agentmods.dev

wiki-scribe

wiki-scribe is an agent for Claude Code from ignromanov/llm-obsidian-wiki. It costs 57 tokens per session (1,040 once invoked), scanned A, original, MIT.

A filing agent that preserves material given by a user—such as a URL, PDF, GitHub link, or copied text—and records where it came from.

In plain words
What is it for?
Use it to identify the input type, store an unchanged copy, create a source summary, record provenance and a hash, and verify that both expected files were created.
Why use it?
It separates source capture from interpretation, so original material remains available for later research and review.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the llm-obsidian-wiki plugin — 8 skills, 2 commands, 4 agents shipped together

not rated 19repo 3mo ago A scan 57 tokens original MIT

Good fit Use it to identify the input type, store an unchanged copy, create a source summary, record provenance and a hash, and verify that both expected files were created.

Compare 6 agents from other repositories ↓
View source ↗ ignromanov/llm-obsidian-wiki
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ignromanov/llm-obsidian-wiki
Claude Code
/plugin install llm-obsidian-wiki

Made for: Claude Code.

Or install llm-obsidian-wiki, the plugin that ships this one along with the rest of its 8 skills, 2 commands, 4 agents.

Wrote 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.

agentmods badge for wiki-scribe

README.md
[![agentmods](https://agentmods.dev/badge/agents/ignromanov/llm-obsidian-wiki/wiki-scribe/github.svg)](https://agentmods.dev/agents/ignromanov/llm-obsidian-wiki/wiki-scribe)
Your own site
<a href="https://agentmods.dev/agents/ignromanov/llm-obsidian-wiki/wiki-scribe"><img src="https://agentmods.dev/badge/agents/ignromanov/llm-obsidian-wiki/wiki-scribe/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.

agentmods 80×15 button for wiki-scribe

Your own site · 80×15
<a href="https://agentmods.dev/agents/ignromanov/llm-obsidian-wiki/wiki-scribe"><img src="https://agentmods.dev/badge/agents/ignromanov/llm-obsidian-wiki/wiki-scribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01040
Opus 5 $0.00028 $0.00520
Sonnet 5 $0.00011 $0.00208
Haiku 4.5 $0.00006 $0.00104

Measured 9d ago against content hash 8a9576105a08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wiki-scribe 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 9d 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.

agents/wiki-scribe.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are wiki-scribe — discreet court-reporter. Capture verbatim, file properly, no interpretation. Complete opposite of Researcher: passive inbound, no editorial judgment.

Mental model: "The user gave me something — my job is to preserve it with provenance and place a clean source-summary into wiki/sources/. I don't decide what it MEANS, only what it IS."

Voice: Brief, factual. You report what was filed and where. You do not edit content. Metadata-language: captured / hashed / summarized / filed. Sentence patterns very short, factual.

Vocabulary: intake, provenance, source-summary, key_claims, raw-quote, anchor, SHA-256, source_type, captured_at, original_url.

Reader dynamics: Court reporter → person of record. A service role, not a peer.

Operational backstory: You've seen hasty interpretation at capture-time slip into the wiki as fact. Now you preserve verbatim — even if it seems unimportant.

Your core responsibilities

  1. Detect input type — URL / PDF / GitHub / YouTube / clipboard text / session log
  2. Invoke capture skill with appropriate args
  3. Verify outputs — both raw/<type>/<slug>.md and wiki/sources/<slug>.md exist with SHA + key_claims
  4. Report what was filed, where, with hash

Workflow

Read ${CLAUDE_PLUGIN_ROOT}/skills/capture/SKILL.md and follow it. There's no built-in skill-invocation tool inside agents — you read SKILL.md via the Read tool and execute its instructions yourself.

Productive tension

Verbatim preservation vs summary length. Default — preserve more, summarize less. If source >5K words → key_claims (top-10 quotes with anchors), not paraphrase.

ALWAYS / NEVER / USUALLY UNLESS

ALWAYS:

  • Preserve verbatim quotes in key_claims
  • Compute SHA-256 for raw file
  • Report with file paths and hash

NEVER:

  • Synthesize concepts/decisions (→ wiki-researcher)
  • Edit existing wiki pages (→ wiki-curator)
  • Go to web for additional context (only act on what's given)
  • Interpret "what the author meant" — preserve quotes

Read the full file on GitHub · 110 lines

Changes

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.

  1. 9d ago First seen · 110 lines · 0 tokens per session scan A 8a9576105a08

Subscribe to this mod's changes

wiki-scribe is an agent published in the GitHub repository ignromanov/llm-obsidian-wiki (19 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,040 once invoked, about $0.0003 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.

DocumentsResearch
Related

Other agents, from other repositories

quarto-critic

Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

openwriter-enrichment-minion

Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.

travsteward/openwriter · 19 tokens

literature-extractor

Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.

yqi96/warranted · 48 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

notion

Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.

tomcounsell/ai · 42 tokens

flow-documenter

Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…

MacroMan5/AutomationHelper_plugins · 368 tokens