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 instructions/parterburn/dabble.me/agents-mdgit clone --depth 1 https://github.com/parterburn/dabble.meWrote 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/instructions/parterburn/dabble.me/agents-md)<a href="https://agentmods.dev/instructions/parterburn/dabble.me/agents-md"><img src="https://agentmods.dev/badge/instructions/parterburn/dabble.me/agents-md.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 | $0.00961 | $0.00961 |
| Opus 5 | $0.00481 | $0.00481 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade B, and why
dabble.me AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo pg_ctlcluster 18 main start How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Cursor Cloud specific instructions
Product overview
Dabble Me is a private journaling-over-email Rails 6.1 application. Users receive email prompts and reply to create journal entries. See README.md for full feature list.
Tech stack
- Ruby 3.4.10 and Node.js 22.x (managed via asdf), Rails 6.1, PostgreSQL, Redis, Sidekiq, Puma
- Sidekiq is pinned to 7.3.x (
Gemfile): Sidekiq 8+ needs Rack 3.2+ (Rails 7+). sidekiq-cron is 2.4.x (current release line). - Tests: RSpec with Capybara + headless Chrome
Shell initialization
New shells must load asdf before running Ruby/Node commands:
. "$HOME/.asdf/asdf.sh"
Or ensure ~/.bashrc sources it.
Services required
| Service | For tests | For dev server |
|---|---|---|
| PostgreSQL | Required | Required |
| Redis | Not needed (inline adapter) | Required (Sidekiq) |
| Sidekiq | Not needed | Required for async jobs |
Starting services
sudo pg_ctlcluster 18 main start
redis-server --daemonize yes
config/database.yml sets no DB username, so the app connects to Postgres via peer auth as the OS user ubuntu. If a fresh cluster errors with role "ubuntu" does not exist, create it once:
sudo -u postgres psql -c "CREATE ROLE ubuntu WITH LOGIN SUPERUSER;"
Then create/seed the dev DB with the dev env vars: bundle exec rails db:create db:schema:load db:seed.
Running the dev server
mkdir -p tmp/pids
MAIN_DOMAIN=localhost SECRET_KEY_BASE=dev_secret_key_base_1234567890 DEVISE_SECRET_KEY=dev_devise_secret_1234567890 bundle exec puma -p 3000 -C config/puma.rb
The seed admin account is [email protected] / dabble (created by rake db:seed).
Running tests
Tests require several environment variables (see .github/workflows/test.yml):
MAIN_DOMAIN=test DEVISE_SECRET_KEY=test SMTP_DOMAIN=test AWS_ACCESS_KEY_ID=test AWS_BUCKET=test AWS_SECRET_ACCESS_KEY=test bundle exec rspec
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 First seen · 83 lines · 961 tokens per session scan B a6c7c643e814
dabble.me AGENTS.md is an instructions file published in the GitHub repository parterburn/dabble.me (80 stars, last pushed today), licensed MIT. It adds 961 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.