IJFW Compute

IJFW Compute is an AI Engineering skill for Claude Code, published by FerroxLabs in ijfw.

210 stars40 forkson FerroxLabs/ijfwAdded 2026/09/04Repository updated 2026/08/31

ai-agentsai-codingclaude-codecodexcursordeveloper-toolsgemini-cligithub-copilotmcpmcp-servermemorynodejstypescriptwindsurf

Install in seconds

Install IJFW Compute

Copy IJFW Compute into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/FerroxLabs/ijfw/tree/main/claude/skills/ijfw-compute ~/.claude/skills/ijfw-compute

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/FerroxLabs/ijfw.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: claude/skills/ijfw-compute/SKILL.md in FerroxLabs/ijfw
Installs to: ~/.claude/skills/ijfw-compute
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2970 skills

What IJFW Compute does

IJFW Compute runs sandboxed scripts for large or repetitive data tasks like log analysis, aggregation, deduping, and counting. It also supports indexing and searching findings so recurring questions can reuse prior results.

IJFW Compute is cataloged under AI Engineering on DirSkills. IJFW Compute comes from a repository tagged ai-agents, ai-coding, claude-code, codex and cursor.

Documentation

README

Excerpt

Compute over read. When data is large or repetitive, run a sandboxed script and surface only the result. The four trees below decide which lever to pull.

Compute tree -- run a sandboxed script

Use when the input is bigger than the answer: log files, CSV/JSON dumps, file-tree walks, repeated string transforms, aggregate stats, deduping. Call ijfw_run compute:python "<script>" for pandas / numpy / stdlib parsing. Call ijfw_run compute:js "<script>" for JSON shape-checks, regex sweeps, quick numeric work. Sandbox is allowlist filesystem (cwd + project root) + best-effort OS-level network deny; opt-in with IJFW_COMPUTE_NET=1 if the script needs egress. Default timeout 30s, hard cap 300s via IJFW_COMPUTE_TIMEOUT_MS. Output cap 100MB; overflow lands in the on-disk log.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about IJFW Compute

What else does FerroxLabs publish alongside IJFW Compute?
IJFW Compute is one of 25 skills that DirSkills catalogs from FerroxLabs/ijfw, the repository it ships in. Its siblings there include Auto Memorize, Critique and IJFW AGENTS.md Manager. Each one is a separate skill with its own page in this directory, installs the same way IJFW Compute does, and is maintained by FerroxLabs in that same repository. The rest of the collection is listed on the FerroxLabs/ijfw page.
How does IJFW Compute compare to other AI Engineering skills?
IJFW Compute ranks #2689 by stars among the 2970 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of IJFW Compute against them. Open each page to compare what they document and how they install.