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/asap-cool/asap-agent-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/rules/asap-cool/asap-agent-skills/asap)<a href="https://agentmods.dev/rules/asap-cool/asap-agent-skills/asap"><img src="https://agentmods.dev/badge/rules/asap-cool/asap-agent-skills/asap.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 | $0.00020 | $0.01620 |
| Opus 5 | $0.00010 | $0.00810 |
| Sonnet 5 | $0.00004 | $0.00324 |
| Haiku 4.5 | $0.00002 | $0.00162 |
Grade A, and why
asap 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 7d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You operate the ASAP platform (French invoicing, contacts, e-signature) through its MCP server. The tools referenced below are provided by that server — connect it first (see the repository README). These playbooks tell you HOW to combine those tools correctly; they never replace them.
Grounding — do this first
ASAP is an invoicing / contacts / e-signature platform for a French freelancer or micro-agency. Before reasoning about any invoice or quote:
- Call
get_org_contextfirst. It returns the active organization, its VAT regime, the enabled apps, and the invoice defaults. Do not assume any of these. - One connection is bound to exactly one organization, fixed when it was authorized. Every call acts within that org; there is no in-session org switch.
- The key's scopes (
contacts/invoice/signature) decide what you may do. A missing scope is a hard403, not something to retry.
The asap://catalogue resource lists every tool, prompt and resource — read it when
you are unsure whether a capability exists.
Compliance invariants (France)
These cause most 4xx errors. Internalize them before mutating anything.
- operation_nature is mandatory to finalize. A fiscal document (facture, avoir,
acompte) needs an explicit
operation_nature—'biens'|'services'|'mixte'. There is no org default. Set it at creation, orfinalize_invoiceblocks with HTTP 422 (2026 mention). - Money is in cents. All amounts are integers in cents.
quantityandvat_rateare decimal tokens passed as strings — e.g."1","20","0". Usevat_rate"0"for franchise-en-base (VAT-exempt micro-entrepreneurs). - Finalizing is irreversible.
finalize_invoiceassigns a gapless legal number (NF203) and seals the document. Preview it first withdry_run: true. - Sealing makes a document immutable. Only a DRAFT can be edited or deleted. Once
finalized,
update_invoice/delete_invoicereturn409. A sealed document is corrected by issuing a new document — never by forcing an edit. See the correct-document playbook.
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.
- 7d ago First seen · 132 lines · 20 tokens per session scan A 132a728e2bf0
asap is a cursor rule published in the GitHub repository asap-cool/asap-agent-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,620 once invoked, about $0.0001 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 cursor rules, from other repositories
kyc-escalation
Write an internal KYC/AML escalation memo: a factual time-stamped trigger description, customer-profile vs activity mismatch analysis, red-flag taxonomy mapping, outstanding information, and a recommendation with rationale. Use when asked to escalate a KYC alert, document an AML concern, write up unusual-activity…
frihet-fiscal
Spanish & EU fiscal context for operating the Frihet ERP MCP tools correctly.
galyarder-cfo-coo
Chief Financial and Operating Officer. Stability guardian. FinOps optimization, legal compliance, risk parity, and operational physics. Apex instance of the Humans 2.0 protocol.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.