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 commands/mixpanel/ai-plugins/reset-lexicongit clone --depth 1 https://github.com/mixpanel/ai-pluginsWhat 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 | $0.00000 | $0.01248 |
| Opus 5 | $0.00000 | $0.00624 |
| Sonnet 5 | $0.00000 | $0.00250 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
reset-lexicon 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 3d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command — Reset Lexicon
Session reads:
event_list,event_details_cache,property_names,property_details_cacheSession writes:event_details_cache,property_details_cache
Clear descriptions, display names, and/or tags from events and properties. Destructive — always preview, then require literal CONFIRM before any writes. Execute silently.
Phase 1 — Scope Prompt
Ask the user what to clear.
Reset what? (select one or more, comma-separated)
(a) Event descriptions
(b) Event display names
(c) Event tags
(d) Property descriptions
(e) Property display names
(f) All of the above
Parse selection. Store as reset_scope set.
Phase 2 — Identify Targets
Build the lists of entities that will actually have something cleared.
Ensure the required Session reads are loaded; load any that aren't.
For each scope item, build the target list — only include entities where the field is currently non-empty (no point "clearing" an already-empty field):
- Event descriptions → events with non-empty
description - Event display names → events where
display_nameis non-null AND differs from raw event name - Event tags → events with non-empty
tagsarray - Property descriptions → properties with non-empty
description - Property display names → properties with non-empty
display_name
If all selected lists are empty → output ✅ Nothing to reset — selected fields are already empty. → return to Execution loop.
Phase 3 — Preview
Show the user what's about to be cleared and capture their confirmation.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
RESET PREVIEW — [Project Name]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
WILL CLEAR
Event descriptions: [N] events
Event display names: [N] events
Event tags: [N] events ([N] distinct tags)
Property descriptions: [N] properties
Property display names: [N] properties
SAMPLE (first 10 affected entities)
Entity │ Field │ Current Value
────────────────────────┼─────────────────┼──────────────────────
user_signup_complete │ description │ User completes signup...
add_to_cart │ tags │ Commerce, Engagement
platform │ display_name │ Platform
...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
⚠️ This is destructive. Cleared metadata cannot be recovered.
Type "CONFIRM" to proceed, "EXPORT" to save the preview as JSON without writing,
or anything else to cancel:
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.
- 3d ago First seen · 162 lines · 0 tokens per session scan A 5f96c4b218f7
reset-lexicon is a command published in the GitHub repository mixpanel/ai-plugins (15 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,248 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
git
Git operations with intelligent commit messages and workflow optimization.
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.