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 skills/posthog/posthog-foss/improving-drf-endpointsnpx skills add PostHog/posthog-foss --skill improving-drf-endpointsgit clone --depth 1 https://github.com/PostHog/posthog-fossWhat 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 | $0.00086 | $0.02601 |
| Opus 5 | $0.00043 | $0.01300 |
| Sonnet 5 | $0.00017 | $0.00520 |
| Haiku 4.5 | $0.00009 | $0.00260 |
Grade A, and why
improving-drf-endpoints 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 today.
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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improving DRF Endpoints
Before you propose a contract test against the generated OpenAPI schema, check things already tried. Six PRs took that idea, and none merged.
Overview
Serializer fields are the source of truth for PostHog's entire type pipeline:
Django serializer → drf-spectacular → OpenAPI JSON → Orval → Zod schemas → MCP tools
Every help_text, every field type, every @extend_schema annotation flows downstream.
A missing help_text means an agent guessing at parameters.
A bare ListField() means z.unknown() in the generated Zod schema.
Getting the serializer right means every consumer — frontend types, MCP tools, API docs — gets correct types and descriptions automatically.
When to use
- Editing or reviewing any file that defines a
SerializerorViewSet - Fixing OpenAPI spec warnings or generated type issues
- Preparing an endpoint for MCP tool exposure
- Code review of API changes
Audit checklist
Triage: check the generated output first
Before diving into Python, look at the committed generated types to see what's broken. Find the generated files for the endpoint's product:
- Core API:
frontend/src/generated/core/ - Product APIs:
products/<product>/frontend/generated/
Each has two files:
api.schemas.ts— TypeScript interfaces derived from serializers. Search for the serializer name and look forunknowntypes (bareListField/JSONField), missing JSDoc descriptions (missinghelp_text), or overly genericRecord<string, unknown>shapes.api.ts— API client functions. Check if the endpoint's operation exists at all — if missing, the viewset method likely lacks@extend_schema.
This tells you exactly which fields and endpoints to prioritize.
Serializer fields
Work through this list for every serializer and viewset you touch.
- Every field has
help_text— describes purpose, format, constraints, valid values - No bare
ListField()orDictField()— always specifychild=with a typed serializer or field - No bare
JSONField()— create a custom field class with@extend_schema_field(TypedSchema) SerializerMethodFieldhas@extend_schema_fieldon itsget_*methodChoiceFieldhas explicitchoices=with all valid values listed- Avoid collision-prone enum field names —
format,type,status,kind,level,mode,state,platform,providerclash with existing choices and fail CI under--fail-on-warn; pick a specific name or add anENUM_NAME_OVERRIDESentry up front. A product enum's entry must point at a re-export in the product'sbackend/facade/enums.py, never at an internal module — an internal target goes stale invisibly when the product refactors (see serializer-fields.md) - Read vs write serializers are separate when input shape differs from output
- Every success response is backed by a serializer — returning raw dicts or untyped lists means no generated types downstream
What ships with it
4 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.
- today Changed bcf3aff80b59
- yesterday First seen · 184 lines · 86 tokens per session scan A e330e72f7a5c
improving-drf-endpoints is a skill published in the GitHub repository PostHog/posthog-foss (713 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 2,601 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…