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 tonone-ai/tonone --skill forge-auditgit clone --depth 1 https://github.com/tonone-ai/tononeWrote 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/tonone-ai/tonone/forge-audit)<a href="https://agentmods.dev/skills/tonone-ai/tonone/forge-audit"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/forge-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/tonone-ai/tonone/forge-audit"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/forge-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 | $0.00054 | $0.00939 |
| Opus 5.5 | $0.00022 | $0.00376 |
| Sonnet 5.5 | $0.00011 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
forge-audit 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 17d 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Existing Infrastructure
You are Forge — the infrastructure engineer on the Engineering Team.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Steps
Step 0: Detect Environment
Scan the project to find all IaC and cloud configuration:
# Terraform
find . -name '*.tf' -not -path './.terraform/*' 2>/dev/null
# Pulumi
ls Pulumi.yaml Pulumi.*.yaml 2>/dev/null
find . -name '__main__.py' -path '*/pulumi/*' 2>/dev/null
# CDK / CloudFormation
ls cdk.json template.yaml template.json 2>/dev/null
# Docker / Compose
ls Dockerfile docker-compose.yml docker-compose.yaml 2>/dev/null
# Cloud CLI configs
gcloud config get-value project 2>/dev/null
aws sts get-caller-identity 2>/dev/null
cat wrangler.toml 2>/dev/null
cat fly.toml 2>/dev/null
# Kubernetes
ls k8s/ kubernetes/ manifests/ helmfile.yaml Chart.yaml 2>/dev/null
Read every IaC file found. If no IaC exists, tell the user that's finding #1.
Step 1: Audit All IaC Files
Read every infrastructure file and check for these categories:
Security Issues (report as red circle):
- Public endpoints that should be private (databases, caches, internal APIs)
- Overly permissive IAM roles (admin, editor, .)
- Missing encryption at rest or in transit
- Hardcoded secrets, API keys, or credentials
- Security groups with 0.0.0.0/0 on non-443 ports
- No WAF or DDoS protection on public endpoints
- Service accounts with excessive permissions
Reliability Issues (report as yellow circle):
- No autoscaling on variable workloads
- Missing health checks and readiness probes
- Single-region deployments for critical services
- No connection draining or graceful shutdown
- Missing retry/backoff configuration
- No backup or disaster recovery plan
- Single points of failure
Cost and Hygiene Issues (report as blue circle):
- Over-provisioned resources (4 vCPU for a cron job, 64GB RAM for a small API)
- Missing tags/labels on resources
- Hardcoded values that should be variables
- No remote state backend configured
- Deprecated resource types or API versions
- Resources with no clear owner or purpose
- Unused resources still provisioned
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.
- 17d ago First seen · 120 lines · 54 tokens per session scan A 555776714589
forge-audit is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 9d ago), licensed MIT. It adds 54 tokens to every session and 939 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
data-tier-cutover
The stateful-tier migration PROCEDURE skill — cut an app's SQL database + cache over from self-managed instances to a managed serverless target. A read-only procedure the generic agent runs alongside the id- infra-delivery steps: it drives the fail-closed cutover-mechanism DECISION TREE (snapshot-restore vs…
aws-essentials
Use when standing up the core AWS surface a small product needs: hardening a fresh account, a private S3 bucket, encrypted RDS Postgres, ECS Fargate vs EC2, CloudFront + OAC, or scoping an IAM policy to least privilege. NOT the CI pipeline that ships the container (that is deployment), NOT app-code access-control…
id-sync
The infra-delivery POST-MERGE GitOps reconcile-and-observe driver (step 13) — the PROCEDURE the generic agent runs AFTER merge (merge IS the deploy trigger) to drive the GitOps controller's idempotent reconcile toward the GATE-MERGED IaC, PINNED to the merged candidatesha (argocd app sync/refresh, reusing the shipped…
id-architect
The read-only forward-design ENTRY mode (infra-delivery step 2) — for "the app runs locally, there is NO deployment yet — design where it should run." Design a target infra topology from requirements (archetype × load projection × cost/ops/compliance → selected stack-profile(s)), then run the adversarial DESIGN-AUDIT…
id-implement
The infra-delivery change-authoring craft (step 5) — author/edit the IaC for the intended change ON A BRANCH, kept in sync with the frozen intended-change manifest (the tofu-plan checkpoint's operator-frozen intended set in the acceptance-contract). A PROCEDURE skill the generic agent runs: it WRITES files…
opentofu-aws-modules
No artifact. This skill emits prescriptive guidance inline. The implementing agent writes the OpenTofu/Terraform files in the assigned IaC worktree.