Not in the top 1,000 by GitHub stars

djolex999/vir

Karpathy's LLM Wiki, built from your Claude Code sessions: a folder of markdown you own, Obsidian-native when you want it. Keeps what you decided, learns rules from what you repeat, readable by any agent.

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/vir/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

e6eb26307ad2 → e6eb26307ad2

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → e6eb26307ad2

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit e6eb26307ad229ab2d8638663eff40530c42f13c

20GitHub stars
0stars in 7 days
1skill in this repository
37commits in 30 days

Heat

1.7
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 202620

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

vir

When your agent uses it

Consult the user's vir knowledge base: notes distilled from their own past coding-agent sessions (decisions, gotchas, patterns, tools). Use before starting non-trivial work in a project, when the user asks 'what did I decide about X', 'have I hit this before', 'check my notes/vault', when debugging an error that may have happened before, and before architectural or library choices.

What it loads into context

Frontmatter

88 tokens

Always available to the agent

SKILL.md

1,297 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 1. Pick the access path (first one that works)
  2. 2. Ask good questions
  3. 3. Read the results
  4. 4. Use what you found
  5. 5. Hard limits

Files

  • SKILL.mdcore4,803 bytes
  • SKILL.mdcore4,803 bytes
  • SKILL.mdcore4,803 bytes
  • SKILL.mdcore4,803 bytes
Read SKILL.md

# vir: the user's own past decisions

vir distills the user's past coding-agent sessions into short markdown notes:
**decisions** (what they chose and why), **gotchas** (what broke and the fix),
**patterns**, and **tools**. The notes are the user's own history, not general
advice. Checking them first avoids re-solving a problem they already solved
or re-opening a decision they already made.

This skill only **reads** the notes. It never writes them.

## 1. Pick the access path (first one that works)

1. **MCP tools.** If `vir_query` is among your tools, use it, and **pass
   `synthesize: false`**. By default it synthesizes an answer with an LLM call
View the complete source on GitHub

Skills included

  • vir

Repository facts

License
MIT
Created
May 19, 2026
Last pushed
Nov 5, 2026
Forks
4
Open issues
2
Project activity
Active

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 3 notes
  • skills/vir/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/vir/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/vir/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • No broad tool permissions
  • No dangerous shell commands
  • No network access
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

No combined signals at this commit.

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skills/vir/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/vir/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/vir/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/vir/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/vir/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/vir/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.