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 Altinity/altinity-skills --skill altinity-expert-clickhouse-grantsgit clone --depth 1 https://github.com/Altinity/altinity-skillsWrote 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/altinity/altinity-skills/altinity-expert-clickhouse-grants)<a href="https://agentmods.dev/skills/altinity/altinity-skills/altinity-expert-clickhouse-grants"><img src="https://agentmods.dev/badge/skills/altinity/altinity-skills/altinity-expert-clickhouse-grants/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/altinity/altinity-skills/altinity-expert-clickhouse-grants"><img src="https://agentmods.dev/badge/skills/altinity/altinity-skills/altinity-expert-clickhouse-grants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.00720 |
| Opus 5 | $0.00039 | $0.00360 |
| Sonnet 5 | $0.00016 | $0.00144 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
altinity-expert-clickhouse-grants 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 10d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnostics
Run all queries from checks.sql in this skill's directory and analyze the results.
Propose Minimal Grants
Provide the smallest set of GRANT statements that match observed needed_grant values. Prefer role-based grants when the user already uses roles.
Example pattern:
-- Direct grants
GRANT SELECT ON system.processes TO user_x;
GRANT SELECT ON INFORMATION_SCHEMA.COLUMNS TO svc_y;
GRANT CLUSTER ON *.* TO svc_z;
-- Role-based grants (preferred)
GRANT SELECT ON system.processes TO role_analytics;
GRANT role_analytics TO user_x;
Scope to the narrowest object that resolves the error: db.table (or a column list) over db.*, and db.* over *.*.
Security-sensitive grants — scope tightly
Some privileges are exfiltration / SSRF / privilege-escalation surfaces. If the failing query needs one, grant the narrowest form and to a role, never broadly on *.*:
SOURCES/S3/URL/FILE/REMOTE(andREAD/WRITEon 25.7+) — external read/write; broad grants enable data exfiltration and SSRF. Grant the specific source needed, not theSOURCESumbrella.SYSTEM,INTROSPECTION— operational/internal exposure; scope to the specific subcommand.ACCESS MANAGEMENT,WITH GRANT OPTION,displaySecretsInShowAndSelect,NAMED COLLECTION ADMIN,ALLOW SQL SECURITY NONE,IMPERSONATE— privilege-escalation/secret-exposure; do not grant these to fix a routineACCESS_DENIEDwithout explicit justification.
A grant that resolves an error but is broader than needed becomes a future audit finding — see the altinity-expert-clickhouse-security skill.
Post-Upgrade Compatibility Checks
Verify access_control_improvements settings, which can change privilege requirements:
select_from_system_db_requires_grantselect_from_information_schema_requires_granton_cluster_queries_require_cluster_grant
If these are enabled post-upgrade, users may require new explicit grants for system.*, INFORMATION_SCHEMA.*, or CLUSTER. The same access_control_improvements flags (plus the version-gated source/engine/definer changes) are covered from the audit side in altinity-expert-clickhouse-security → references/14-version-specific-security-checks.md; keep the two in sync.
What ships with it
1 file 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.
- 10d ago First seen · 48 lines · 79 tokens per session scan A e380019a6764
altinity-expert-clickhouse-grants is a skill published in the GitHub repository Altinity/altinity-skills (16 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 720 once invoked, about $0.0004 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…