claude-historian-mcp: Skill for Claude Code

.claude/skills/claude-historian/SKILL.md

claude-historian is a skill for Claude Code from Vvkmnn/claude-historian-mcp. It costs 43 tokens per session (633 once invoked), scanned A, original, MIT.

A conversation-history search skill for finding earlier answers, fixes, decisions, tool workflows, sessions, and file changes.

In plain words
What is it for?
Use it before web searches, while debugging errors, or when returning to a familiar project or file.
Why use it?
It reduces repeated investigation by checking whether the same problem or project context was handled before.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Vvkmnn/claude-historian-mcp's own configuration. It tells Claude Code how to work on claude-historian-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-historian-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Vvkmnn/claude-historian-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Vvkmnn/claude-historian-mcp/master/.claude/skills/claude-historian/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Vvkmnn/claude-historian-mcp

Made for: Claude Code.

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 claude-historian

README.md
[![agentmods](https://agentmods.dev/badge/skills/vvkmnn/claude-historian-mcp/claude-historian/github.svg)](https://agentmods.dev/skills/vvkmnn/claude-historian-mcp/claude-historian)
Your own site
<a href="https://agentmods.dev/skills/vvkmnn/claude-historian-mcp/claude-historian"><img src="https://agentmods.dev/badge/skills/vvkmnn/claude-historian-mcp/claude-historian/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 claude-historian

Your own site · 80×15
<a href="https://agentmods.dev/skills/vvkmnn/claude-historian-mcp/claude-historian"><img src="https://agentmods.dev/badge/skills/vvkmnn/claude-historian-mcp/claude-historian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 633 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 $0.00043 $0.00633
Opus 5 $0.00022 $0.00316
Sonnet 5 $0.00009 $0.00127
Haiku 4.5 $0.00004 $0.00063

Measured 12d ago against content hash d62c3d7d74c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-historian 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.

.claude/skills/claude-historian/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Historian

Search conversation history before starting fresh. You may already have the answer.

When to Use

Before WebSearchsearch(query: "...", scope: "similar") or search(query: "...", scope: "conversations"). Past solutions beat web results.

Stuck on an errorsearch(query: "<error message>", scope: "errors"). Finds past fixes with code.

Entering a familiar projectsearch(scope: "sessions") for recent work. search(query: "...", scope: "plans") for past decisions.

Working on a familiar filesearch(scope: "files", filepath: "src/index.ts"). Shows past changes with context.

Quick Reference

Situation Tool Call
Error with no obvious cause search(query: "<error>", scope: "errors")
"Have I done this before?" search(query: "...", scope: "similar")
Working on familiar file search(scope: "files", filepath: "...")
Need past design reasoning search(query: "...", scope: "plans")
What did I do last session? search(scope: "sessions")
Successful tool workflows search(scope: "tools")
General search search(query: "...", scope: "conversations")
Deep-dive into session inspect(session_id: "...")
Rules, skills, CLAUDE.md search(query: "...", scope: "config")
Task management history search(query: "...", scope: "tasks")
Memories across sessions search(query: "...", scope: "memories")

Key Parameters

  • scope: Target your search — conversations, errors, files, plans, config, tasks, similar, sessions, tools, memories, or all (default)
  • limit: Number of results (default 10)
  • project: Filter by project name substring (works with conversations, sessions)
  • timeframe: today, yesterday, week, month

Common Mistakes

Mistake Fix
Going straight to WebSearch Check historian first — past solutions are more relevant
Vague queries Use specific terms: error messages, file paths, tool names
Using scope: "all" for errors Use scope: "errors" — it has dedicated fix extraction
Long keyword-dump queries Keep to 3-5 specific terms, not 10+ generic ones

Read the full file on GitHub · 51 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. 12d ago First seen · 51 lines · 43 tokens per session scan A d62c3d7d74c2

Subscribe to this mod's changes

claude-historian is a skill published in the GitHub repository Vvkmnn/claude-historian-mcp (178 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 633 once invoked, about $0.0002 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.