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 skills add PostHog/posthog-foss --skill optimizing-clickhouse-and-hogql-queriesgit 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/optimizing-clickhouse-and-hogql-queries)<a href="https://agentmods.dev/skills/posthog/posthog-foss/optimizing-clickhouse-and-hogql-queries"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/optimizing-clickhouse-and-hogql-queries/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/optimizing-clickhouse-and-hogql-queries"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/optimizing-clickhouse-and-hogql-queries.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 31 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 31 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 33 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 34 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 36 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 | $0.00177 | $0.05182 |
| Opus 5 | $0.00088 | $0.02591 |
| Sonnet 5 | $0.00035 | $0.01036 |
| Haiku 4.5 | $0.00018 | $0.00518 |
Grade A, and why
optimizing-clickhouse-and-hogql-queries 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimizing ClickHouse and HogQL queries
Optimizes ClickHouse and HogQL queries (HogQL compiles to ClickHouse), not Postgres / Django ORM. For an app-DB query (Model.objects.filter(...)), stop and use profiling-slow-api-endpoints; Step 0 has the full triage.
Work from the ClickHouse SQL, not the HogQL. Get the ClickHouse SQL the query produces, optimize that, then translate the change back into the HogQL query, query runner, printer, or a migration. Reasoning about HogQL alone hides what ClickHouse executes.
Assumes you can write HogQL. For new queries from scratch use /writing-clickhouse-queries; for migration mechanics, /clickhouse-migrations.
Optimizing every query a team owns
When the job is "optimize all of team X's queries," build the full inventory first or you'll miss some.
- Resolve the team to its owned paths with
/establishing-code-ownership. Owned paths span backend Python andfrontend/src/..., often across several products; don't silently narrow to one product or to the backend. - Find queries across every path. Most are Python (
*QueryRunner,execute_hogql_query, rawsync_execute), but plenty are built client-side and POSTed to/query. Grepfrontend/for:api.queryHogQL(...),HogQLQueryString, thehogql`...`templateNodeKind.HogQLQuery/kind: 'HogQLQuery'with aquery:string- nodes that compile to ClickHouse:
DataTableNode,EventsQuery,TrendsQuery/InsightVizNode,PropertyFilterType.HogQL - literals with
SELECT ... FROM events, or product markers ('survey sent',$survey_id)
The same query is sometimes implemented twice (backend runner plus frontend HogQL, often a stalled migration). Both are in-scope; a backend printer/function fix won't reach a hand-built frontend string.
Step 0: confirm you're at the right layer
Check how the query is built:
| What you see | Where it goes | What to use |
|---|---|---|
execute_hogql_query(...), HogQLQuery, a *QueryRunner, an insight, a HogQL .ambr |
ClickHouse via the HogQL printer | This skill |
sync_execute(...), client.execute(...), hand-written SELECT ... FROM events, a migration |
ClickHouse directly (no HogQL) | This skill (steps 2-5; skip step 1) |
Model.objects.filter(...), .raw(...), a queryset, RawSQL over the app DB |
Postgres via Django ORM | Not this skill. profiling-slow-api-endpoints |
personhog_client.*, get_personhog_client(), get_person_by_* |
personhog (gRPC, Postgres) | Not this skill. posthog/personhog_client/README.md |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -6 tokens per session 590b8047a52c
- 11d ago First seen · 169 lines · 183 tokens per session scan A 5140d851e4b3
optimizing-clickhouse-and-hogql-queries is a skill published in the GitHub repository PostHog/posthog-foss (715 stars, last pushed yesterday), licensed MIT. It adds 177 tokens to every session and 5,182 once invoked, about $0.0009 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…