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/mixpanel/ai-pluginsWrote 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/mixpanel/ai-plugins/enrich-and-tag)<a href="https://agentmods.dev/commands/mixpanel/ai-plugins/enrich-and-tag"><img src="https://agentmods.dev/badge/commands/mixpanel/ai-plugins/enrich-and-tag/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/mixpanel/ai-plugins/enrich-and-tag"><img src="https://agentmods.dev/badge/commands/mixpanel/ai-plugins/enrich-and-tag.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 | $0.00000 | $0.01546 |
| Opus 5 | $0.00000 | $0.00773 |
| Sonnet 5 | $0.00000 | $0.00309 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
enrich-and-tag 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command — Enrich & Tag Lexicon
Session reads:
event_list,event_details_cache,property_names,property_details_cache,volume_rank_mapSession writes:event_list,event_details_cache,property_names,property_details_cache,existing_tags
Auto-generate display names, descriptions, and tags for events and properties that are missing them. One combined preview, one confirmation, then three sequential write groups: events → tags → properties. Execute silently.
Phase 1 — Identify Gaps
Find events and properties without descriptions, display names, or tags.
Ensure the required Session reads are loaded; load any that aren't.
Build three gap lists:
Event metadata gaps: for each event, record which of these are empty:
description(null/empty)display_name(null OR equals raw event name)
Event tag gaps: events where tags is null or empty array.
Property metadata gaps: properties where description is null/empty OR display_name is null/empty.
If all three lists are empty → output ✅ All events and properties already have descriptions, display names, and tags. → return to Execution loop.
Phase 2 — Generate Suggestions
Generate the new values for every gap found in Phase 1.
General rules
- Seed with business context. Load the project's business context (company name, product domain, business model, key user flows). Pass it into every description and tag prompt so enrichment matches the actual product instead of generic guesses from event names. Fall back to name-based generation if business context is unavailable.
- Default casing: Title Case for display names and tags. The user can override in the preview — no upfront config prompt.
Display names (events and properties)
Convert raw names from snake_case / camelCase / kebab-case into a human-readable form. Strip prefixes (mp_, $mp_, $). System events ($-prefixed) still get readable display names.
Descriptions (events and properties)
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.
- 10d ago First seen · 164 lines · 0 tokens per session scan A ddfffd831337
enrich-and-tag is a command published in the GitHub repository mixpanel/ai-plugins (14 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,546 tokens. 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.