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 agentmods add skills/tmj-90/gaffer/cloud-securitynpx skills add tmj-90/gaffer --skill cloud-securitygit clone --depth 1 https://github.com/tmj-90/gafferWhat 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 | $0.00068 | $0.01023 |
| Opus 5 | $0.00034 | $0.00511 |
| Sonnet 5 | $0.00014 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
cloud-security 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess cloud posture before attackers do
Cloud misconfigurations are the most common initial-access vector. Find them in review, not in an incident.
The four critical categories
| Category | Most common mistake | Check |
|---|---|---|
| IAM | Privilege escalation via PassRole + AssumeRole + wildcard policies |
No * on Action without explicit justification; no inline policies |
| Storage | Public S3 / GCS / Azure Blob | Block Public Access enabled; no * principal in bucket policies |
| Network | 0.0.0.0/0 ingress on admin ports |
No open 22/3389 to internet; VPC peering limited to known CIDRs |
| IaC | Secrets in .tf/.yml |
No hardcoded credentials; no var with default that contains a secret |
IAM analysis
Work the privilege-escalation graph:
- What actions does this principal have?
- Can it
iam:PassRoleto a more-privileged role? - Can it
sts:AssumeRoleon a wildcard or overly-permissive trust policy? - Does it have
*on resource for any action?
Principle of least privilege: every principal has only the permissions it needs to perform its function, nothing more.
S3 / storage
BlockPublicAcls: true,BlockPublicPolicy: true,IgnorePublicAcls: true,RestrictPublicBuckets: true— all four on every bucket unless public hosting is the explicit purpose.- Bucket policy principal
"*"(unauthenticated) is a BLOCK finding unless the bucket is a public CDN origin. - Server-side encryption (SSE-S3 minimum; SSE-KMS preferred for sensitive data).
- Access logging enabled for compliance buckets.
Network / security groups
- No inbound
0.0.0.0/0or::/0on ports 22 (SSH), 3389 (RDP), 5432 (Postgres), 3306 (MySQL), 27017 (MongoDB). - Egress rules: restrict to known destinations where possible — a blanket
0.0.0.0/0egress allows C2. - VPC flow logs enabled for forensic capability.
IaC security review
- No credentials in
.tf,.yml, or.jsoncommitted to version control. - Provider credentials from environment or secrets manager, not hardcoded.
- Run
tfsec/checkov/kicsin CI; block on HIGH/CRITICAL.
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.
- 2d ago First seen · 79 lines · 68 tokens per session scan A 0db6c8907c7a
cloud-security is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,023 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
mobile-developer
Expert knowledge in mobile app development for iOS, Android, and cross-platform solutions.
skill-creator
Create or update AnkaLoop skills. Use when designing, structuring, or packaging skills with scripts, references, and assets. This skill should be used when users want to create a new skill (or update an existing skill) that extends AnkaLoop's capabilities with specialized knowledge, workflows, or tool integrations.
ai-engineer
Expert knowledge in AI/ML development, model deployment, and MLOps practices.
gh-ci-analyzer
使用 gh CLI 分析 GitHub Actions CI 日志，提供结构化的故障诊断和报告.
security-best-practices
Security best practices and vulnerability prevention guidelines.
react-developer
Expert knowledge in React development, hooks, state management, and modern React patterns.