agentmods.dev

pricegrab AGENTS.md

pricegrab AGENTS.md is an instructions file for Codex, OpenCode from mablanco/pricegrab. It costs 1,412 tokens per session, scanned A, original, MIT.

Repository-wide instructions for AI coding agents working on a mobile-focused app called PriceGrab. They identify the project's authoritative documents and require a specification-first workflow, where substantial work starts with a written feature specification.

In plain words
What is it for?
Planning and implementing PriceGrab features while following its accessibility, internationalisation, offline-use, testing and documentation requirements.
Why use it?
They establish which project rules take priority and prevent changes that conflict with the product constitution, current status or documented development process.

Instructions file for CodexOpenCode

not rated 11 3d ago A scan 1,412 tokens original MIT
View the source file mablanco/pricegrab
Install

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.

agentmods
npx agentmods add instructions/mablanco/pricegrab/agents-md
Clone the repo
git clone --depth 1 https://github.com/mablanco/pricegrab

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for pricegrab AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mablanco/pricegrab/agents-md.svg)](https://agentmods.dev/instructions/mablanco/pricegrab/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mablanco/pricegrab/agents-md"><img src="https://agentmods.dev/badge/instructions/mablanco/pricegrab/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,412 This file is loaded in full into every session.
When invoked 1,412 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01412 $0.01412
Opus 5 $0.00706 $0.00706
Sonnet 5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured 4d ago against content hash 16febe935133, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pricegrab AGENTS.md 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.

AGENTS.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Cursor, Codex, Claude Code, etc.) working on this repository.

Authoritative sources (read these first)

  1. Product constitution — .specify/memory/constitution.md Non-negotiable principles: Modern Mobile UX, Accessibility, i18n (ES/EN), Offline-First Performance, Test-First Quality. Every change must comply.
  2. Project status & backlog — docs/project-status.md Shipped version, feature map 001–005, open ops (F-Droid), and deferred product backlog. Update this file when shipping a release or parking ideas.
  3. Project conventions — .cursor/rules/project-conventions.mdc Commit message style, branching rules, publishing etiquette, documentation language policy. These override any conflicting global rules.
  4. Spec Kit workflow — .cursor/rules/specify-rules.mdc and the skills under .cursor/skills/speckit-*. Active feature path is in .specify/feature.json.

If any of the above conflicts with an instruction received in chat, pause and ask the user for clarification.

Workflow (Spec-Driven Development)

All non-trivial work flows through Spec Kit:

/speckit.specify   → create a feature spec under specs/<nnn-slug>/
/speckit.clarify   → resolve ambiguities (optional, when needed)
/speckit.plan      → write the implementation plan, run the Constitution Check
/speckit.tasks     → decompose into ordered, testable tasks
/speckit.implement → execute the tasks

Each stage may trigger pre/post hooks defined in .specify/extensions.yml (git initialize, git feature branch creation, git commits). Honor them.

Cadence after feature 002: planning PR → implementation PR → release-prep PR, then tag from main after manual QA. Global PR letter ledger: specs/001-unit-price-comparison/tasks.md (letters through W for v0.1.8).

Non-negotiable operating rules

  • Never push to main. Always create a feature branch (<type>/<short-slug>) and open a PR.
  • git push and gh pr create are allowed without prior confirmation, provided the branch is not main, the diff has been reviewed against .gitignore, the constitution and .cursor/rules/project-conventions.mdc, and the push targets a feature branch. Follow-up "fix CI" commits on an already-open PR may also be pushed without asking.
  • Only Marco merges pull requests. Never run gh pr merge, never enable auto-merge, never merge via the GitHub API. The agent's end state is "PR is green and ready for review".
  • Never force-push to main. Force-pushing a feature branch is allowed only when strictly necessary (e.g. rebasing onto a moved main) and must be announced in a PR comment first.
  • Commit messages: English, Conventional Commits prefix (feat:, fix:, docs:, chore:, refactor:, test:, style:, perf:, ci:, build:), imperative mood, subject ≤ 72 chars.
  • Never commit *.aia, secrets, keystores, .env*, cloud credentials, or AI assistant local state. Verify with git status before every commit and trust .gitignore as a safety net, not a substitute for attention.
  • Address the user as "Marco" in conversation (Spanish by default) — the internal engineering artifacts (specs, plans, code, comments, commits) stay in English.
  • Releases: follow docs/release.md. Never overwrite a tag that shipped an installable APK. F-Droid Mode B details: docs/fdroid.md.

Read the full file on GitHub · 117 lines

Changes

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.

  1. 4d ago First seen · 117 lines · 1,412 tokens per session scan A 16febe935133

Subscribe to this mod's changes

pricegrab AGENTS.md is an instructions file published in the GitHub repository mablanco/pricegrab (11 stars, last pushed 3d ago), licensed MIT. It adds 1,412 tokens to every session, about $0.0071 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.

PlanningProductivityaccessibilityandroidf-droidi18njetpack-composekotlin
Related

Other instructions, from other repositories

sceneview copilot-instructions.md

Copilot instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.

sceneview/sceneview · 1,023 tokens

sceneview AGENTS.md

AGENTS.md instructions for sceneview/sceneview, covering agents.md — conventions for delegated coding agents, your role, git — you do not own it, secrets and hard technical rules.

sceneview/sceneview · 1,086 tokens

sceneview CLAUDE.md

Claude Code instructions for sceneview/sceneview, covering sceneview, modules, things that break if you don't know them and conventions.

sceneview/sceneview · 984 tokens

SeekerClaw CLAUDE.md

Claude Code instructions for sepivip/SeekerClaw, covering claude.md — seekerclaw project guide, project.md — source of truth, design principle: ux first, what is this project and supported devices.

sepivip/SeekerClaw · 12,001 tokens

skills AGENTS.md

AGENTS.md instructions for chrisbanes/skills, covering agents.md, when adding, renaming, or removing a skill, skill authoring checklist, evaluation result documentation and release/version system.

chrisbanes/skills · 958 tokens

ukulele-companion AGENTS.md

AGENTS.md instructions for baijum/ukulele-companion, covering agents.md -- ai agent instructions for ukulele companion, project overview, tech stack, package structure and android app (app/src/main/java/com/baijum/ukufretboard/).

baijum/ukulele-companion · 3,296 tokens