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/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-status)<a href="https://agentmods.dev/rules/mablanco/pricegrab/project-status"><img src="https://agentmods.dev/badge/rules/mablanco/pricegrab/project-status/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/mablanco/pricegrab/project-status"><img src="https://agentmods.dev/badge/rules/mablanco/pricegrab/project-status.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 | $0.00599 | $0.00599 |
| Opus 5.5 | $0.00240 | $0.00240 |
| Sonnet 5.5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
project-status 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 1mo 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
PriceGrab — status & backlog (agent memory)
Full detail: docs/project-status.md. Refresh that
file when shipping or parking work. Summary below (as of 2026-09-08).
Now
- Shipped: v0.1.11 /
versionCode12 — richer result card (absolute + percent). Prior: 0.1.10 Settings/Material You (opt-in, default off); 0.1.9 compact rows; 0.1.8 up to 3 offers. - Dist: F-Droid Mode B + GitHub Releases; no Play Store.
- F-Droid: public suggested is 0.1.11 (also serves 0.1.9 / 0.1.8).
0.1.7 still
disable: not repro— never re-tag 0.1.7. - Active feature pointer:
.specify/feature.json→specs/008-richer-result-card(done). Next Spec Kit letters start after AF. - Icons:
ART_SCALE=0.72,ART_OFFSET_X=-17,ART_OFFSET_Y=-45.
Features shipped
001 compare → 002 reset/undo → 003 polish → 004 units → 005 multi-offer (max 3) → 006 compact row → 007 settings/Material You → 008 richer result card.
Next cue (planning chat)
Prefer free-text offer labels next; then copy/share → favorites → buy-N / pack-vs-loose. Avoid as immediate next: 4+ offers, density g↔ml, Play, live FX.
Backlog (deferred — pick via Spec Kit)
- Spec Out of Scope: 4+ offers; density g↔ml; US units; currency/FX; buy-N; history; splash; custom font; motion; tablet; Reset confirm; deeper Undo
- Ideas: free-text labels (preferred); favorites; copy/share; widget; pack-vs-loose
Conventions (pointers)
- Chat: Spanish with Marco. Artifacts: English. UI/store: ES+EN.
- Never push/merge
main. Cadence: planning → impl → release-prep → tag after QA. - Prompt Marco before any MINOR (0.2.0+) version bump.
- Playbooks:
docs/release.md,docs/fdroid.md. Ledger:specs/001-…/tasks.md. - Workspace root may be
~/Repos/PriceGrab; git/Gradle live inpricegrab/.
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.
- 1mo ago Changed · +6 lines · +91 tokens per session e0521045a961
- 1mo ago First seen · 41 lines · 508 tokens per session scan A 3515ccf586da
project-status is a cursor rule published in the GitHub repository mablanco/pricegrab (11 stars, last pushed 1mo ago), licensed MIT. It adds 599 tokens to every session, about $0.0024 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 2026-08-30.
Other cursor rules, from other repositories
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.
android-viewmodel
Android ViewModel conventions — StateFlow, repository abstraction, coroutines, no LiveData.