Menu
Build LLM-ready code dumps with optional docs, then count tokens with tokencount (o200k-base) against a context budget (for example 272k for GPT-5).
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | context-packer |
| description | Build LLM-ready code dumps with optional docs, then count tokens with tokencount (o200k-base) against a context budget (for example 272k for GPT-5). |
Use this skill when the user wants to:
prepare-context.sh:
path + ``` + contents) for all selected files<project>/prompt/<output>.txt (or /tmp/context-packer/... with --tmp-output)tokencount --encoding o200k-base$HOME/dev/pi-skills/context-packer/prepare-context.sh <project_dir> [options]
# Default budget (272000), code + docs + tests pack
$HOME/dev/pi-skills/context-packer/prepare-context.sh ~/dev/pui
# Code-focused pack (exclude docs and tests)
$HOME/dev/pi-skills/context-packer/prepare-context.sh ~/dev/pui --no-docs --no-tests
# Include env/sensitive files explicitly (off by default for safety)
$HOME/dev/pi-skills/context-packer/prepare-context.sh ~/dev/pui --include-env --include-secrets
# Custom budget and output name
$HOME/dev/pi-skills/context-packer/prepare-context.sh ~/dev/pui \
--budget 272000 \
--output pui-gpt5.txt
# Fail with exit code 2 if over budget
$HOME/dev/pi-skills/context-packer/prepare-context.sh ~/dev/pui --fail-over-budget
--output <name> output filename (default: context-dump.txt)--tmp-output write output to /tmp/context-packer/... instead of <project>/prompt/--budget <tokens> token budget (default: 272000)--with-docs include docs/ (default: on)--with-tests include test files (__tests__, tests/, test/, *.test.*, *.spec.*, etc.) (default: on)--no-docs exclude docs/--no-tests exclude test files (__tests__, tests/, test/, *.test.*, *.spec.*, etc.)--include-lockfiles include lockfiles (pnpm-lock.yaml, Cargo.lock, etc.)--include-env include env files (.env, .env.*, .envrc) (default: off)--include-secrets include potentially sensitive files (.npmrc, .netrc, keys/certs, cloud credential files, etc.) (default: off)--no-clipboard do not refresh clipboard from output file--fail-over-budget return non-zero if budget exceeded--install-tools install missing tokencount via cargotokencount installed (cargo install tokencount)copy_files (not required)pbcopywl-copyIf no clipboard tool is available, the script still writes output files; it just skips clipboard copy.
Analyze pi session transcripts to discover patterns that could become AGENTS.md rules, skills, or prompt templates. Mines your usage history for automation opportunities.
Build PR-focused context packs (PR description + git diff + full changed files + related files via Scribe), then budget-fit and token-check with o200k-base.
Review a pull request for bugs, style issues, and guideline compliance. Local review - does not post to GitHub.
Compress images to a target file size using macOS sips. No dependencies required.
Multi-model code review. Runs code-review skill with 3 models in parallel, then synthesizes findings.
Compress videos to a target file size using ffmpeg two-pass encoding. Useful for Discord/Slack upload limits.