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 ragnarok22/agent-skills --skill django-doctorgit clone --depth 1 https://github.com/ragnarok22/agent-skillsWrote 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/ragnarok22/agent-skills/django-doctor)<a href="https://agentmods.dev/skills/ragnarok22/agent-skills/django-doctor"><img src="https://agentmods.dev/badge/skills/ragnarok22/agent-skills/django-doctor/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/ragnarok22/agent-skills/django-doctor"><img src="https://agentmods.dev/badge/skills/ragnarok22/agent-skills/django-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00076 | $0.02271 |
| Opus 5 | $0.00038 | $0.01136 |
| Sonnet 5 | $0.00015 | $0.00454 |
| Haiku 4.5 | $0.00008 | $0.00227 |
Grade A, and why
django-doctor 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 11d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Django Doctor
Run a deterministic Django audit across four categories: Security, Performance, Correctness, and Architecture.
Primary output is a scored report with sanitized evidence summaries and prioritized remediation actions.
How to use
Read individual rule files for detailed explanations and search patterns.
Conventions
- rules/audit-conventions.md - Audit conventions and shared defaults
Security (14 rules)
- rules/security.md - SEC-01 through SEC-14
- SEC-01: Hardcoded SECRET_KEY
- SEC-02: DEBUG=True in deployable settings
- SEC-03: Raw SQL without parameterization
- SEC-04: Missing CSRF protection on state-changing endpoints
- SEC-05: Exposed traces or raw exception messages
- SEC-06: Wildcard CORS or ALLOWED_HOSTS
- SEC-07: Missing authentication on protected endpoints
- SEC-08: Secrets committed in source
- SEC-09: Missing security middleware settings
- SEC-10: XSS via
mark_safe()or|safetemplate filter - SEC-11: Unsafe file upload handling
- SEC-12: Missing rate limiting on authentication endpoints
- SEC-13: Mass assignment via uncontrolled serializer fields
- SEC-14: Unsafe
JsonResponsewith unescaped user data
Performance (11 rules)
- rules/performance.md - PERF-01 through PERF-11
- PERF-01: Missing select_related/prefetch_related
- PERF-02: Unbounded list endpoints
- PERF-03: N+1 queries in loops
- PERF-04: Missing indexes for hot filters
- PERF-05: Loading unnecessary model fields
- PERF-06: Heavy synchronous work in request cycle
- PERF-07: Missing caching for low-churn reference data
- PERF-08: Per-row writes instead of bulk operations
- PERF-09: Using
.count()where.exists()suffices - PERF-10: Heavy synchronous work in Django signals
- PERF-11: QuerySet evaluated multiple times
Correctness (14 rules)
- rules/correctness.md - COR-01 through COR-14
- COR-01: Missing migrations
- COR-02: Missing model constraints for business rules
- COR-03: Risky cascade deletes
- COR-04: Timezone-naive datetime usage
- COR-05: Mutable default arguments
- COR-06: Silenced exceptions
- COR-07: Inefficient or incorrect queryset evaluation
- COR-08: Django system check failures
- COR-09: Missing
transaction.atomic()for multi-step writes - COR-10: Using
.get()withoutDoesNotExisthandling - COR-11: Missing
__str__on models - COR-12: Deprecated Django APIs still in use
- COR-13: Settings not split by environment
- COR-14: Incorrect signal receiver signatures
What ships with it
8 files 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.
- 11d ago First seen · 237 lines · 76 tokens per session scan A a7999851139b
django-doctor is a skill published in the GitHub repository ragnarok22/agent-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 2,271 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.