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/denyszhak/pystack-skills/python-external-clientnpx skills add denyszhak/pystack-skills --skill python-external-clientgit clone --depth 1 https://github.com/denyszhak/pystack-skillsWhat 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 | $0.00186 | $0.03536 |
| Opus 5 | $0.00093 | $0.01768 |
| Sonnet 5 | $0.00037 | $0.00707 |
| Haiku 4.5 | $0.00019 | $0.00354 |
Grade A, and why
python-external-client 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 yesterday.
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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External HTTP client pattern
Every external system your service talks to — an LLM provider, Stripe, Slack, a CRM — gets its own typed Python wrapper. The wrapper is a thin class with one method per API call your service actually needs. Inside, it uses a shared httpx.AsyncClient pool that lives for the app's lifetime and is torn down at shutdown.
This skill encodes the canonical shape: a BaseHTTPClient for shared concerns (retry policy, error handling), per-system subclasses with domain-shaped methods, and httpx.MockTransport for fast in-process tests.
Bonus payoff: provider decoupling. When you have multiple providers for the same role (OpenAI / Anthropic / Gemini for LLM, SendGrid / Postmark / SES for email), define a Protocol for the role and let each concrete client satisfy it. Services depend on the Protocol; swapping providers is one env var.
When to use this skill
- Adding a new external client (
app/clients/<name>.py) - Adding a method to an existing client because a service needs one new call
- Writing tests for a client (or a service that uses one)
- Choosing a retry policy
The rules
1. BaseHTTPClient carries the retry policy and the http pool
# app/clients/base.py — shape; full version in examples/base.py
type HTTPMethod = Literal["GET", "POST", "PUT", "PATCH", "DELETE", "HEAD", "OPTIONS"]
class BaseHTTPClient:
def __init__(self, *, http: httpx.AsyncClient, config: BaseHTTPClientConfig) -> None:
self._http = http
self._config = config
@classmethod
def from_config(cls, config: BaseHTTPClientConfig) -> Self:
http = httpx.AsyncClient(
base_url=config.BASE_URL,
timeout=config.TIMEOUT,
limits=httpx.Limits(
max_keepalive_connections=config.KEEP_ALIVE_CONNECTIONS,
max_connections=config.MAX_CONNECTIONS,
),
headers=config.auth_headers(), # per-system seam, see config below
)
return cls(http=http, config=config)
async def close(self) -> None:
await self._http.aclose()
async def _request(self, method: HTTPMethod, url: str, **kwargs: Any) -> httpx.Response:
# tenacity AsyncRetrying with stop_after_attempt(config.MAX_RETRIES) +
# wait_exponential, retrying on TransportError and HTTPStatusError.
...
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.
- yesterday First seen · 310 lines · 186 tokens per session scan A d6099d36fa20
python-external-client is a skill published in the GitHub repository denyszhak/pystack-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 186 tokens to every session and 3,536 once invoked, about $0.0009 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
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…