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/provasign/prism/cursorrulesgit clone --depth 1 https://github.com/provasign/prismWhat 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 | $0.00537 | $0.00537 |
| Opus 5 | $0.00269 | $0.00269 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
cursorrules 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 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.
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.
What it actually says
Prism — context delivery
Prism indexes this repo's call and type graph. grep finds the same lines — prism tells you which of them matter (file-level precision 0.51 -> 0.91 on change tasks) and answers in one call where search-then-read takes several.
Route by the question. One call, and treat its result as final:
| Question | Call |
|---|---|
| where is X? | prism_search(query="X") — searches symbol names AND raw text. Several names? You MUST batch: query=["X","Y"] — one search per name wastes a turn each. Know where to look: path=, glob=, files_only=true |
| a literal string, message or config key | prism_search(query="...", scope="text") — pure grep, cheapest. Use it for TEXT; leave the default for code |
| EVERY site of X (rewrite them all, count them) | prism_search(query="X", exhaustive=true) — results are capped at 25 by default and a capped answer to a completeness question looks complete. Say exhaustive; add files_only=true to keep it cheap |
| X, plus the lines around it | prism_search(query="X", context=N) — one call instead of search-then-prism_read |
| read one function, or one file | prism_lookup(name="pkg.Func") / prism_read |
| give me the code for X, ready to edit | prism_query(task="<label>", terms=["X"]) — keys on terms; the wording changes nothing |
| who breaks if I change X? | prism_change_impact(query="Type.method") |
| is my diff complete? | prism_verify |
Before editing an existing symbol, run prism_change_impact: declarations,
every override and implementation, all resolved callers, type-resolved in one
call. Relay that set as-is — re-verifying or filtering it through
grep/sed/scripts measurably drops real sites.
Bash-only (subagents, CI) — same verbs, add --format text:
prism search <term>... [--path <file-or-dir>] [--exhaustive] --scope text
prism query "<task>" --terms X
prism change-impact 'Type.method'
prism lookup <pkg.Func> | prism read <file> | prism verify --base <ref>
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 · 34 lines · 537 tokens per session scan A 4562dc788e6d
cursorrules is a cursor rule published in the GitHub repository provasign/prism (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 537 tokens to every session, about $0.0027 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
adapter-features
Database-specific features must be implemented in the specialized adapter only. Base adapters (postgres, mysql, etc.) must remain database-agnostic.
unit-tests-tdd
TDD required for behavior changes; ≥80% package coverage on touched packages; unit-test conventions.
integration-tests
Human-readable integration test requests; helpers vs httptest; suites/ vs per-DB placement.
refactor-large-files
Guidance for splitting large route files into maintainable pieces.
seed-data
Patterns for development seed data — stable UUIDs, realistic data, cross-references.
feature-flags
Feature flag patterns — use when working with feature toggles.