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/cardosofelipe/pragma-stack/claude-mdgit clone --depth 1 https://github.com/cardosofelipe/pragma-stackWhat 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 | $0.02284 | $0.02284 |
| Opus 5 | $0.01142 | $0.01142 |
| Sonnet 5 | $0.00457 | $0.00457 |
| Haiku 4.5 | $0.00228 | $0.00228 |
Grade A, and why
pragma-stack CLAUDE.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 3d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Claude Code context for FastAPI + Next.js Full-Stack Template.
See AGENTS.md for project context, architecture, and development commands.
Claude Code-Specific Guidance
Critical User Preferences
File Operations - NEVER Use Heredoc/Cat Append
ALWAYS use Read/Write/Edit tools instead of cat >> file << EOF commands.
This triggers manual approval dialogs and disrupts workflow.
# WRONG ❌
cat >> file.txt << EOF
content
EOF
# CORRECT ✅ - Use Read, then Write tools
Work Style
- User prefers autonomous operation without frequent interruptions
- Ask for batch permissions upfront for long work sessions
- Work independently, document decisions clearly
- Only use emojis if the user explicitly requests it
When Working with This Stack
Dependency Management:
- Backend uses uv (modern Python package manager), not pip
- Always use
uv runprefix:IS_TEST=True uv run pytest - Or use Makefile commands:
make test,make install-dev - Add dependencies:
uv add <package>oruv add --dev <package>
Database Migrations:
- Use the
migrate.pyhelper script, not Alembic directly - Generate + apply:
python migrate.py auto "message" - Never commit migrations without testing them first
- Check current state:
python migrate.py current
Frontend API Client Generation:
- Run
bun run generate:apiafter backend schema changes - Client is auto-generated from OpenAPI spec
- Located in
frontend/src/lib/api/generated/ - NEVER manually edit generated files
Testing Commands:
- Backend unit/integration:
IS_TEST=True uv run pytest(always prefix withIS_TEST=True) - Backend E2E (requires Docker):
make test-e2e - Frontend unit:
bun run test - Frontend E2E:
bun run test:e2e - Use
make testormake test-covin backend for convenience
Security & Quality Commands (Backend):
make validate— lint + format + type checksmake audit— dependency vulnerabilities + license compliancemake validate-all— quality + security checksmake check— full pipeline: quality + security + tests
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.
- 3d ago First seen · 254 lines · 2,284 tokens per session scan A 113482396e3d
pragma-stack CLAUDE.md is an instructions file published in the GitHub repository cardosofelipe/pragma-stack (11 stars, last pushed 6mo ago), licensed MIT. It adds 2,284 tokens to every session, about $0.0114 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
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.