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/apideck-libraries/api-skills/apideck-pythonnpx skills add apideck-libraries/api-skills --skill apideck-pythongit clone --depth 1 https://github.com/apideck-libraries/api-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 | $0.00116 | $0.02092 |
| Opus 5 | $0.00058 | $0.01046 |
| Sonnet 5 | $0.00023 | $0.00418 |
| Haiku 4.5 | $0.00012 | $0.00209 |
Grade A, and why
apideck-python 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apideck Python SDK Skill
Overview
The Apideck Unified API provides a single integration layer to connect with 200+ third-party services across accounting, CRM, HRIS, file storage, ATS, e-commerce, and more. The official Python SDK (apideck-unify) provides typed clients for all unified APIs.
Installation
pip install apideck-unify
Requires Python 3.9+. Dependencies: httpx, pydantic.
IMPORTANT RULES
- ALWAYS use the
apideck-unifySDK. DO NOT make rawhttpx/requestscalls to the Apideck API. - ALWAYS pass
api_key,app_id, andconsumer_idwhen initializing the client. - ALWAYS set the
APIDECK_API_KEYenvironment variable rather than hardcoding API keys. - USE
service_idto specify which downstream connector to use (e.g.,"salesforce","quickbooks"). If a consumer has multiple connections for an API,service_idis required. - USE context managers (
with/async with) for client lifecycle management. - USE the
fieldsparameter to request only the columns you need. - USE the
filter_parameter (note the trailing underscore) to narrow results server-side. - ALWAYS handle errors with try/except using
models.ApideckErroras the base class.
Quick Start
from apideck_unify import Apideck
import os
with Apideck(
api_key=os.getenv("APIDECK_API_KEY", ""),
app_id="your-app-id",
consumer_id="your-consumer-id",
) as apideck:
res = apideck.crm.contacts.list(
service_id="salesforce",
limit=20,
filter_={"email": "[email protected]"},
)
while res is not None:
for contact in res.data:
print(contact.name, contact.emails)
res = res.next()
SDK Patterns
Client Setup
from apideck_unify import Apideck
import os
with Apideck(
api_key=os.getenv("APIDECK_API_KEY", ""),
app_id="your-app-id",
consumer_id="your-consumer-id",
) as apideck:
# Make API calls here
pass
The consumer_id identifies the end-user whose connections are being used. In multi-tenant apps, set this per-request or per-user session.
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 · 246 lines · 116 tokens per session scan A 1c05cbe01421
apideck-python is a skill published in the GitHub repository apideck-libraries/api-skills (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 116 tokens to every session and 2,092 once invoked, about $0.0006 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
form-design
Forms have three layers of guidance: helper text below the input explains what to enter, placeholder shows the expected format, and validation confirms correctness. Real-time validation for complex inputs. Submit enables only when the form is valid. Use when designing or reviewing any form, input field, or data entry…
user-flows-and-guided-paths
Related features and tasks — such as purchase flows, onboarding, or multi-step configuration — should be designed as natural, guided paths that feel coherent and fit the product hierarchy. Use wizards for complex sequential tasks. Use when designing flows, onboarding, checkout, setup sequences, or any multi-step user…
workflow-commit
Commit changes the way a sandboxed agent must — write Conventional Commit messages and, because commit signing fails inside the sandbox, hand the real commit off through a generated commit.sh script. Inside a git worktree, commit normally (unsigned) and emit a commit.sh that re-signs the range; in the main checkout…
ebay-sold-listings-search
All process output to user (progress updates, process notifications) follows the user's language.
1688-product-detail
Extracts comprehensive wholesale product data from 1688.com product detail pages: title, tiered pricing, SKU variants with dimensions/weight, product images, seller info, shop scores, buyer protection, cross-border flags, product attributes, coupon/promotion data, and review stats. Use when user mentions 1688…
amazon-listing-competitor-analysis-skill
This skill helps users analyze Amazon competitor listings by ASIN and produce structured competitive intelligence plus strategic opportunity points for their own go-to-market. The Agent should proactively apply this skill when users want to analyze a competitor Amazon listing by ASIN, understand what a top-ranked…