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 agentmods add rules/virastack/ai/apigit clone --depth 1 https://github.com/virastack/aiWhat 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 | $0.00000 | $0.00790 |
| Opus 5 | $0.00000 | $0.00395 |
| Sonnet 5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
api scanned grade A 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
* **Architecture:** NEVER make raw HTTP calls (`fetch()` or `axios.get()`) directly inside feature components or hooks. Always use the project's centralized API client/wrapper. No cross-feature API imports, no hardcoded How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Layer
Constraints
- Location: Place all HTTP calls under
features/[feature]/api. - Validation: Use Zod for input/output validation when data is external or untrusted. Parse responses before they reach UI or state.
- Return Type: Return typed data, not raw responses.
- Contract First: ALWAYS define TypeScript/Zod contracts before writing the implementation. Every public behavior is a commitment.
- Error Handling: Normalize HTTP failures to a consistent
ApiError(code,message,details) before throwing. - Pagination & Limits: Unbounded data fetching is FORBIDDEN. Always enforce pagination or limits on list requests.
- HTTP Client Strategy:
- CRITICAL CHECK: Check
package.jsonto determine the project's HTTP client. - Default (ViraStack): Prefer a centralized native
fetchwrapper (e.g.,src/lib/api.ts) whenaxiosis not installed. - If
axiosis installed, use a centralizedaxiosinstance (e.g.,src/lib/api.ts) instead. - Match the wrapper's return shape: fetch wrappers typically return
Tdirectly; axios returns{ data }.
- CRITICAL CHECK: Check
- Interceptors: Handle cross-cutting concerns (auth, headers, JSON parsing, retries) within the centralized client/wrapper.
- Naming:
verb-entity.api.ts(e.g.,get-users.api.ts). Function:getUsers. - SSR Safety: Use only whitelisted internal URLs or absolute paths for server-to-server calls to prevent SSRF.
Bans
- Raw Exposure: Forbidden to use raw API data inside UI components, hooks, or state without validation.
- Logic Leaks: Forbidden to leak internal error stack traces or raw errors to the client.
- Security: Forbidden to construct dynamic URLs using unsanitized user inputs.
- Architecture: NEVER make raw HTTP calls (
fetch()oraxios.get()) directly inside feature components or hooks. Always use the project's centralized API client/wrapper. No cross-feature API imports, no hardcoded endpoint strings in queries.
Mandatory Patterns
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.
- yesterday First seen · 86 lines · 0 tokens per session scan A 460e5a95f2c5
api is a cursor rule published in the GitHub repository virastack/ai (23 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 790 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
marker-triage
Triage a Marker.io website-feedback backlog at scale. Use when asked to go through, categorize, prioritize, deduplicate, or make sense of many Marker.io issues at once. Splits content fixes from functional bugs, groups by page, rates criticality, flags duplicates and repeat reporters, surfaces quick wins, lists…
marker-client-report
Turn a project's completed Marker.io work into a client-ready report. Use when asked to write a weekly or monthly recap for a client, summarize what was shipped or fixed this period, or produce a status update for a website project from Marker.io. Read-only: it reads issues and writes a markdown report, it does not…
marker-insights
Aggregate Marker.io website feedback into recurring patterns. Use when asked to find the most common issues on a site, which pages get the most feedback, recurring content problems, or the content-vs-bug split across many Marker.io reports, and produce a prioritized brief for a website team or agency. Read-only: it…
marker-bug-to-fix
Take one Marker.io bug report and produce a ready-to-review code fix. Use when asked to fix, investigate, reproduce, or find the root cause of a specific Marker.io issue in the current repository. Pulls the issue's screenshot, console errors, network requests and DOM, locates the cause in code, proposes a minimal…
marker-sync
Keep Marker.io and your issue tracker (GitHub, Linear, Jira) in sync. Use when asked to pull new Marker.io issues into a tracker, enrich tracker tickets with Marker context, mark issues resolved or ready-to-test in both places, or reconcile status mismatches between Marker.io and the tracker.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.