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 skills/tarekkharsa/agentstack/querynpx skills add Tarekkharsa/agentstack --skill querygit clone --depth 1 https://github.com/Tarekkharsa/agentstackWhat 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 | $0.00037 | $0.00573 |
| Opus 5 | $0.00018 | $0.00287 |
| Sonnet 5 | $0.00007 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
posthog_query 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 yesterday.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PostHog Query
Unofficial, agentstack-authored. Not affiliated with or endorsed by PostHog.
Use this skill when someone asks a product question in plain language ("are people dropping off at checkout?", "is the new onboarding sticking?") and you need to translate it into a concrete PostHog insight rather than guessing.
Workflow
- Restate the question as a measurable outcome. Pin down the metric (count, unique users, conversion rate, retention), the population (all users, a cohort, a single platform), and the time window before touching any tool.
- Pick the right insight type for the shape of the question:
- Trends — "how many / how often" over time, with optional breakdowns.
- Funnels — "where do people drop off" across an ordered sequence of steps.
- Retention — "do people come back" after a first action.
- Paths — "what do people actually do" when the journey is unknown.
- Map the question to real events and properties. List the project's events
first (do not assume
signupexists) and choose the closest match. Prefer unique-user math over raw event counts unless volume is the point. - Set an explicit date range and interval. Default to a window that captures at least one full cycle of the behavior (e.g. 30 days for weekly habits); never leave it implicit.
- Add breakdowns or a cohort filter only when they answer the question. One clear breakdown beats three noisy ones.
- Sanity-check the result: does the denominator make sense, is the funnel order correct, are bot or internal users excluded? State caveats with the answer.
Conventions
- Confirm the target event names against the project before building — a query on the wrong event is worse than no query.
- Funnel steps must be in the order users actually experience them; a misordered step silently reports near-zero conversion.
- Report the date range, population, and any filters alongside every number so the result is reproducible.
- Prefer saving reusable questions as named insights on a dashboard over one-off ad hoc queries.
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.
- yesterday First seen · 51 lines · 37 tokens per session scan A aeb4e91b86ee
posthog_query is a skill published in the GitHub repository Tarekkharsa/agentstack (3 stars, last pushed 18d ago), licensed Apache-2.0. It adds 37 tokens to every session and 573 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
stack-merge
Bulk-merge a Graphite stack into main via admin-bypass fast-forward push. Replaces the Graphite merge queue for rivet-dev/rivet. Invoke when the user says "merge the stack at ", "ship everything through ", "bulk-merge up to ", "fast-forward main to ", or any request to land multiple stacked PRs at once in one shot.…