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-implementation)<a href="https://agentmods.dev/rules/fusebase-dev/fusebase-flow/fusebase-flow-implementation"><img src="https://agentmods.dev/badge/rules/fusebase-dev/fusebase-flow/fusebase-flow-implementation.svg" alt="Measured on agentmods" 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 | $0.00510 |
| Opus 5 | $0.00000 | $0.00255 |
| Sonnet 5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade C, and why
fusebase-flow-implementation scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`rm -rf`, `git push --force`, `git reset --hard`, `git checkout -- .`, `git clean -fdx`, `git add .`, `git add -A`, `--no-verify`. Full list at `policies/command-policy.yml`. What it actually says
Fusebase Flow — AI Developer discipline
Use only when in AI Developer role with a locked spec.
Self-check before any code edit
- Spec exists at
docs/specs/<slug>/spec.mdand is referenced - Decisions are LOCKED in
docs/specs/<slug>/decisions.md - Tasks list exists with the current T-number declared
- Pre-task git checkpoint clean (
git status --shortempty) - Worker-undisturbed paths from
policies/protected-paths.ymlwill show empty diff for this task
If any check fails, STOP and ask the operator.
Per-task discipline
- One task = one commit (FR-03)
- Lint + typecheck clean per commit (FR-13)
- Stage files explicitly by name — never
git add -A/git add .(FR-06) - Commit message format:
<type>(<scope>): T<n> <one-liner>feat(spa): T17 ...fix(extension): T18 ...test(backend): T19 ...docs(post-deploy): T20 ...
Pre-commit attestation (output before each commit)
T<n> pre-commit check:
☐ Lint clean
☐ Typecheck clean
☐ Worker-undisturbed unchanged
☐ One task scope (no bundling)
☐ No TODO/FIXME/WIP markers
☐ Commit message cites T<n>
→ Committing T<n>: <scope>
Stop at gate
When tasks T..T are committed, produce the gate report per docs/specs/<slug>/verification-gate.md. Do NOT proceed to T. Wait for an explicit deploy handoff (FR-05).
Forbidden without operator confirmation
rm -rf, git push --force, git reset --hard, git checkout -- ., git clean -fdx, git add ., git add -A, --no-verify. Full list at policies/command-policy.yml.
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 · 53 lines · 0 tokens per session scan C 436d2f49cb29
fusebase-flow-implementation 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 510 tokens. A static security scan graded it C with 1 finding (recursive force delete). 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
git
Cursor rule "git" from duongductrong/cursor-kit, covering git conventions, commit messages, types, subject rules and examples.
workflow
Development workflow and commit practices.
hook-commits
Set up pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
upload-report
Run automation and upload or verify Katalon Platform reports for Katalon Studio/KRE, JUnit XML, and Playwright reports. Use when you need to combine Katalon MCP project/result discovery with Katalon CLI execution, Katalon Report Uploader, or @katalon/playwright-reporter; configure report folders, report types…
auto-commit
Commit changes after every completed agent task.
test-management
Organize, classify, and trace Katalon True Platform/TestOps test assets. Use when you need to structure test cases into folders and suites, move or reorganize cases, search and find existing assets at scale, link or unlink requirements to test cases, or produce a requirement-to-test traceability report (which…