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/rajitsaha/100xprismWrote 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/rajitsaha/100xprism/spec)<a href="https://agentmods.dev/rules/rajitsaha/100xprism/spec"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/spec/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/rajitsaha/100xprism/spec"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/spec.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 | $0.00012 | $0.00541 |
| Opus 5 | $0.00006 | $0.00270 |
| Sonnet 5 | $0.00002 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec — Implementation-Ready Specification
Turn a vague request into an unambiguous, implementation-ready specification. Do not write any code until the spec is approved.
How to use
/spec <feature request>— clarify, read codebase, produce spec, get approval
Phase 1 — Clarify (ask, don't assume)
Ask targeted questions to eliminate ambiguity:
- Who triggers this? (user action, background job, webhook, cron?)
- What is the exact input? (types, shapes, valid ranges, optional vs required)
- What is the exact output? (return value, side effects, UI state change)
- What are the error cases? (invalid input, missing data, network failure, auth failure)
- What are the constraints? (performance, backwards-compatibility, permissions, rate limits)
- What does "done" look like? (how do you know it works?)
Only ask questions that materially change the spec. Infer what you can from the codebase.
Phase 2 — Read context
PROJECT_ROOT=$(git rev-parse --show-toplevel)
cd "$PROJECT_ROOT"
git log --oneline -10
Read relevant existing code: find related files with Grep/Glob, understand existing data shapes, API contracts, naming conventions. Note anything constraining the implementation.
Phase 3 — Write the spec
## Feature: [name]
### Summary
One paragraph: what this does and why.
### Inputs
- [param]: [type] — [description, valid values, required/optional]
### Outputs / Side Effects
- [what changes, what is returned, what events are fired]
### Acceptance Criteria
- [ ] [specific, testable condition]
- [ ] [specific, testable condition]
### Edge Cases & Error Handling
- [condition] → [expected behavior]
### Out of Scope
- [explicitly list what this does NOT do]
### Open Questions
- [anything unresolved — flag for user to decide]
Phase 4 — Get approval
Present the spec. Do not proceed to implementation until the user says "approved", "lgtm", "ship it", or similar.
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.
- 5d ago First seen · 80 lines · 12 tokens per session scan A a8fe7d11bd3c
spec is a cursor rule published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 8d ago), licensed MIT. It adds 12 tokens to every session and 541 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 2026-09-03.
Other cursor rules, from other repositories
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.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.