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/sandeep-alluru/foghornWrote 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/sandeep-alluru/foghorn/project)<a href="https://agentmods.dev/rules/sandeep-alluru/foghorn/project"><img src="https://agentmods.dev/badge/rules/sandeep-alluru/foghorn/project/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/sandeep-alluru/foghorn/project"><img src="https://agentmods.dev/badge/rules/sandeep-alluru/foghorn/project.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 | $0.00220 | $0.00220 |
| Opus 5.5 | $0.00088 | $0.00088 |
| Sonnet 5.5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
project 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 2mo 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
80% identical to project — 8 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.
What it actually says
foghorn — Cursor Rules
What this project does
Decision staleness alerts for AI agents
Module map
src/foghorn/
├── # TODO: fill in after implementation
Invariants — never break these
- TODO: list invariants
Code style
- Python 3.10+, fully type-annotated, mypy strict mode
- Ruff lint rules: E W F I UP B S N SIM RUF PT
- No print() in library code — use rich.console.Console
- All public functions and classes must have docstrings
- Tests: pytest, CliRunner for CLI tests
When adding a new feature
- Implement in the appropriate module
- Export from init.py, add to all alphabetically
- Add tests in tests/test_.py
- Update CHANGELOG.md under [Unreleased]
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.
- 2mo ago First seen · 33 lines · 220 tokens per session scan A b8cb0fbc27d4
project is a cursor rule published in the GitHub repository sandeep-alluru/foghorn (0 stars, last pushed 2mo ago), licensed MIT. It adds 220 tokens to every session, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 80% identical to project, differing in 8 lines, and is treated as a copy.
Other cursor rules, from other repositories
crystal-memory
Mandatory Memory Crystal discipline for Cursor sessions.
memory-informed-longitudinal-work
Long-running multi-session work (research, eval loops, iterative benchmarks) — resume prior lessons, capture per-run outcomes, build up stable truths over time.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
context-loader
Use when starting a new substantive conversation or switching contexts — load relevant memories to prime the session with continuity.
memory-informed-design
Use when making architecture, API, or design decisions — consult prior decisions and capture new ones in-flight.
memory-informed-refactor
Use before substantive refactors — load relevant prior context, capture refactor insights as they land.