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 instructions/qapla/qapla-api-skill/agents-mdgit clone --depth 1 https://github.com/Qapla/qapla-api-skillWhat 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 | $0.00748 | $0.00748 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
qapla-api-skill AGENTS.md 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.
What it actually says
Qapla' Public API (v1.3)
When the task involves integrating with or answering questions about the
Qapla' shipping & tracking REST API (push shipments or raw orders, generate
and confirm carrier labels, track parcels, get multi-carrier quotes, look up
pickup points/PUDO, verify addresses, list couriers and channels), use the
knowledge in this repo's references/ directory.
Start here: read references/overview.md — it is
the canonical orientation (domain model + "which endpoint do I need?" decision
rule). Then references/conventions.md and references/authentication.md apply
to every call, and the per-endpoint deep-dives live in
references/{pushshipment,pushorder,createlabel,getquotes,getpudos,trackingbytimeframe,apivirtual}.md
with the full catalog in references/endpoints.md. To receive outbound event
callbacks (Pillar 2) see references/webhooks.md; to interpret tracking statuses
see references/statuses.md (branch on the canonical id); for the version policy
and the separate v2 generation see references/versioning.md; to upgrade a legacy
integration see references/migration.md. For the v2 API (Bearer/JWT, RESTful,
async jobs) start at references/v2/overview.md and its resource deep-dives
(references/v2/{authentication,parcels,sandbox,couriers,stock-release,endpoints}.md).
Runnable sample payloads are in
references/examples/; a dependency-free reference client is
scripts/qapla_client.py.
Core facts (the rest is in references/overview.md):
| Topic | Value |
|---|---|
| Base URL | https://api.qapla.it/<version>/<endpoint> (e.g. https://api.qapla.it/1.3/pushShipment) |
| Auth | Per-channel API Key, sent as apiKey in the JSON body. Treat it as a secret; never hard-code it. |
| Response envelope | {"<endpointName>": {"result": "OK"|"KO", "error": null|"<message>"}}. For batch endpoints also check the per-item result. |
| Rate limit | Token bucket: 120 capacity, +2/sec. A batch of N items costs N tokens. Over limit → HTTP 429 (back off and retry). |
| Sandbox | Pass "sandbox": true in the body where supported (e.g. createLabel). Exception: getQuotes uses an x-sandbox header. |
| Versions | 1.3 is current; many endpoints are still 1.2-only (not yet migrated), so calling them under /1.2/ is expected. 1.4 is createLabel-only. A separate v2 (Bearer/JWT, RESTful, async jobs) is the platform's emerging generation; its stable core is documented under references/v2/. See references/versioning.md. |
Guardrails: this documents the public API only — do not invent endpoints, parameters, or fields. The live docs at https://api.qapla.dev/1.3/ are the source of truth; if anything here drifts, trust them.
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 First seen · 41 lines · 748 tokens per session scan A 0b3ac1af0dda
qapla-api-skill AGENTS.md is an instructions file published in the GitHub repository Qapla/qapla-api-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 748 tokens to every session, about $0.0037 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 instructions, from other repositories
shopify-theme-builder AGENTS.md
Instructions for moVictor99/shopify-theme-builder, covering agents.md — shopify-theme-builder, three hard constraints (never trade these away), conventions and composition.
omg-payment-skill AGENTS.md
AGENTS.md instructions for chenmitchell/omg-payment-skill, covering agents.md — openai codex 與 agent sdk 使用指引, 適用對象, 載入方式, 方式一：作為知識庫 and 方式二：作為 system prompt extension.
omg-payment-skill CLAUDE.md
Claude Code instructions for chenmitchell/omg-payment-skill, covering claude code 使用指引, 前置條件, 安裝方式, 方式一：作為專案 skill and 方式二：作為使用者層級 skill.
omg-payment-skill GEMINI.md
Gemini CLI instructions for chenmitchell/omg-payment-skill, covering google gemini 使用指引, 適用版本, 載入方式, gemini web / app and gemini cli.
stewie-pixel guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
rubydex AGENTS.md
AGENTS.md instructions for Shopify/rubydex, covering instructions, project overview, documentation, ruby gem and structure.