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/packmindhub/packmind/agents-mdgit clone --depth 1 https://github.com/PackmindHub/packmindWhat 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 | $0.01695 | $0.01695 |
| Opus 5 | $0.00847 | $0.00847 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
packmind 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 yesterday.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
_# Nx Monorepo Structure
This is an Nx monorepo containing applications and reusable packages.
Core Technologies
- Runtime: Node.js (version specified in
.nvmrc) - Language: TypeScript
- Database: PostgreSQL with TypeORM for entity persistence
- Cache: Redis for caching
- Background Jobs: BullMQ for job queue management
- Testing: Jest with @swc/jest as test runner. Tests are run with
./node_modules/.bin/nx run <project-name>as detailed below.
Directory Structure
apps/- Deployable applications (API, frontend, CLI, e2e tests, docs)packages/- Reusable domain and infrastructure packages shared across apps.github/workflows/- CI/CD pipelines for build, test, quality checks, and deployment
Local Development Environment
Local development uses Docker Compose to run all services (API, frontend, database, Redis, etc.):
docker compose up
This starts the entire development environment. Docker Compose automatically provisions PostgreSQL and Redis - no manual setup required.
Working with Nx
The following commands apply for both NX apps and packages (use ./node_modules/.bin/nx show projects to list actual apps and packages.)
- Test a project:
./node_modules/.bin/nx test <project-name> - Lint a project:
./node_modules/.bin/nx lint <project-name> - Build a project:
./node_modules/.bin/nx build <project-name> - Test affected projects:
pnpm run test:staged - Lint affected projects:
pnpm run lint:staged
Code Quality
- Linting:
./node_modules/.bin/nx lint <project-name>runs ESLint, using the config fileeslint.config.mjs. - Formatting: Prettier is used for code formatting. You don't have to run it, it's set as a pre-commit hook.
Commands
- When running commands, ensure you use the correct Node version (see .nvmrc at the project's root level)
- When renaming or moving a file that is commited to git, use
git mvinstead ofmv - Ensure the env variable
PACKMIND_EDITIONis properly set tooss
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.
- yesterday First seen · 126 lines · 1,695 tokens per session scan A 9066f4643e00
packmind AGENTS.md is an instructions file published in the GitHub repository PackmindHub/packmind (306 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,695 tokens to every session, about $0.0085 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 instructions, from other repositories
token-saver CLAUDE.md
Instructions for ppgranger/token-saver, covering token-saver plugin, how it works and important rules.
arai CLAUDE.md
Instructions for taniwhaai/arai, covering claude.md — arai, commands, architecture, prompt-collector module (src/promptcollector.rs) and extending the match pipeline.
ai-agent-instruction-modules AGENTS.md
Instructions for tablackburn/ai-agent-instruction-modules, covering ai agent instructions, instructions for ai agents, instruction applicability matrix, available instruction files and quick reference.
arai AGENTS.md
Instructions for taniwhaai/arai, covering agents.md — arai, core discipline (non-negotiable), taniwha / subagent rules, work style and tool usage.
stenographer-mode copilot-instructions.md
Instructions for AkashAi7/stenographer-mode, covering steno mode — global instructions, contract, rules and levels.
booklib AGENTS.md
Instructions for booklib-ai/booklib, covering booklib, stack, key directories, commands and rules.