julia-evaluation

A set of rules for running and testing Julia code in a persistent Julia REPL, which is an interactive coding session. It also explains when to reload changed code and when a full reset is needed.

In plain words
What is it for?
Use it when evaluating or testing Julia code, managing hot-reloaded .jl files, displaying results, and deciding between reloading code and restarting the worker.
Why use it?
It keeps interactive Julia work consistent and helps avoid unnecessary session resets. It distinguishes ordinary function changes from changes that require rebuilding the session.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/samtalki/agentrepl.jl/julia
Any agent
npx skills add samtalki/AgentREPL.jl --skill julia
Clone the repo
git clone --depth 1 https://github.com/samtalki/AgentREPL.jl

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.00555
Opus 5 $0.00021 $0.00278
Sonnet 5 $0.00008 $0.00111
Haiku 4.5 $0.00004 $0.00056

Measured 2d ago against content hash 2182e6c8718f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

julia-evaluation 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 2d 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-plugin/skills/julia/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Julia REPL — Behavioral Rules

Use the MCP tools (eval, reset, pkg, activate, session, revise, log_viewer, info) for interactive Julia work. Prefer julia script.jl via bash for one-shot scripts.

Before Every Eval

Always display code in a readable julia code block BEFORE calling eval. The MCP permission prompt shows code as an escaped string which is unreadable.

After Eval

MCP tool results are collapsed in Claude Code. For visual output (plots, heatmaps), tell the user to expand the tool result (Ctrl+O) to see it with full color — do NOT paste ANSI art into your message (it loses colors and streams token-by-token). For structured text (tables, matrices, DataFrames), paste in a fenced code block. Do not paste simple scalars or errors.

Revise vs Reset

Prefer revise — it preserves session state. Only reset when required.

Change Action
Function/method body or signature revise(action="revise")
Struct layout (Julia < 1.12) reset required
Corrupted state / stuck code reset required

After editing .jl files, call revise(action="revise") to hot-reload (a PostToolUse hook reminds you after .jl edits).

Error Recovery

Error Fix
UndefVarError Re-run definition or check spelling
MethodError Check argument types
LoadError pkg(action="add", packages="...")
cannot redefine reset (struct layout change)
Hung/infinite eval(code=..., timeout=5) or reset

First Use

On first Julia use in a conversation, ask which environment to activate (current directory, specific path, or global).

Capabilities

  • Sessions persist variables, functions, and packages across evals
  • Multiple named sessions provide isolated workers
  • timeout parameter kills hung code and respawns the worker
  • max_output prevents context overflow from large results
  • isolated=true evals in a fresh module without polluting Main
  • ephemeral=true evals in a disposable temporary session

Read the full file on GitHub · 53 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. 2d ago First seen · 53 lines · 42 tokens per session scan A 2182e6c8718f

Subscribe to this mod's changes

julia-evaluation is a skill published in the GitHub repository samtalki/AgentREPL.jl (6 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 555 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 2026-08-31.