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/mablanco/pricegrab/project-conventionsgit clone --depth 1 https://github.com/mablanco/pricegrabWrote 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/mablanco/pricegrab/project-conventions)<a href="https://agentmods.dev/rules/mablanco/pricegrab/project-conventions"><img src="https://agentmods.dev/badge/rules/mablanco/pricegrab/project-conventions.svg" alt="Measured on agentmods" 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 | $0.00794 | $0.00794 |
| Opus 5 | $0.00397 | $0.00397 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
project-conventions 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PriceGrab — Project Conventions
These conventions apply to this repository only. They override matching global rules (e.g., the "commits in Spanish" rule from the user's global preferences). Any rule not addressed here continues to follow the user's global preferences.
Commit messages
- Write commit messages in English.
- Use Conventional Commits prefixes:
feat:,fix:,docs:,chore:,refactor:,test:,style:,perf:,ci:,build:. - Subject line: imperative mood, ≤ 72 characters, no trailing period.
- Body (optional): wrap at ~72 columns, explain the why, not the what.
Branching & PR flow
- Never push directly to
main. Always work on a feature branch and open a PR. - Branch naming:
<type>/<short-slug>— e.g.feat/compare-screen,fix/decimal-parsing-es,chore/bootstrap-project. - Delete the remote branch after the PR is merged.
- Keep
mainprotected (required reviews + passing CI) once CI exists.
Publishing & remotes
git pushandgh pr createare allowed without prior confirmation, as long as:- The push targets a feature branch, never
maindirectly. - The branch content has been reviewed by the agent against
.gitignore, the constitution and this file (no secrets, no legacy prototype sources, no*.aiafiles, no AI assistant state). - When CI fails on an open PR, follow-up "fix CI" commits may be pushed to the same feature branch without asking, until the PR is green or the agent hits a blocker it cannot resolve.
- The push targets a feature branch, never
- Only Marco merges pull requests. Never run
gh pr merge, never enable auto-merge, never squash/rebase/merge via the API. Leaving the PR "ready for review" is the end state for the agent. - Never push to
maindirectly, not even for a one-liner. Always open a PR. - Never force-push to
mainunder any circumstance. Force-pushing a feature branch is allowed only when strictly necessary (e.g. rebase to resolve conflicts) and must be preceded by a note to Marco in the PR. - Never commit legacy prototype sources (
*.aia) or any sensitive authentication material (tokens, keystores,.env, cloud credentials, AI assistant state). Rely on.gitignoreto enforce this; verify withgit statusbefore every commit.
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.
- 5d ago First seen · 70 lines · 794 tokens per session scan A ca0d72a78a69
project-conventions is a cursor rule published in the GitHub repository mablanco/pricegrab (11 stars, last pushed 4d ago), licensed MIT. It adds 794 tokens to every session, about $0.0040 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 2026-08-30.
Other cursor rules, from other repositories
cursorrules
You are an expert in SceneView, the #1 open-source 3D & AR SDK for Android and iOS.
compose-accessibility
Compose accessibility rules for TalkBack — icons, headings, Canvas, live regions, focus, modals, and attribute preservation.
testing-conventions
Testing conventions — JUnit 4, Kotest property tests, instrumented tests, what to test when.
compose-coroutines
Compose scroll/coroutine patterns — prevent programmatic scroll from being mistaken for user scroll, cancellation-safe flag resets.
ios-viewmodel
ViewModels conform to ObservableObject and expose state via @Published properties.
compose-ui
Compose UI conventions — Material 3, recomposition optimization, Compose-only UI, theming.