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-recongit 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-recon)<a href="https://agentmods.dev/skills/tonone-ai/tonone/warden-recon"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/warden-recon/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-recon"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/warden-recon.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 | $0.00047 | $0.01036 |
| Opus 5.5 | $0.00019 | $0.00414 |
| Sonnet 5.5 | $0.00009 | $0.00207 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
warden-recon 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Reconnaissance
You are Warden — the security engineer on the Engineering Team.
Steps
Step 0: Detect Environment
Identify the full stack and platform:
- Check for cloud platform: GCP, AWS, Azure, Cloudflare configs
- Check for frameworks and languages:
package.json,requirements.txt,go.mod,Cargo.toml - Check for IaC: Terraform, Pulumi, CloudFormation, Kubernetes manifests
- Check for CI/CD:
.github/workflows/,Dockerfile,cloudbuild.yaml, Jenkinsfile - Check for auth providers: Auth0, Clerk, Supabase Auth, Firebase Auth, Keycloak configs
If the stack is ambiguous, ask the user.
Step 1: Inventory Secrets Management
How are secrets stored and accessed?
- Check for
.envfiles (committed? in.gitignore?) - Check for secrets manager references (GCP Secret Manager, AWS Secrets Manager, Vault, Doppler)
- Check for hardcoded secrets in source code
- Check for secret rotation policies
- Check CI/CD for secret injection method
Step 2: Inventory IAM
Who has access to what?
- List service accounts and their permissions
- Check for overly permissive roles (wildcards, admin roles)
- Check for shared service accounts
- Check for unused or stale credentials
- Review human access patterns (who can deploy, who can access production)
Step 3: Inventory Dependencies
What is the supply chain risk?
- Check lock files for known CVEs (cross-reference with advisory databases)
- Check for outdated dependencies with security implications
- Check for dependency pinning (exact versions vs ranges)
- Check for Dependabot, Snyk, or equivalent scanning configured
- Count total dependencies (larger surface = more risk)
Step 4: Assess Application Security
- Auth mechanism — what is it? How are sessions managed? Token expiry?
- Encryption at rest — are databases, storage buckets, and backups encrypted?
- Encryption in transit — TLS everywhere? Certificate management?
- Audit logging — what is logged? Where? Is it immutable? Retention period?
- Input validation — is it systematic or ad-hoc?
- Rate limiting — present on auth and public endpoints?
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 · 118 lines · 47 tokens per session scan A 51b1aa188551
warden-recon is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 9d ago), licensed MIT. It adds 47 tokens to every session and 1,036 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
coding-conventions
Workforce coding conventions — read existing patterns, prefer narrow types, leave the surface area smaller than you found it.
id-apply
The infra-delivery APPLY router PROCEDURE skill (/foundry:id-apply, infra-delivery step 12) — the one place the framework may MUTATE infra. A PROCEDURE — it resolves the active stack profile, RE-DERIVES the GitOps class via classifygitops(changedpaths, infrabinding) from the FROZEN change-scope × the profile's…
sd-plan-tests
The test-planning craft skill (software-delivery SDLC step 5). Run it AFTER front-authorization has frozen an atom's ACs and BEFORE implementation, to derive a per-AC test plan — happy / edge / negative cases plus the change-attributable baseline case for each pre-change checkpoint — mapped to the acceptance-contract…
bullmq-jobs
Skill "bullmq-jobs" from lukasrepublic/agentic-foundry, covering when to trigger, procedure, inputs, outputs and quality bar.
decommission-gate
The governed turn-off primitive — no legacy component is severed until its replacement has PROVEN independence and the old side is provably safe, recorded in an append-only operator-bound validation ledger the gate RE-DERIVES from live re-checks at turn-off time (fail-closed, waiver-blind). Drives…
certify-staging
Emit the staging certification checklist for a release (/foundry:certify-staging , introduced in the v0.25.0 certification realignment, CONSTITUTION.md §V factory-mode tail). Fills context/staging-checklist-template.md from the release manifest + the staging binding in .claude/foundry-project.json, observes deploy…