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 SethGammon/Citadel --skill infra-auditgit clone --depth 1 https://github.com/SethGammon/CitadelWrote 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/sethgammon/citadel/infra-audit)<a href="https://agentmods.dev/skills/sethgammon/citadel/infra-audit"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/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/sethgammon/citadel/infra-audit"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/infra-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 203 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00044 | $0.02080 |
| Opus 5 | $0.00022 | $0.01040 |
| Sonnet 5 | $0.00009 | $0.00416 |
| Haiku 4.5 | $0.00004 | $0.00208 |
Grade A, and why
infra-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 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.
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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/infra-audit -- Infrastructure Auditor
When to Use
- Before adding a new database, cache, or queue to a project
- When onboarding to an unfamiliar codebase and need to understand its infra
- Before planning a workspace campaign that spans multiple services
- When someone asks "what systems does this project talk to?"
Do not use when:
- The user already knows the infra and just wants to wire something up (use
/architect) - The question is about code architecture, not infrastructure (use
/research)
Protocol
Step 1: DISCOVER
Scan the project for infrastructure configuration files. Check each category:
Container orchestration:
docker-compose.yml,docker-compose.*.ymlDockerfile,*.dockerfilek8s/,kubernetes/,helm/,charts/
Environment and secrets:
.env,.env.*,.env.example,.env.local*.envfiles in config directories
Database and ORM:
- Prisma:
prisma/schema.prisma - Drizzle:
drizzle.config.ts,drizzle/ - TypeORM:
ormconfig.*,data-source.ts - Sequelize:
.sequelizerc,config/database.* - Knex:
knexfile.* - SQLAlchemy:
alembic.ini,alembic/ - Django:
settings.py(DATABASES section) - Rails:
config/database.yml - Go: look for
pgx,gorm,sqlxin go.mod
Message queues and event streaming:
- Redis: connection strings,
ioredis,redisin package.json/requirements.txt/go.mod - RabbitMQ:
amqplib,pika,amqpimports - Kafka:
kafkajs,confluent-kafka,saramaimports - NATS:
nats,nats.goimports - SQS/SNS:
@aws-sdk/client-sqs,boto3sqs references
Cache:
- Redis (dual-use -- note if used as cache vs. pub/sub vs. primary store)
- Memcached:
memcached,pylibmcimports
Search:
- Elasticsearch:
@elastic/elasticsearch,elasticsearch-py - Meilisearch, Typesense, Algolia client libraries
Object storage:
- S3:
@aws-sdk/client-s3,boto3s3 references - MinIO, GCS, Azure Blob client libraries
External APIs:
- Stripe, Twilio, SendGrid, Auth0, Firebase, Supabase client libraries
- Any
NEXT_PUBLIC_*orVITE_*env vars pointing to external services
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 · 227 lines · 44 tokens per session scan A 92e0e76b5947
infra-audit is a skill published in the GitHub repository SethGammon/Citadel (918 stars, last pushed 5d ago), licensed MIT. It adds 44 tokens to every session and 2,080 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
compose-org
Run a task as an evolved multi-agent ORG using the installed liquid-org framework — where YOU (the running Claude) embody the org: you ask liquid-org which proven team topology + specialist personas to use (retrieved from its evolved pool, or assembled fresh), then dispatch ONE SUBAGENT PER TALENT to play each role…
liquid-rank
Rank the available skills by RELEVANCE to the current task, on demand, using liquid-org's read-only hermes skill ranker. This is an EXPLICIT, OPT-IN selector you invoke WHEN you want help choosing the most relevant skill for what you're doing — it is NOT default, automatic skill selection, and it does NOT decide for…
present-gate
First-officer gate-presentation rendering — the captain-facing gate-review template and assembly rules, including workflow-owned finding labels. Invoke at the gate point after the FO has decided a stage must be presented.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
prototype
Use when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.
contexts
Use when the user says "get context on X", "how does X work", or wants architectural orientation before coding.