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 brandhaug/b2b-saas-starter --skill investigate-cloudflaregit clone --depth 1 https://github.com/brandhaug/b2b-saas-starterWrote 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/brandhaug/b2b-saas-starter/investigate-cloudflare)<a href="https://agentmods.dev/skills/brandhaug/b2b-saas-starter/investigate-cloudflare"><img src="https://agentmods.dev/badge/skills/brandhaug/b2b-saas-starter/investigate-cloudflare/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/brandhaug/b2b-saas-starter/investigate-cloudflare"><img src="https://agentmods.dev/badge/skills/brandhaug/b2b-saas-starter/investigate-cloudflare.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 | $0.00045 | $0.00929 |
| Opus 5.5 | $0.00018 | $0.00372 |
| Sonnet 5.5 | $0.00009 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
investigate-cloudflare 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 12d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate Cloudflare
Investigate read-only unless the user also requests a fix or operational change. Read monitoring for event contracts and coverage gaps, the logger policy for privacy boundaries, and the research note for platform capabilities and limitations.
Establish the target
Identify the Cloudflare account, environment, affected Worker, UTC incident window, and symptom or issue ID from the request and deployment evidence. Map Worker names back to deployment configuration. Verify the active version and release time before comparing source with a failure. A local commit does not prove what ran.
Use already available access in this order: connected Observability MCP tools,
authenticated Cloudflare CLI, then the dashboard. Discover tools and installed
CLI help before constructing commands. If none is available, complete the local
configuration/source review and identify the missing access explicitly. Never
print credentials or dump .env, tokens, or authentication configuration.
Query narrowly
The SQL API is beta and
schemas vary by plan and permissions. Discover datasets and columns before
constructing a query. Use cf sql datasets and installed command help, or the
connected tool's dataset discovery. A query needs one schema-qualified dataset,
a scope, and a lower time bound. Prefer an explicit upper bound too.
The documented CLI shape is:
cf sql query '<SELECT using discovered fields and dataset>' \
--scope-account '<account tag>' \
--time-since '<UTC start>' \
--time-until '<UTC end>'
Use --scope-zone instead for a zone. When using these flags, omit corresponding
tenancy and timestamp predicates from SQL. See CLI query instructions.
Use parameter binding supported by the chosen tool instead of interpolating user
text. Keep aggregates and result limits small; expand the window when the initial
result requires it. Do not infer a Worker dataset name from an HTTP request example.
What ships with it
1 file 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.
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.
- 12d ago Changed · +3 lines f04d6a36e82e
- 13d ago First seen · 85 lines · 45 tokens per session scan A ee42f68bcd57
investigate-cloudflare is a skill published in the GitHub repository brandhaug/b2b-saas-starter (51 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 929 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 2026-10-03.
Other skills, from other repositories
incident-response-skill
A skill that uses object-style tool references with purpose descriptions and required flags, plus strict validation.
add-a-service
Scaffold a new service under services/ in the builders-stack monorepo. Use when something needs its own URL, port, or independent deploy. Covers the package, entrypoint, config, Tilt, deployment registry, and shared small-image build path.
tuturuuu-browser-vercel-debugging
Reproduce deployed Tuturuuu bugs and correlate browser evidence with Vercel logs.
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…
optimize-a-query
Diagnose and fix a slow Postgres query in the builders-stack — read its EXPLAIN plan, find the missing index or the ORM N+1, and confirm the fix. Use when a page or endpoint is slow, a query times out, or pgstatstatements shows a hot query. Pairs with design-a-schema for the index itself.
harness-compatibility-protocol
Cross-vendor parity invariants, lifecycle delegation, and seven external-drift dimensions shared by the harness compatibility checker and fixer.