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/review-issuesgit 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 | $0.01099 |
| Opus 5 | $0.00000 | $0.00549 |
| Sonnet 5 | $0.00000 | $0.00220 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
review-issues 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command — Review Issues
Session reads:
event_list,volume_rank_map,event_details_cacheSession writes:issues_list,event_list,volume_rank_map
Fetch open data quality issues, triage by severity, produce a prioritised report. Execute silently.
Phase 1 — Fetch Issues
Pull every open data quality issue for the project and normalise into issues_list.
Load the project's open issues.
If the response exceeds 200 entries, sort by timestamp descending and keep the top 200. This is a UX cap to keep the triage report navigable — the rest can be reviewed in subsequent runs as the top ones are dismissed.
Deduplicate on (event_name, property_name, issue_type) — keep the most recent timestamp.
Store as issues_list. Each entry: { id, issue_type, description, event_name, property_name, timestamp, status }.
If zero issues → output ✅ No open data quality issues. → return to Execution loop.
Phase 2 — Triage
Group every issue by type, then assign a severity to each.
Group by type (precedence order — first match wins)
Evaluate each issue against these patterns in order. Assign to the first group that matches:
- Type Drift — issue_type contains "type" or "drift"
- Null Property Values — issue_type contains "property" or "null"
- Volume Anomalies — issue_type contains "volume" or "anomaly"
- Other — everything else
Assign severity
If volume_rank_map is not in session, fetch it now: run the payload in assets/volume-ranking-query.json and parse into volume_rank_map: { event_name: { volume, rank } }. If the query fails, proceed with volume_rank_map = {} — severity scoring below will skip the volume tiebreaker.
Null Property Values:
- High → property on top-20 event OR key dimension (
user_id,content_id,platform,plan_id,subscription_status,device_type) - Medium → property on active event (has 7-day volume)
- Low → on hidden / dropped / zero-volume event
Type Drift:
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 · 138 lines · 0 tokens per session scan A 82a4a0bcc4c3
review-issues is a command published in the GitHub repository mixpanel/ai-plugins (15 stars, last pushed 8d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,099 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.