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-securitygit 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-security)<a href="https://agentmods.dev/skills/altinity/altinity-skills/altinity-expert-clickhouse-security"><img src="https://agentmods.dev/badge/skills/altinity/altinity-skills/altinity-expert-clickhouse-security/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-security"><img src="https://agentmods.dev/badge/skills/altinity/altinity-skills/altinity-expert-clickhouse-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00081 | $0.01841 |
| Opus 5.5 | $0.00032 | $0.00736 |
| Sonnet 5.5 | $0.00016 | $0.00368 |
| Haiku 4.5 | $0.00008 | $0.00184 |
Grade A, and why
altinity-expert-clickhouse-security 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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClickHouse security audit
A professional, read-only security audit from system.users, system.grants, system.roles, system.row_policies, system.settings_profile_elements, system.quotas, system.named_collections, system.functions, system.clusters and supplied configuration files.
Run altinity-expert-clickhouse-connection first if the connection mode, cluster and time window are not yet established.
Core behavior
- Work as a senior ClickHouse security reviewer. Prefer read-only SQL and metadata inspection.
- Never run destructive SQL and never attempt online password guessing.
- Never print secrets, password hashes, salts, private keys, access keys, tokens, or recovered password candidates.
- Correlate findings. Do not flag a setting without considering grants, network exposure, user intent, version and observed query behavior.
- State explicitly what could not be verified from the access you had.
- Give remediation only when asked, and then minimally. For grant changes use the least-privilege, role-based method of the grants skill: the smallest scoped statements, roles over users, never a broad
*.*grant.
Query packs
checks.sql— 20 checks: server identity, fullSHOW ACCESSdump, user inventory with auth method and host ACL, roles and role graph, grant posture per principal, admin-equivalent and access-management holders, security-sensitive privileges, column-scoped grants, row policies, settings profiles and elements, quotas, named collection names, user-defined and executable functions, secure ports, cluster topology and the distributed user, external-engine tables and DEFINER views, logging and auth-audit baseline. Local node only; cluster-wide checks live inreferences/15-cluster-distributed-security.md.references/— 20 depth files, indexed below. Load only the ones a finding points at.
How to run the query packs
- Read each pack file from this skill's directory (the skill loader prints the directory path).
- Run statements one at a time, never a whole file. Statements end with
;and start with a-- @check <id> <title>header; keep the id with its result. - Honor
-- @requires: skip the statement when the named table is missing, whenkeeperis required and the server has no Keeper/ZooKeeper, or when the version condition is not met. List skipped ids with the reason. - Keep
{cluster}as written when a cluster macro exists; otherwise apply the connection skill's rewrite rule. Any other{placeholder}is a template variable: substitute a real value first or skip the statement. - On an error, record the check id and the first line of the error, then continue. Only for
UNKNOWN_IDENTIFIER, runDESCRIBE TABLE system.<table>and drop the missing column. - A
severitycolumn is the verdict for that row. Copy it; do not re-grade.
What ships with it
21 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.
- checks.sql 7.4 KB
- references/01-scope-and-safety.md 2.8 KB
- references/02-identity-authentication.md 2.6 KB
- references/03-users-roles-grants-rbac.md 4.0 KB
- references/04-definer-impersonation-principals.md 4.7 KB
- references/05-network-exposure-and-tls.md 3.1 KB
- references/06-table-functions-external-sources.md 2.5 KB
- references/07-table-engines-and-external-integrations.md 1.7 KB
- references/08-row-column-policy-security.md 2.9 KB
- references/09-settings-profiles-constraints-quotas.md 4.2 KB
- references/10-audit-logging-and-log-integrity.md 2.6 KB
- references/11-query-log-threat-hunting.md 2.9 KB
- references/12-secrets-named-collections-credentials.md 3.1 KB
- references/13-password-hash-hygiene.md 3.5 KB
- references/14-version-specific-security-checks.md 2.2 KB
- references/15-cluster-distributed-security.md 2.5 KB
- references/16-keeper-and-interserver-security.md 2.5 KB
- references/17-executable-udf-and-code-execution.md 2.3 KB
- references/18-encryption-at-rest-and-backups.md 2.7 KB
- references/19-http-interface-surface.md 2.2 KB
- references/20-reporting-severity-and-output-format.md 6.3 KB
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.
- 1mo ago Changed · +14 lines · -49 tokens per session 9d9be59cbb85
- 1mo ago First seen · 76 lines · 130 tokens per session scan A 996e2f5126df
altinity-expert-clickhouse-security is a skill published in the GitHub repository Altinity/altinity-skills (17 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,841 once invoked, about $0.0003 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.