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 skills add toffyui/ccteams --skill django-playbookgit clone --depth 1 https://github.com/toffyui/ccteamsWrote 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/skills/toffyui/ccteams/django-playbook)<a href="https://agentmods.dev/skills/toffyui/ccteams/django-playbook"><img src="https://agentmods.dev/badge/skills/toffyui/ccteams/django-playbook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/toffyui/ccteams/django-playbook"><img src="https://agentmods.dev/badge/skills/toffyui/ccteams/django-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00049 | $0.03165 |
| Opus 5 | $0.00024 | $0.01582 |
| Sonnet 5 | $0.00010 | $0.00633 |
| Haiku 4.5 | $0.00005 | $0.00316 |
Grade A, and why
django-playbook 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 9d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Django Playbook
This is the literal procedure a frontier model follows on a Django/DRF codebase. Follow it in order; most Django defects come from skipping the reconnaissance steps and writing "generic Django" instead of THIS project's Django.
Operating loop
- Pin the stack before writing a line. Read the dependency file
(
requirements.txt,pyproject.toml,Pipfile.lock, orpoetry.lock):- Django version: the
django/Djangopin. Stay inside that version's API — no Django 5.x features (GeneratedField,db_default) in a 4.2 project. Mark any version-specific advice with the version. - DRF version: the
djangorestframeworkpin, if present. If DRF is not in the deps, this is a plain-Django task — do not add serializers. - Test runner and lint:
pytest/pytest-django+ apytest.ini/[tool.pytest]→pytest; otherwisepython manage.py test.ruff/flake8/blackin deps + a config → part of verification.
- Django version: the
- Read
settings.py(or thesettings/package) before touching code.INSTALLED_APPS: which of your apps exist, which third-party apps are wired (rest_framework,django_filters,debug_toolbar).USE_TZ: ifTrue(set in generated settings for years; the global default flipped toTruein Django 5.0), all naive datetimes are a bug — see failure catalog #6.AUTH_USER_MODEL: never hard-codeauth.User; referencesettings.AUTH_USER_MODELin FKs andget_user_model()in code.REST_FRAMEWORK: default permission/auth/pagination classes — they change what an omittedpermission_classesactually does.
- Detect the project's layout and MIRROR it, don't impose. Read one
neighboring app's
models.py,views.py,serializers.py,urls.py:- Fat models (logic on models/managers) vs a
services.py/selectors.pysplit — match whichever this repo already uses (decision tree c). - App structure (
apps/<name>/vs flat), CBV vs FBV, viewsets+routers vsAPIView. Convention in THIS repo beats convention in general.
- Fat models (logic on models/managers) vs a
- Run
python manage.py checkearly — before and after your change. It catches app-config, model, and admin errors that tests lazy-load past. - Build in this order: model (fields,
on_delete,Meta.indexes,Meta.constraints) →makemigrations→ manager/service → view → serializer → url wiring. Each layer is testable before the next exists. - Migration discipline:
- One migration = schema change OR data change, never both.
- After ANY model change, run
makemigrationsand read the generated file. A model edit without a migration is a runtime error waiting for deploy. - Data migrations use
RunPythonwith a realreversefunction (RunPython.nooponly when truly irreversible — say so in a comment) and the historical model viaapps.get_model('app', 'Model'), never the importedapp.modelsclass (it drifts).
- Run the verification recipe (below) and paste real output before reporting. A diff without executed commands is a claim, not a result.
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.
- 9d ago First seen · 204 lines · 49 tokens per session scan A 9f294d5a7b02
django-playbook is a skill published in the GitHub repository toffyui/ccteams (48 stars, last pushed 8d ago), licensed MIT. It adds 49 tokens to every session and 3,165 once invoked, about $0.0002 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 skills, from other repositories
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
convex-explain-app
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.
platform-custom-field-generate
Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…
openloomi-api
OpenLoomi ships a local-first HTTP API served from the desktop app (port 3414, fallback 3515). All auth, Memory, AI, RAG, Loop, and Audit data live in a local SQLite database — your data stays on your machine and the OpenLoomi app is the source of truth. The only externally-routed auth path is the Composio OAuth…
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…
field-service-sobject-create-configure
Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…