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/CAIRNepal/heritagegraphWrote 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/cairnepal/heritagegraph/specify-rules)<a href="https://agentmods.dev/rules/cairnepal/heritagegraph/specify-rules"><img src="https://agentmods.dev/badge/rules/cairnepal/heritagegraph/specify-rules/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/cairnepal/heritagegraph/specify-rules"><img src="https://agentmods.dev/badge/rules/cairnepal/heritagegraph/specify-rules.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 | $0.00498 | $0.00498 |
| Opus 5.5 | $0.00199 | $0.00199 |
| Sonnet 5.5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
specify-rules 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 3d 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.
What it actually says
For additional context about technologies to be used, project structure,
shell commands, and other important information, read the current plan:
specs/006-reviewer-triage-and-approval/plan.md (and specs/006-reviewer-triage-and-approval/quickstart.md for migrations, queue triage, and schema proposal smoke checks).
Reviewer triage + schema extension approval: composite queue priority, filters/sort/share URL, moderator-gated proposals — see specs/006-reviewer-triage-and-approval/research.md, specs/006-reviewer-triage-and-approval/data-model.md, and contracts specs/006-reviewer-triage-and-approval/contracts/openapi-reviewer-triage.v1.yaml, specs/006-reviewer-triage-and-approval/contracts/openapi-schema-extension-proposals.v1.yaml.
Identity layer (claim-first): EntityCluster, same-referent membership on HeritageAssertion, merge/split audit, workspace UI — see specs/005-identity-layer/plan.md, specs/005-identity-layer/quickstart.md, specs/005-identity-layer/research.md, specs/005-identity-layer/data-model.md, and specs/005-identity-layer/contracts/openapi-identity-layer.v1.yaml.
YAML-driven schema registry, LinkML generation, and runtime UI loading: specs/004-yaml-driven-schema/plan.md, specs/004-yaml-driven-schema/quickstart.md, specs/004-yaml-driven-schema/research.md, specs/004-yaml-driven-schema/data-model.md, and specs/004-yaml-driven-schema/contracts/openapi-schema-registry.v1.yaml.
Grounded frontend chatbot: specs/003-grounded-chatbot/plan.md and specs/003-grounded-chatbot/quickstart.md.
In-place submission / ontology edit: specs/002-in-place-submission-edit/plan.md and
specs/002-in-place-submission-edit/quickstart.md.
OCR / document pipeline: specs/001-ocr-async-pipeline/plan.md and
specs/001-ocr-async-pipeline/quickstart.md.
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.
- 3d ago First seen · 24 lines · 498 tokens per session scan A 264ecdb63d74
specify-rules is a cursor rule published in the GitHub repository CAIRNepal/heritagegraph (4 stars, last pushed 3d ago), licensed MIT. It adds 498 tokens to every session, about $0.0020 per session on Opus 5.5. 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 2026-10-22.
Other cursor rules, from other repositories
jarvis-agent-rules
MCP server jarvis: notes, Jira, knowledge graph, sessions, preferences.
initial-configuration-rule
Describes the initial configuration process for the PressThat application, including website details.
new-user-experience-nux-flow-rule
Details the new user experience flow, guiding users through the initial setup and configuration.
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.