Borrowing it
Nothing to install: this file belongs to alfadur7/llm-wiki-newsroom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alfadur7/llm-wiki-newsroom/main/.claude/commands/wiki-export.mdgit clone --depth 1 https://github.com/alfadur7/llm-wiki-newsroomWrote 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/commands/alfadur7/llm-wiki-newsroom/wiki-export)<a href="https://agentmods.dev/commands/alfadur7/llm-wiki-newsroom/wiki-export"><img src="https://agentmods.dev/badge/commands/alfadur7/llm-wiki-newsroom/wiki-export/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/commands/alfadur7/llm-wiki-newsroom/wiki-export"><img src="https://agentmods.dev/badge/commands/alfadur7/llm-wiki-newsroom/wiki-export.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 | $0.00000 | $0.01327 |
| Opus 5 | $0.00000 | $0.00664 |
| Sonnet 5 | $0.00000 | $0.00265 |
| Haiku 4.5 | $0.00000 | $0.00133 |
Grade A, and why
wiki-export 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Export wiki to merged files for Claude.ai Project Knowledge.
Usage: /wiki-export
Traversal Pattern
Outside the matrix — Meta layer (deterministic). The Editor-in-Chief calls tools/export.py.
| Cycle | Owner |
|---|---|
| Trigger | Editor-in-Chief |
| Export | tools/export.py (deterministic) |
| Commit·Push | Editor-in-Chief → explicit approval from the wiki operator (memory git-approval) |
Output (wiki-export/ Folder)
Root meta copies (1:1 copy)
overview.md·contradiction.md·index.md
Sub-folder merges (# All FOLDER (N) header + --- separator) — synthesis layer only
all-overviews.md·all-contradictions.md·all-timelines.md·all-syntheses.md·all-trails.mdall-entities.mdandall-concepts.mdare NOT generated (hub bodies = the graph layer). On a full-scale corpus those two files alone (≈1.24M tokens, as measured on the original large corpus) would overwhelm the Claude.ai project context (~200K, fully loaded, not searched) → the chief culprit of context-overflow errors. The full text lives in thegraph/_pages.jsonnodes (#q=), and the directory is held byindex.md(one line + deep link per entity·concept). (python tools/export.pyprints the live RAG-budget estimate for the current corpus.)
Sources — a one-line index instead of full bodies
all-sources-index.md(single file) — one line per source (`slug` — title (date)), grouped bygraph/_clusters.jsonprimary cluster. No summary snippet (slim — the snippet was most of this index's ~118K tokens, the headline is enough, and the full text is one graph deep link away).
Claude.ai project instruction document (README.md)
README.md— the complete custom-instruction document: 2-tier structure explanation + file-structure table (derived from ROOT_META + FOLDER_MERGES + index, drift-impossible) + upload budget guide (Core/Optional are auto-filled greedily up to_CONTEXT_LIMITin_TIER_PRIORITYorder and split — as the corpus grows, large synthesis files are auto-demoted to Optional; fixed numbers, drift-impossible) + answer rules + deep-link convention + wiki-structure reference. Paste this entire document into the Claude.ai project instruction field. The per-file handoff block is discarded (the instruction field is the single channel — removing the 11× ~9K-token duplication).
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 · 56 lines · 0 tokens per session scan A e4d9252f7422
wiki-export is a command published in the GitHub repository alfadur7/llm-wiki-newsroom (85 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,327 tokens. 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 commands, from other repositories
output
Generate output artifacts from active wiki content — summaries, reports, study guides, slide outlines, timelines, glossaries, comparisons. Outputs are filed back into the wiki.
show
Display a past OCR review session.
choose-model
Compare current models across configured AI providers and produce an executable plan without running paid work. Use when the user asks which model or provider should perform a task.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.