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-company-flow-auditgit 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-company-flow-audit)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-company-flow-audit"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-company-flow-audit/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-company-flow-audit"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-company-flow-audit.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 | $0.00072 | $0.01553 |
| Opus 5 | $0.00036 | $0.00776 |
| Sonnet 5 | $0.00014 | $0.00311 |
| Haiku 4.5 | $0.00007 | $0.00155 |
Grade A, and why
llm-wiki-company-flow-audit 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 12d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki Company Flow Audit
Goal
Help users plan company/team-level LLM-Wiki ingestion and operations from real information flows, without pretending that all knowledge can be safely or usefully automated.
When to use
Use when the user asks:
- where team/company information currently lives;
- how to collect from Confluence, Jira, GitHub, Slack, Teams, Drive, meetings, support, analytics or email;
- what can be fully automated and what cannot;
- how to keep external docs updated when they change;
- how fragile vault-review/lint systems are;
- how much time link/contradiction repair takes;
- whether there is a good UI for review queues;
- whether confidential information and access control are supported;
- what pitfalls to avoid;
- whether the maintenance cost is worth the value.
Inputs
- The list of systems currently holding team/company knowledge (e.g. Confluence, Jira, GitHub, Slack, Teams, Drive, PagerDuty).
- Team/org scale (personal pilot, one team, cross-functional, or company-level) so the maintenance-planning range fits.
- Whether a source registry or ingestion tooling already exists, and its refresh policy (webhook, poll, manual, snapshot).
- Any confidentiality/access constraints: data classification tiers, who owns which sources, existing permission boundaries.
- Prior review-queue or UI setup (PR-based review, Obsidian vault, dashboard) if one is already in place.
Required references
Read these when available:
references/docs/company-information-flows.mdreferences/docs/adoption-objections.mdreferences/docs/adoption-q-and-a.mdreferences/docs/19-security-threat-model.md
For vendor claims about Confluence, Jira, Slack, Teams, Google Drive, SharePoint or GitHub, browse and cite current official docs.
Core stance
Use this answer:
Start from the information flows that already influence decisions. Automate capture, metadata, version/hash tracking, stale marking and review reports. Do not fully automate truth promotion, contradiction resolution, sensitive summaries or official documentation updates.
What ships with it
4 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.
- 12d ago First seen · 197 lines · 72 tokens per session scan A 62716abf8bab
llm-wiki-company-flow-audit is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 19d ago), licensed MIT. It adds 72 tokens to every session and 1,553 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
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…
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…
wiki-query
Answer a question using ONLY the existing wiki vault as the knowledge base — no web search, no general LLM knowledge. Reads hot.md first (cheap recent context), then catalog.md to navigate, then drills into specific pages, then optionally semantic-searches the wiki, and synthesizes an answer with citations. Use when…
wiki-fold
Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window…
wiki
Bootstrap or check a Karpathy-style "LLM wiki" structure inside an Obsidian vault — a self-maintaining knowledge base where pages reference each other and the LLM keeps it tidy. Sets up catalog.md (curated page catalog), journal.md (append-only operation history), hot.md (recent-context cache), and overview.md…