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.
git clone --depth 1 https://github.com/Purchasely/Purchasely-AI-PluginWrote 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/commands/purchasely/purchasely-ai-plugin/debug)<a href="https://agentmods.dev/commands/purchasely/purchasely-ai-plugin/debug"><img src="https://agentmods.dev/badge/commands/purchasely/purchasely-ai-plugin/debug/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/commands/purchasely/purchasely-ai-plugin/debug"><img src="https://agentmods.dev/badge/commands/purchasely/purchasely-ai-plugin/debug.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 | $0.00020 | $0.00091 |
| Opus 5.5 | $0.00008 | $0.00036 |
| Sonnet 5.5 | $0.00004 | $0.00018 |
| Haiku 4.5 | $0.00002 | $0.00009 |
Grade A, and why
debug 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 1mo 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
Purchasely SDK Debugging
The user invoked this command with: $ARGUMENTS
Read skills/purchasely-debug/SKILL.md from this plugin, then follow that skill exactly. Pass the arguments above as the skill's $ARGUMENTS.
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.
- 1mo ago First seen · 11 lines · 20 tokens per session scan A f127ad9baf7e
debug is a command published in the GitHub repository Purchasely/Purchasely-AI-Plugin (2 stars, last pushed 10d ago), licensed MIT. It adds 20 tokens to every session and 91 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other commands, from other repositories
flutter-build
Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.
erne-debug-video
ERNE — Video-based visual debugging using frame extraction and temporal analysis.
erne-debug
ERNE — Systematic diagnosis of bugs using the performance-profiler agent.
react-native
Command "react-native" from getsentry/toolkit, covering examples, also associate with a release and distribution(s), xcode build step (react-native xcode) and important notes.
proguard
Command "proguard" from getsentry/sentry-mcp, covering examples, upload mapping files, upload a proguard/r8 mapping file, upload multiple mapping files and validate without uploading (dry-run).
proguard
Command "proguard" from getsentry/cli, covering examples, upload mapping files, upload a proguard/r8 mapping file, upload multiple mapping files and validate without uploading (dry-run).