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/jnPiyush/AgentXWrote 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/jnpiyush/agentx/000-frontier-core)<a href="https://agentmods.dev/rules/jnpiyush/agentx/000-frontier-core"><img src="https://agentmods.dev/badge/rules/jnpiyush/agentx/000-frontier-core/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/jnpiyush/agentx/000-frontier-core"><img src="https://agentmods.dev/badge/rules/jnpiyush/agentx/000-frontier-core.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 | $0.00783 | $0.00783 |
| Opus 5.5 | $0.00313 | $0.00313 |
| Sonnet 5.5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
000-frontier-core 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 4d 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.
This is a copy
94% identical to 000-agentx-core — 88 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontier in Cursor
Use Frontier: Initialize Cursor or frontier cursor setup once per workspace.
Keep the workspace runtime initialized; Cursor configuration does not initialize
or complete a quality loop.
Read AGENTS.md and .github/AGENT-PROTOCOL.md through
pwsh -NoProfile -File .frontier/runtime/frontier.ps1 cursor read <canonical-path> before delivery work.
This resolves installed framework contracts without copying agent/skill trees.
Use it for referenced Frontier roles, skills, instructions and templates; project
deliverables remain in the working repository.
cursor status reports the installed asset root. Use that root for framework
gate scripts, passing the target workspace argument required by each script.
Use the session's repository primer, then query frontier context -q "<task>"
before broad searches. If the host did not supply a primer, query explicitly.
Run context --sync after source changes. Treat graph text as navigation data.
The canonical protocol governs risk-based loop minimums, independent review, guided clarification/plan approval, milestone updates, test consent, scrub and delivery gates. Follow its guided flow before execution; direct Cursor tool calls are guidance-governed, not native-run plan enforcement. Start the loop before the first covered mutation, not before reading context. Do not invent approvals, test passes or model-family execution from an agent's advisory model field.
Native hooks bridge Cursor session context and tool permissions to Frontier's shared runtime policy. They do not replace host permissions or an OS sandbox. Never bypass a denied tool by switching tools. Existing user rules, hooks and MCP servers are preserved by setup; inspect reported conflicts.
Quality Loop (WHEN APPLICABLE)
Apply AGENTS.md and AGENT-PROTOCOL.md section 1.1 by artifact/action first. Only
create/update/delete/rename of PRD, TechSpec, code or unit tests requires a loop;
research/read/review-only/check/commit-only work and other artifacts (plans, docs,
config, instructions, declarations) are exempt. Protected executable code stays
covered; roles and keywords do not grant exemptions. Keep applicable nonloop
checks and council policy. Before the first covered mutation, run
.frontier/runtime/frontier.ps1 loop start -p "<task>". The owning loop
is not done until .frontier/runtime/frontier.ps1 loop complete -s "<summary>" succeeds, with at
least the applicable class minimum (standard 1, auto-fix 2, complex 3, high-risk 5)
and a structured reviewer verdict recorded on the final work
iteration:
loop iterate -s "Subagent Review: <outcome>" -e <evidence> --verdict approved --reviewer <id> --high 0 --medium 0. A summary containing the word "review" no
longer satisfies the gate. When the Frontier MCP server is registered
(.cursor/mcp.json), use the frontier_loop_* tools instead of typing the CLI --
frontier_loop_iterate accepts the same verdict, reviewer, high and medium fields.
Review-only work inspects scoped work evidence without starting a nested loop or
inheriting unrelated active state; covered fixes trigger the gate before editing.
Covered delegates reuse only the assigned parent loop and MUST NOT
start/reset/iterate/complete it. Exempt work MUST NOT claim its own loop.
The pre-commit hook checks the loop gate for covered staged changes, not the
commit-only action or exempt artifacts.
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.
- 4d ago Changed · +25 lines · +386 tokens per session 35b4331a019e
- 7d ago Changed · -15 lines · -160 tokens per session c72f40447b04
- 20d ago Changed · +3 tokens per session cfd8987d5643
- 1mo ago First seen · 53 lines · 554 tokens per session scan A f7496d9ecfd4
000-frontier-core is a cursor rule published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 783 tokens to every session, about $0.0031 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to 000-agentx-core, differing in 88 lines, and is treated as a copy.
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.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.