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.
git clone --depth 1 https://github.com/fusebase-dev/fusebase-flowWrote 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/rules/fusebase-dev/fusebase-flow/fusebase-flow-security)<a href="https://agentmods.dev/rules/fusebase-dev/fusebase-flow/fusebase-flow-security"><img src="https://agentmods.dev/badge/rules/fusebase-dev/fusebase-flow/fusebase-flow-security/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/rules/fusebase-dev/fusebase-flow/fusebase-flow-security"><img src="https://agentmods.dev/badge/rules/fusebase-dev/fusebase-flow/fusebase-flow-security.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 | $0.00000 | $0.00631 |
| Opus 5 | $0.00000 | $0.00316 |
| Sonnet 5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
fusebase-flow-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 today.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fusebase Flow — security & permissions rules
Hard prohibitions
- Never print secret values (FR-12). Redact in any output.
- Never
git add.env, credentials, private keys (FR-06). - Never write a customer-visible external message without
external_customer_visible_messageapproval artifact (FR-12). - Never use a session key / cookie without
session_key_or_cookie_useapproval artifact (FR-12). - Never modify auth/permission code without
auth_or_permission_changeapproval artifact (FR-12).
Approval artifacts
If an action requires approval per policies/approval-policy.yml, an approval artifact must exist on disk. The agent authors it on the operator's approval — never the operator by hand at a terminal. For a Full-lane deploy, on the DP.6 phrase approve deploy now (forgiving — any case/spacing; legacy APPROVE-DEPLOY-NOW also passes) — the operator types only the phrase, never a composed sentence (Lightweight lane: a plain chat go-ahead, recorded via approve-local.sh lightweight_deploy — DP.12); for any other approval-gated action (protected-path edit, FR-25 baseline adoption, database migration, auth/permission change), once the operator OKs that specific action in chat. Authoring with NO operator authorization is self-approval and forbidden:
state/approvals/<action>-<slug>-<YYYYMMDD>.json
The agent runs this on that approval — the operator types no command: bash hooks/local/approve-local.sh <action> <slug> "<reason>".
Hooks check for an unexpired artifact before allowing the action.
Secret-pattern scanning
policies/secret-patterns.yml defines patterns that hooks block. If the operator pastes a secret-shaped string in chat, the user_prompt_submit hook surfaces a warning. If a write would persist a secret to disk, the pre_tool_use hook blocks.
Categories that trigger this rule
- Auth middleware, permission checks, role/scope code, login/logout flows
.env, secrets handling, credential storage, encryption code- Outbound external messages (email, SMS, webhooks, public posts)
- Data export, bulk import, customer data movement
- Production DB writes outside the established repository pattern
- Deploy config, CI/CD pipeline, infra-as-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.
- today First seen · 47 lines · 0 tokens per session scan A dbb178500843
fusebase-flow-security is a cursor rule published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 631 tokens. 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 2026-09-08.
Other cursor rules, from other repositories
vibeflow
Vibeflow spec-driven development methodology — guardrails, pipeline, and project knowledge system.
test-case-to-katalon-studio
Convert Katalon True Platform/TestOps manual test cases into Katalon Studio automation inside a local Studio Test Project checkout. Use when you need to author or extend a .tc test case file and its paired Groovy script under Scripts/, keep test case variable GUIDs consistent with the .ts test suite bindings that read…
test-maintenance
Maintain and evolve a Katalon True Platform/TestOps regression suite as the application changes. Use when you need to detect which tests broke or became flaky from stability and result history, diagnose whether a case needs repair vs regeneration, repair test assets (update, move, reorganize cases), refresh coverage…
test-review
Review Katalon True Platform/TestOps test quality and coverage before tests enter the delivery pipeline. Use when you need to check whether a suite is ready to run, review requirement and configuration coverage, assess test-case quality and flakiness/stability, spot weak or unreliable cases, and produce a review…
client-workflow-bootstrap
Cursor rule "client-workflow-bootstrap" from ulises-jeremias/agent-toolkit, covering agent vs skill rule — why agent (cite clause), when to use vs holistic, caller / skills / handoff, interview process and gate before generating.
coding-style
Supercharge your Cursor/AI IDE with rules, commands, and skills.