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 po4yka/llm-wiki-skills --skill llm-wiki-gitlab-operating-modelgit clone --depth 1 https://github.com/po4yka/llm-wiki-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/po4yka/llm-wiki-skills/llm-wiki-gitlab-operating-model)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-gitlab-operating-model"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-gitlab-operating-model/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/po4yka/llm-wiki-skills/llm-wiki-gitlab-operating-model"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-gitlab-operating-model.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 | $0.00073 | $0.02273 |
| Opus 5 | $0.00036 | $0.01137 |
| Sonnet 5 | $0.00015 | $0.00455 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
llm-wiki-gitlab-operating-model 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 11d 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki GitLab Operating Model
Goal
Plan an LLM-Wiki operating model for a self-managed GitLab instance inside an enterprise/internal network, with GitLab-native governance, CI/CD, permissions, compliance, publishing and reliability controls.
Use references/docs/23-gitlab-self-hosted-operating-model.md as the reference model.
When to use
- The user runs GitLab Self-Managed (CE/EE) or an air-gapped/offline GitLab contour and needs an LLM-Wiki governance and delivery model on top of it.
- Groups/subgroups, CODEOWNERS, MR approval rules, protected branches/environments or GitLab CI/CD pipelines need to be designed or reviewed for LLM-Wiki content.
- Identity/RBAC (LDAP, SAML, SCIM), runner topology, audit/compliance evidence, or offline mirror strategy need mapping to GitLab primitives.
- The user asks how to move LLM-Wiki authorship and publishing off the GitLab Wiki feature onto a CI/CODEOWNERS/eval-gated workflow.
- Not for GitHub-hosted repositories (use the GitHub-specific operating-model skill instead) or for generic project-management advice unrelated to GitLab.
Starter templates
Use these local templates when available:
references/templates/gitlab-operating-model.yamlreferences/templates/gitlab-codeowners.llm-wikireferences/templates/gitlab-llm-wiki-ci.ymlreferences/templates/gitlab-merge-request-template.mdreferences/templates/gitlab-protected-branch-environment-policy.yamlreferences/templates/gitlab-raci-daci.yamlreferences/templates/gitlab-slo-scorecard.yaml
Copy only the templates that match the user's GitLab operating-model scope, then replace placeholder groups, approvers, environments and runner assumptions.
Inputs
- GitLab edition/tier if known: Free, Premium, Ultimate; CE/EE install context if relevant.
- GitLab deployment: single-node, HA, Geo, offline/air-gapped, Kubernetes, VM/bare metal.
- Organization model: team count, top-level group strategy, subgroups, tenants/domains.
- Desired LLM-Wiki surfaces: repo docs, internal portal, GitLab Pages, MCP/API, agent bundle, exports.
- Existing controls: LDAP, SAML, SCIM, CODEOWNERS, branch protection, approval rules, protected environments, runners, registries, audit events, SIEM.
- Risk profile: internal-only, sensitive, regulated, production-critical.
- Current pain: review bottleneck, runner sprawl, policy drift, stale knowledge, ungoverned agent writes, compliance evidence gaps.
What ships with it
60 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.
- references/docs/23-gitlab-self-hosted-operating-model.md 24 KB
- references/policies/redaction-retention-policy.md 3.7 KB
- references/policies/review-incident-response.md 3.1 KB
- references/templates/agent-export-bundle.yaml 2.1 KB
- references/templates/CODEOWNERS.llm-wiki 2.2 KB
- references/templates/eval-scorecard.yaml 3.2 KB
- references/templates/export-manifest.yaml 2.2 KB
- references/templates/export-profile.yaml 2.3 KB
- references/templates/gitlab-codeowners.llm-wiki 2.8 KB
- references/templates/gitlab-llm-wiki-ci.yml 3.1 KB
- references/templates/gitlab-merge-request-template.md 1.7 KB
- references/templates/gitlab-operating-model.yaml 4.1 KB
- references/templates/gitlab-protected-branch-environment-policy.yaml 3.1 KB
- references/templates/gitlab-raci-daci.yaml 2.8 KB
- references/templates/gitlab-slo-scorecard.yaml 3.1 KB
- references/templates/ingestion-fidelity-suite.yaml 3.3 KB
- references/templates/ingestion-pipeline-profile.yaml 3.2 KB
- references/templates/llm-wiki-evals.github-actions.yml 3.1 KB
- references/templates/llm-wiki-ingestion.github-actions.yml 2.6 KB
- references/templates/llm-wiki-publish.github-actions.yml 4.2 KB
- references/templates/llm-wiki-security.github-actions.yml 2.9 KB
- references/templates/mcp-security-profile.yaml 3.6 KB
- references/templates/mcp-wiki-profile.yaml 4.4 KB
- references/templates/openapi-wiki-core.yaml 11 KB
- references/templates/promptfoo-llm-wiki-redteam.yaml 3.8 KB
- references/templates/promptfoo-llm-wiki.yaml 3.4 KB
- references/templates/redaction-policy.yml 535 B
- references/templates/release-notes.md 304 B
- references/templates/reports/critique-audit-report.md 1.8 KB
- references/templates/reports/ecosystem-refresh.md 758 B
- references/templates/reports/monthly-eval.md 358 B
- references/templates/reports/source-refresh-report.md 898 B
- references/templates/reports/weekly-lint.md 205 B
- references/templates/retrieval-eval-set.yaml 1.9 KB
- references/templates/schemas/canonical-vocabularies.json 1.4 KB
- references/templates/schemas/domain-pack-profile.schema.json 1.1 KB
- references/templates/schemas/domain-pack.schema.json 1.6 KB
- references/templates/schemas/page.schema.json 2.6 KB
- references/templates/schemas/skill-router.schema.json 1.7 KB
- references/templates/schemas/taxonomy.md 1.6 KB
- references/templates/security-scorecard.yaml 4.0 KB
- references/templates/source-manifest.yaml 2.2 KB
- references/templates/static-site-export-profile.yaml 2.0 KB
- references/templates/team-onboarding-checklist.md 2.5 KB
- references/templates/team-operating-model.yaml 3.5 KB
- references/templates/team-raci-daci.yaml 2.8 KB
- references/templates/team-review-workflow.yaml 2.7 KB
- references/templates/team-slo-scorecard.yaml 2.6 KB
- references/templates/vault/AGENTS.md 1.4 KB
- references/templates/vault/CLAUDE.md 1.2 KB
- references/templates/wiki/claim-provenance-report.md 283 B
- references/templates/wiki/concept-page.md 596 B
- references/templates/wiki/entity-page.md 593 B
- references/templates/wiki/human-synthesis-atom.md 957 B
- references/templates/wiki/index.md 483 B
- references/templates/wiki/lint-report.md 436 B
- references/templates/wiki/log.md 400 B
- references/templates/wiki/query-page.md 340 B
- references/templates/wiki/source-page.md 665 B
- references/templates/wiki/technology-decision.md 798 B
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.
- 11d ago First seen · 307 lines · 73 tokens per session scan A 5ace9a1c16bd
llm-wiki-gitlab-operating-model is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 18d ago), licensed MIT. It adds 73 tokens to every session and 2,273 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 2026-08-31.
Other skills, from other repositories
okf-harness-bootstrap
This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.
okf-harness
One Door routes OKF Harness workspace requests to exactly one internal workflow at a time.
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
meta-sync-template
Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
wiki-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…