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 daftAI2026/daftAI-skills --skill daftai-cloudflare-billing-auditgit clone --depth 1 https://github.com/daftAI2026/daftAI-skillsWrote 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/daftai2026/daftai-skills/daftai-cloudflare-billing-audit)<a href="https://agentmods.dev/skills/daftai2026/daftai-skills/daftai-cloudflare-billing-audit"><img src="https://agentmods.dev/badge/skills/daftai2026/daftai-skills/daftai-cloudflare-billing-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/daftai2026/daftai-skills/daftai-cloudflare-billing-audit"><img src="https://agentmods.dev/badge/skills/daftai2026/daftai-skills/daftai-cloudflare-billing-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 | $0.00094 | $0.03223 |
| Opus 5.5 | $0.00038 | $0.01289 |
| Sonnet 5.5 | $0.00019 | $0.00645 |
| Haiku 4.5 | $0.00009 | $0.00322 |
Grade A, and why
daftai-cloudflare-billing-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 3d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
47 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 245 B
- CLAUDE.md 462 B
- references/CLAUDE.md 1.7 KB
- references/compute-ai.md 3.8 KB
- references/connected-evidence.md 21 KB
- references/d1.md 3.8 KB
- references/durable-objects.md 6.1 KB
- references/legacy-report-schema.md 8.4 KB
- references/maintenance.md 8.9 KB
- references/mcp-setup.md 6.8 KB
- references/operations.md 5.3 KB
- references/preferences.example.json 80 B
- references/preferences.md 8.8 KB
- references/progressive-review.md 6.9 KB
- references/queues.md 3.8 KB
- references/report-schema.md 20 KB
- references/report-writing-en.md 1.7 KB
- references/report-writing.md 5.3 KB
- references/scanner.md 12 KB
- references/sources.json 32 KB
- references/storage.md 3.2 KB
- references/tool-setup.md 6.9 KB
- references/workers.md 5.3 KB
- references/workflow.md 7.0 KB
- scripts/audit-engine.ts 28 KB runs code
- scripts/audit-fs.ts 1.4 KB runs code
- scripts/audit-types.ts 3.6 KB runs code
- scripts/audit.portable.test.ts 13 KB runs code
- scripts/audit.progressive.test.ts 14 KB runs code
- scripts/audit.range.test.ts 9.9 KB runs code
- scripts/audit.regression.test.ts 2.8 KB runs code
- scripts/audit.security.test.ts 19 KB runs code
- scripts/audit.test.ts 28 KB runs code
- scripts/audit.ts 6.9 KB runs code
- scripts/config.ts 20 KB runs code
- scripts/connected-contract.ts 20 KB runs code
- scripts/connected.test.ts 28 KB runs code
- scripts/discovery.ts 5.9 KB runs code
- scripts/fs-common.ts 3.6 KB runs code
- scripts/installed-smoke.ts 7.2 KB runs code
- scripts/linux-fs.ts 19 KB runs code
- scripts/portable-fs.ts 13 KB runs code
- scripts/progressive.ts 16 KB runs code
- scripts/report-markdown.test.ts 2.6 KB runs code
- scripts/report-preferences.test.ts 5.9 KB runs code
- scripts/report-preferences.ts 3.9 KB runs code
- scripts/source-scan.ts 16 KB runs code
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.
- 3d ago Changed · +30 lines · +13 tokens per session 0ad31c46342c
- 5d ago First seen · 70 lines · 81 tokens per session scan A b7295712ac1b
daftai-cloudflare-billing-audit is a skill published in the GitHub repository daftAI2026/daftAI-skills (18 stars, last pushed 4d ago), with no licence file. It adds 94 tokens to every session and 3,223 once invoked, about $0.0004 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 2026-10-14.
Other skills, from other repositories
deploy-kimi-k26-on-rtx-pro-6000
Deploy and serve Moonshot Kimi-K2.6 (1T MoE, MLA, 256K context, vision) in a user-chosen quantization — official INT4 QAT (moonshotai/Kimi-K2.6, compressed-tensors→Marlin; vLLM or SGLang) or NVFP4 (nvidia/Kimi-K2.6-NVFP4, ModelOpt FP4; vLLM only — SGLang NVFP4 is NaN-broken on sm120) — on a Linux server (verified…
deploy-kimi-k3-on-rtx-pro-6000
Deploy and serve Moonshot Kimi-K3 (2.8T MoE, hybrid KDA+MLA attention, native vision via MoonViT-3d) from Unsloth's GGUF quantizations (unsloth/Kimi-K3-GGUF) via llama.cpp on a Linux server with 8x NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB, sm120) GPUs. Unlike vLLM/SGLang's tensor-parallel all-in-VRAM…
mac-mini-as-headless-server
Use when setting up a Mac (especially Mac Mini or Apple Silicon Mac Studio) for unattended 24/7 server operation, headless use, or remote-only access. Covers sleep prevention, screen saver, Wake-on-LAN, auto-restart, App Nap, SSH enablement, and — on Apple Silicon — a caffeinate LaunchDaemon that stops the headless…
ubuntu-nvidia-gpu-enablement
Enable NVIDIA GPUs on a Ubuntu server for compute/inference serving — install the open-kernel-module driver (required for Blackwell/Hopper), CUDA toolkit, turn on IOMMU (inteliommu=on iommu=pt), set up nvidia-persistenced, and install/wire a container runtime (Docker + nvidia-container-toolkit, or the minimal CLI)…
ubuntu-lxd-gpu-server
Install LXD on an Ubuntu server and pass all NVIDIA GPUs into LXD system containers via CDI — install snapd+LXD (snap), run lxd init with a ZFS or dir storage pool, set up a host CDI spec at /etc/cdi and wire the nvidia-container-toolkit auto-refresh units so it stays fresh across driver upgrades, and grant every GPU…
pentest-cloud-auditor
Assess AWS, Azure, and GCP controls for IAM escalation and cloud service exposure.