Borrowing it
Nothing to install: this file belongs to JBurlison/WoWAddonAPIAgents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JBurlison/WoWAddonAPIAgents/main/.github/instructions/wow-api-important.instructions.mdgit clone --depth 1 https://github.com/JBurlison/WoWAddonAPIAgentsWrote 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/instructions/jburlison/wowaddonapiagents/wow-api-important)<a href="https://agentmods.dev/instructions/jburlison/wowaddonapiagents/wow-api-important"><img src="https://agentmods.dev/badge/instructions/jburlison/wowaddonapiagents/wow-api-important/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/instructions/jburlison/wowaddonapiagents/wow-api-important"><img src="https://agentmods.dev/badge/instructions/jburlison/wowaddonapiagents/wow-api-important.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 | $0.00389 | $0.00389 |
| Opus 5.5 | $0.00156 | $0.00156 |
| Sonnet 5.5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade C, and why
WoW client-aware API guidance scanned grade C with 1 finding 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Generated by npm run build from instructions/wow-api.instructions.md. --> What it actually says
WoW target selection
Use wow-addon-development and wow-client-targets. Resolve explicit targets or inspect the addon's existing configuration; ask when ambiguous. Supported targets are Retail (live), Forever (forever), and Classic progression (classic). All means those three only.
Pin source evidence per target. Verify signatures, event payloads, loaded templates, and addon restrictions before use. Apply Secret Values, combat restrictions, and deprecations only where verified for that client/build. Historical Retail 12.0.0 notes are not universal rules. Use separate target artifacts with shared core code and verified adapters. Report offline/stale evidence and distinguish static checks from in-game validation.
For visible UI changes, follow the workflow's mock-up choice before implementation, honoring an existing answer or accepted design. Use UIForever testing for available matching flavors; simulator checks do not replace real-client tests.
Preserve the accepted design using the visual-fidelity checks. Do not silently replace custom artwork with stock skins; combine custom textures and native interaction when appropriate, then compare actual rendered screenshots. Use connected client testing for available Witchcraft context/error tools and native computer use, without assuming either is installed or that no errors proves visual accuracy.
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.
- 5d ago Changed · +2 lines · +103 tokens per session 678969d1461d
- 6d ago Changed · -415 lines · -4,383 tokens per session scan A → C c7803444ef27
- 2mo ago First seen · 431 lines · 4,669 tokens per session scan A c3c6b0fca2e4
WoW client-aware API guidance is an instructions file published in the GitHub repository JBurlison/WoWAddonAPIAgents (71 stars, last pushed yesterday), licensed MIT. It adds 389 tokens to every session, about $0.0016 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
WoW client-aware API guidance compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WoW client-aware API guidanceJBurlison/WoWAddonAPIAgents | Instructions file | 71 | yesterday | MIT | C | 389 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |