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 OutlineDriven/outline-driven-development --skill django-access-reviewgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/django-access-review)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/django-access-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/django-access-review/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/outlinedriven/outline-driven-development/django-access-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/django-access-review.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 | $0.00044 | $0.01186 |
| Opus 5 | $0.00022 | $0.00593 |
| Sonnet 5 | $0.00009 | $0.00237 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
django-access-review 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Django access control & IDOR review
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to review Django access control, IDOR, authorization, permissions, or tenant isolation |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Investigate source via read/grep/glob only. |
| Side effect | Reports access-control vulnerabilities as chat output; changes nothing |
| Done | Validated IDOR/authz findings with evidence, impact, and fix suggestions returned |
Inputs
Required: a Django or Django REST Framework codebase reachable as filesystem paths.
Optional: a specific component, endpoint, or model to scope the review. Without a scope, review the whole codebase and state which endpoints were and were not covered.
Procedure
Investigate rather than pattern-match. Every codebase enforces authorization differently; understand this implementation before judging it.
-
Map the authorization model. Before judging any endpoint, determine where permission checks live (decorators, middleware, base classes, DRF
permission_classes, custom mixins), how queries are scoped (custom managers,get_queryset()overrides, middleware-set context), and what the ownership model is (single user, organization/tenant, hierarchical, role-based). Use grep/glob over*.pyto findpermission_classes,@login_required,@permission_required, base view classes, managers,get_queryset, and ownership fields (owner,user_id,organization,tenant). Do not proceed to findings until the model is understood. Done when: the authorization model and ownership rules are understood. -
Map the attack surface. Identify models that hold user data and carry ownership fields or are addressed by ID in URLs, request bodies, or query params. For each, list the exposed operations: list, retrieve, create, update, delete, and custom actions. Done when: models and exposed operations are mapped.
-
Ask the core question per endpoint. For each endpoint handling user data: "If I am User A and I know the ID of User B's resource, can I access, modify, or delete it?" Trace the data flow: (a) where the resource ID enters (URL path, query param, request body); (b) where that ID fetches data (the ORM query or DB call); (c) what checks exist between entry and fetch: is the query scoped to the current user, is there an explicit ownership check, is there an object-level permission, does a base class/mixin/manager enforce access. If no check is visible, check parent classes, middleware, managers, and URL-level decorators before concluding a gap. Done when: each endpoint has an end-to-end authorization trace.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -12 tokens per session 58d56a7bd178
- 5d ago First seen · 46 lines · 56 tokens per session scan A d81ab0f6dfde
django-access-review is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,186 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 2026-09-03.
Other skills, from other repositories
make-bot-ui
Use when a human invokes this skill to build a webhook UI that wakes a bot. Not for unpreviewed or unapproved credential, host, Tailscale, deployment, remote, paid, or irreversible changes.
contract-driven
Use when crossing a public API boundary, guarding complex invariants, or hardening untrusted input or integration seams. Not for remote or irreversible changes.
mcp-builder
Use when asked to create an MCP server to integrate an API or service in Python or TypeScript. Not for remote, credential, publish, deploy, or irreversible changes.
document-api-endpoint
Use when reconciling an API endpoint's generated OpenAPI schema and declared response types with its actual runtime response. Not for general API documentation: use docs-and-adrs.
api-and-interface-design
Use when asked to design or change a public API, route, CLI flag, or module boundary. Not for remote, credential, publish, deploy, or irreversible changes.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.