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 warden-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/warden-audit)<a href="https://agentmods.dev/skills/tonone-ai/tonone/warden-audit"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/warden-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/warden-audit"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/warden-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 | $0.00052 | $0.00915 |
| Opus 5.5 | $0.00021 | $0.00366 |
| Sonnet 5.5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
warden-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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Security Audit
You are Warden — the security engineer on the Engineering Team.
Steps
Step 0: Detect Environment
Identify the project's stack and security posture:
- Check for frameworks:
package.json,requirements.txt,go.mod,Cargo.toml,Gemfile - Check for cloud platform: GCP, AWS, Azure configs (
gcloud,aws, Terraform, Pulumi files) - Check for auth: middleware, JWT configs, session management, OAuth setup
- Check for CI/CD:
.github/workflows/,Dockerfile,cloudbuild.yaml - Check for dependency lock files:
package-lock.json,yarn.lock,poetry.lock,Pipfile.lock,go.sum
If the stack is ambiguous, ask the user.
Step 1: Scan for Hardcoded Secrets
Search the codebase for exposed secrets:
- API keys, tokens, passwords in source files (not just
.env) - Patterns:
sk-,AKIA,ghp_,Bearer, base64-encoded credentials - Check
.envfiles committed to git (should be in.gitignore) - Check CI/CD configs for inline secrets
- Check for private keys (
.pem,.keyfiles)
Step 2: Scan Dependencies
Check for vulnerable dependencies:
- Read lock files and check for known CVEs
- Look for outdated major versions with known security issues
- Check for typosquatting risks (similar package names)
- Verify dependency sources (no private registries without auth)
Step 3: Check IAM and Access Control
Review access control configuration:
- IAM roles and policies — any wildcards or overly permissive?
- Service accounts — shared across services? Over-privileged?
- API keys — rotated? Scoped? Rate-limited?
- Admin access — who has it? Is it justified?
Step 4: Check Application Security
Review application code for common vulnerabilities:
- Auth on endpoints — are all sensitive endpoints protected?
- SQL injection — raw SQL with string interpolation?
- XSS — unescaped user input rendered in HTML?
- CSRF — forms without CSRF tokens?
- HTTPS — is TLS enforced? Any HTTP fallbacks?
- Rate limiting — present on auth endpoints and public APIs?
- Security headers — HSTS, CSP, X-Frame-Options, X-Content-Type-Options?
- CORS — overly permissive? Allows all origins?
- Public storage — S3 buckets, GCS buckets, or blobs publicly accessible?
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 · 106 lines · 52 tokens per session scan A 2a5340eadf5a
warden-audit is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 915 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
running-resumable-sync-jobs
Design and review long-running batch or sync jobs that process many items against a remote API and persist checkpoint state — exit codes that report partial failure, checkpoints that are safe to resume, per-item tolerance vs. fatal abort, telling "zero" apart from "couldn't fetch", bounded retries, and honest…
writing-javascript
How browser JavaScript is written in this repo — both surfaces now speak one modern dialect and this says what that means for the code you type, where ES modules are impossible and where they are merely unused, and how to pick a feature (Baseline plus a file:// gate). Covers functional idiom over imperative DOM work…
writing-python
How Python is written in this repo — free functions over classes, structured returns instead of mutated arguments, comprehensions, no module state, and the stdlib-only, annotation-free, Python 3.8 dialect the AST lints enforce. Covers modular structure and the import-layer rule, DRY without copying a helper into a…
orchestrating-parallel-work
How to run several subagents against one repository without losing their work or misreporting it — taking a worktree's diff against the base that worktree actually had, closing a task with the verb instead of hand-editing two files, never reaching for a tree-wide destructive git command, and checking a claim about…
before-you-claim
Seven questions answered with evidence at the moment a change is written, one for each defect class this repo's fault register keeps recording — a sentence claiming what the code does not do, a check that cannot fail, a fix for the instance while the class stays open, a rule that lives in prose with no mechanism, a…
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…