Borrowing it
Nothing to install: this file belongs to PostHog/posthog-foss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PostHog/posthog-foss/master/.agents/skills/querying-tophog/SKILL.mdgit clone --depth 1 https://github.com/PostHog/posthog-fossWrote 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/skills/posthog/posthog-foss/querying-tophog)<a href="https://agentmods.dev/skills/posthog/posthog-foss/querying-tophog"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/querying-tophog/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/skills/posthog/posthog-foss/querying-tophog"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/querying-tophog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 65 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 62 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 70 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 72 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 128 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00120 | $0.02080 |
| Opus 5 | $0.00060 | $0.01040 |
| Sonnet 5 | $0.00024 | $0.00416 |
| Haiku 4.5 | $0.00012 | $0.00208 |
Grade A, and why
querying-tophog 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Querying tophog
tophog is the ingestion pipeline's heavy-hitter tracker: workers accumulate
per-key aggregates (counts, timers) in memory and periodically flush them to
the tophog ClickHouse table via Kafka (clickhouse_tophog topic). It answers
"which actor is responsible" questions that fleet-level Prometheus metrics
cannot — per-metric label cardinality is unbounded (distinct_id,
session_id), so this data lives only in ClickHouse. Retention is 30 days.
The staff-only Django admin has a dashboard over it, but for agent-driven triage query it directly through the internal Metabase.
Access — internal Metabase, never Grafana
The production ClickHouse clusters hold customer data, so there is
deliberately no ClickHouse datasource for agents in Grafana. The
sanctioned path is the internal Metabase using the engineer's own SSO
session — per-person identity, attributable in Metabase's query history, no
standing credential. General mechanics live in the
querying-production-databases-via-metabase skill; the short version:
-
The user must run login themselves (the agent shell cannot access the Keychain):
hogli metabase:login --region eu(orus). macOS will prompt about "Chrome Safe Storage" — that'sbrowser_cookie3decrypting the browser's cookie store to capture the SSO session; one-time Allow is the right choice. -
Discover the database id — it is not stable across Metabase rebuilds:
hogli metabase:databases --region euPick "PostHog ClickHouse PROD Data Tier" (the data tier, not the query tier — tophog lives with the events data).
-
Run queries; the cookie is read internally and never enters the transcript:
hogli metabase:query --region eu --database-id <id> <<'SQL' SELECT ... SQL
Schema
Table tophog (Distributed over sharded_tophog), ordered by
(pipeline, lane, metric, timestamp, key), partitioned by day:
| Column | Type | Notes |
|---|---|---|
timestamp |
DateTime64(6) | Flush-window time; always bound it (daily partitions) |
metric |
LowCardinality(String) | See inventory below |
type |
LowCardinality(String) | Aggregation semantics: sum (default), max, avg |
key |
Map(String, String) | The actor: access as key['team_id'], key['distinct_id'], key['partition'], key['session_id'] |
value |
Float64 | The aggregated value for this flush window |
count |
UInt64 | Observations in the window |
pipeline |
LowCardinality(String) | e.g. analytics |
lane |
LowCardinality(String) | main, overflow, historical, async, turbo |
labels |
Map(String, String) | Extra non-key labels |
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 Changed 80b5db640876
- 11d ago First seen · 216 lines · 120 tokens per session scan A 52123974a6a5
querying-tophog is a skill published in the GitHub repository PostHog/posthog-foss (715 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 2,080 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…