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/AcKeskin/contextureWrote 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/ackeskin/contexture/config-authoring)<a href="https://agentmods.dev/rules/ackeskin/contexture/config-authoring"><img src="https://agentmods.dev/badge/rules/ackeskin/contexture/config-authoring/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/ackeskin/contexture/config-authoring"><img src="https://agentmods.dev/badge/rules/ackeskin/contexture/config-authoring.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 | $0.00000 | $0.03931 |
| Opus 5.5 | $0.00000 | $0.01572 |
| Sonnet 5.5 | $0.00000 | $0.00786 |
| Haiku 4.5 | $0.00000 | $0.00393 |
Grade C, and why
config-authoring scanned grade C 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 today.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- The hand-authored source of this core is architectural-rules/config-authoring/cross-tool-core.md; the projector copies it into AGENTS.md and .github/copilot-instructions.md. Do not hand-edit the generated copies — e How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated from
architectural-rules/config-authoring/— do not hand-edit.
Contract enforcement
- A body-stated contract that a script could evaluate ships with the script. If the contract is a property of a file on disk — a required frontmatter key, a byte or word cap, a cross-reference that must resolve, a generated copy that must match its source — prose alone will not hold it. A rule that only lives in prose ships broken examples, and they pass every gate that does not read the thing the rule is about.
- A checker carries fixtures on both polarities. A violating case must be reported and the legal cases must not be. A checker tested only on violations is a false-positive generator waiting for its first real run; one tested only on clean input proves nothing.
- State what the checker does not cover. Where a contract has a checkable part and a judgment part, gate the first and leave the second an explicit checklist item. Silence reads as coverage, and a partly-gated contract that looks fully gated is worse than an ungated one nobody trusted.
- Put the gate where the defect is authored, not where it is discovered. A contract enforced only at consumption time — a plan step missing its verification, caught when execution reaches it — is found at the most expensive moment. The runtime gate stays; add the authoring-time one.
- A contract that cannot be checked says so. "Surface assumptions before coding" and "every changed line traces to the request" are judgment and always will be. Label them, rather than letting them sit in the same voice as the enforced ones — a reader cannot tell a gate from an aspiration by tone.
Why: the corpus already does this eight times over (leak scan, residue check, projection drift, byte and token budgets, symlink drift, stale spec pins, agent output contract) without ever having named it, so new contracts get written as prose by default and the pattern is rediscovered per-case. Naming it makes the check the default question when a contract is authored: is this a gate or a checklist, and which am I about to imply?
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.
- today First seen · 110 lines · 0 tokens per session scan C 6c55624e0e3d
config-authoring is a cursor rule published in the GitHub repository AcKeskin/contexture (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,931 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-27.
Other cursor rules, from other repositories
fusebase-flow-implementation
Fusebase Flow implementation phase rules. Use when editing source code per a locked spec.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.