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 marcoguillermaz/Tierward --skill infra-auditgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/marcoguillermaz/tierward/infra-audit)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/infra-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/infra-audit/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/marcoguillermaz/tierward/infra-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/infra-audit.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 | $0.00083 | $0.03589 |
| Opus 5 | $0.00042 | $0.01795 |
| Sonnet 5 | $0.00017 | $0.00718 |
| Haiku 4.5 | $0.00008 | $0.00359 |
Grade B, and why
infra-audit scanned grade B with 2 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **D-6 Apt without cleanup** (**Low**): `apt-get install` without `rm -rf /var/lib/apt/lists/*` in the same RUN layer. Image bloat; not a security issue but noise. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **D-3 ADD with URL** (**High**): `ADD http(s)://...` statement. Prefer `RUN curl ... && ...` with explicit verification (checksum or signature). How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope for v1
- Static analysis only. Parses workflow files, Dockerfiles, K8s manifests, Terraform files, and GitLab CI configs on disk. Does not execute workflows, does not connect to cloud providers, does not validate runtime state.
- Five layers: GitHub Actions, Dockerfile, Kubernetes manifest, Terraform, GitLab CI. Each layer runs only if its markers are detected (see Step 1) - no noisy N/A sections for layers that don't apply.
- Stack-agnostic: the detected backend language / framework does NOT affect which checks run. Infrastructure is orthogonal to application stack.
Configuration (adapt before first run)
Replace these placeholders:
[WORKFLOWS_PATH]- GitHub Actions workflows (default:.github/workflows/)[DOCKERFILE_PATH]- Dockerfile location if non-standard (default:Dockerfileat repo root)[K8S_PATH]- Kubernetes manifest directory (default:k8s/,deploy/,manifests/- auto-detect)[TERRAFORM_PATH]- Terraform directory (default:terraform/,infra/,iac/- auto-detect)[GITLAB_CI_PATH]- GitLab CI config (default:.gitlab-ci.ymlat repo root)
Step 0 - Target and mode resolution
Parse $ARGUMENTS for target: or mode: tokens.
| Pattern | Meaning |
|---|---|
target:layer:<gha|docker|k8s|terraform|gitlab> |
Audit only one layer |
target:file:<glob> |
Audit a specific file or glob |
mode:all / no argument |
Full audit - every layer whose markers are detected in Step 1. |
Announce: Running infra-audit - scope: [FULL | target: <resolved>]
Step 1 - Layer detection
Detect which layers apply. Each has a marker - absence means the layer is skipped entirely with no findings (not "N/A flagged").
| Layer | Marker |
|---|---|
| GHA (GitHub Actions) | .github/workflows/*.{yml,yaml} exists |
| Docker | Dockerfile at repo root OR any **/Dockerfile* with content matching ^FROM |
| K8s | .{yml,yaml} files matching apiVersion: + kind: + common K8s kinds (Deployment, Service, Pod, StatefulSet, DaemonSet, Job, CronJob, Ingress, ConfigMap, Secret) |
| Terraform | *.tf files exist |
| GitLab CI | .gitlab-ci.yml at repo root |
What ships with it
1 file 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.
- 11d ago First seen · 186 lines · 83 tokens per session scan B c69b3dec6f01
infra-audit is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 4d ago), licensed MIT. It adds 83 tokens to every session and 3,589 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
harness-engineering
Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.
codex-hud
Show Codex workspace context with local config, git state, hooks, and project hints. Standalone mode can show an expanded snapshot; patched Codex TUI footer mode is single-line. Use when the user says "codex-hud", "show Codex HUD", "status HUD", "workspace snapshot", or asks for richer Codex context.
address-conductor-comment
A workflow for handling pending Conductor code-review comments, including reading their discussion and assigning changes to subagents when appropriate.
explain-comment
A skill that reads a specified file or code range and adds explanatory comments in Japanese. The comments use a question style and focus on important logic, design choices, and side effects.
saleae-mcp-debugger
Use this skill for hardware-in-the-loop firmware capture and decode workflows through the Saleae Logic 2 MCP server.
build-feature
Full pipeline: evaluation -> spec -> implementation -> review -> QA.