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/astro-stack/django-orbit/claude-mdgit clone --depth 1 https://github.com/astro-stack/django-orbitWhat 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 | $0.01333 | $0.01333 |
| Opus 5 | $0.00666 | $0.00666 |
| Sonnet 5 | $0.00267 | $0.00267 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
django-orbit 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 2d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
Django Orbit is a reusable Django app (published to PyPI as django-orbit) that provides "satellite observability" — a debugging/monitoring dashboard at /orbit/ that records requests, SQL queries, logs, exceptions, cache operations, model events, background jobs, and more. It is inspired by Laravel Telescope.
The key design constraint: Orbit must never interfere with the host app. Every watcher must fail gracefully (WATCHER_FAIL_SILENTLY), and all writes to OrbitEntry must be guarded by _table_exists() to prevent poisoning migrations on a fresh database.
Commands
# Install in editable mode with dev dependencies
pip install -e ".[dev]"
# Run all tests
pytest
# Run a single test file
pytest tests/test_core.py
# Run a single test by name
pytest tests/test_core.py::test_middleware_captures_request
# Run with coverage
pytest --cov=orbit --cov-report=html
# Format and lint
black orbit tests
isort orbit tests
flake8 orbit tests
mypy orbit
# Run the demo server
python demo.py setup # Populate sample data
python manage.py runserver
Architecture
Central model: OrbitEntry (orbit/models.py)
A single polymorphic model storing all telemetry. All event types share one table with a type discriminator and a JSONField payload. Entries are grouped across a request lifecycle via family_hash.
Data flow
HTTP Request
→ OrbitMiddleware (orbit/middleware.py)
→ installs OrbitQueryWrapper on connection (orbit/recorders.py)
→ sets family_hash context for log handler (orbit/handlers.py)
→ calls get_response()
→ Response captured → OrbitEntry(type='request') saved
→ All SQL queries → OrbitEntry(type='query') saved
→ All log calls → OrbitEntry(type='log') via OrbitLogHandler
Watcher system (orbit/watchers.py)
install_all_watchers() is called from OrbitConfig.ready(). Each watcher monkey-patches a Django/Python subsystem:
- Command watcher: patches
BaseCommand.execute - Cache watcher: patches
cache.get/set/delete - Model watcher: connects to
post_save/post_deletesignals - HTTP client watcher: patches
urllib3/requests - Mail watcher: patches
EmailMessage.send - Signal watcher: patches
Signal.send - Redis watcher: patches
redis.StrictRedis - Job watcher: hooks into Celery/Django-Q/RQ signals
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.
- 2d ago First seen · 122 lines · 1,333 tokens per session scan A a2a75f8b0b70
django-orbit CLAUDE.md is an instructions file published in the GitHub repository astro-stack/django-orbit (176 stars, last pushed 9d ago), licensed MIT. It adds 1,333 tokens to every session, about $0.0067 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
opensre AGENTS.md
AGENTS.md instructions for Tracer-Cloud/opensre, covering opensre development reference, ci failures and tests (mandatory — every pr / push), build and run commands, code style and tests (high-signal, not exhaustive).
CPA-Manager-Plus AGENTS.md
AGENTS.md instructions for seakee/CPA-Manager-Plus, covering repository rules, operation, layout, commands and architecture.
openllmetry CLAUDE.md
Instructions for traceloop/openllmetry, covering openllmetry repository guide, repository structure, nx workspace commands, run tests across all packages and run linting across all packages.
openlit AGENTS.md
AGENTS.md instructions for openlit/openlit, covering openlit agent rules, ce/oss boundary, extension points, project hierarchy and ui and security.
evlog AGENTS.md
AGENTS.md instructions for HugoRCD/evlog, covering evlog, commands, monorepo structure, conventions and code style: no slop.
agent-inspect AGENTS.md
Instructions for rajudandigam/agent-inspect, covering agentinspect ai maintainer instructions, product boundary, source of truth, public-copy rule and start every task.