that returns success is not evidence that the control exists.
When to use this
- Creating a repository, or hardening an existing one against a baseline.
- Creating or changing a ruleset, branch protection, tag protection, or merge requirements.
- Changing repository visibility, ownership, archival, or deletion.
- Granting or reviewing collaborator access, team access, deploy keys, or environment reviewers.
- Enabling or configuring secret scanning, push protection, code scanning, or dependency alerts.
- Writing or reviewing
SECURITY.md,CODEOWNERS, or private vulnerability reporting. - Configuring how the repository publishes releases, and which identity publishes them.
- Reviewing agent-facing content the repository ships: skills, hooks, commands, or MCP servers.
When NOT to use this
- Organization or enterprise settings, ruleset rollout across many repositories, custom property
schemas, or audit log configuration. Use
github-organization-governance. - The contents of a workflow file, an
action.yml, or adependabot.yml. Usegithub-actions-security. - Git hosting other than GitHub.
- Application code security, which the language skills cover.
What ships with it
5 files beside SKILL.md 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.
- 9d ago First seen · 315 lines · 153 tokens per session scan C 60155232d25d
github-repository-security is a skill published in the GitHub repository konstruktoid/hardened-images (90 stars, last pushed yesterday), licensed Apache-2.0. It adds 153 tokens to every session and 4,259 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
prowler-changelog
Manages changelog entries for Prowler components following keepachangelog.com format. Trigger: When creating PRs, adding changelog entries, or working with any CHANGELOG.md file in ui/, api/, mcpserver/, or prowler/.
prowler-pr
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml…
prowler-ci
Helps with Prowler repository CI and PR gates (GitHub Actions workflows). Trigger: When investigating CI checks failing on a PR, PR title validation, changelog gate/no-changelog label, conflict marker checks, secret scanning, CODEOWNERS/labeler automation, or anything under .github/workflows.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
performing-kubernetes-cis-benchmark-with-kube-bench
Audit Kubernetes cluster security posture against CIS benchmarks using kube-bench with automated checks for control plane, worker nodes, and RBAC.
argocd-gitops
Implement GitOps with ArgoCD for declarative Kubernetes deployments. Configure applications, manage sync policies, implement progressive delivery, and automate deployments from Git repositories. Use when implementing GitOps workflows or continuous deployment to Kubernetes.