OpenParable
Skip to content
← Back to skills

Context Status

Productivity
context-status

Context Status is an Agent Skill for productivity published in the brycewang-stanford/Auto-Empirical-Research-Skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Show current session status and context health for the sewage project. Use to check context usage, active work state, and what will survive compaction.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/HEAD/skills/41-sticerd-eee-sewage-econometrics-check/skills/context-status/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/context-status, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Context Status

Show current session status including context usage estimate and project state.

Workflow

Step 1: Check Session State

# Recent git activity
git log --oneline -5

# Working tree status
git status --short

# Recent output files
ls -lt output/log/ 2>/dev/null | head -5

Step 2: Check Project Progress

# Count analysis scripts
find scripts/R/09_analysis/ -name "*.R" | wc -l

# Count output tables and figures
ls output/tables/*.tex 2>/dev/null | wc -l
ls output/figures/ 2>/dev/null | wc -l

# Check manuscript sections
ls docs/overleaf/*.tex 2>/dev/null

Step 3: Report Status

Format output:

Session Status
---
Recent commits: [last 3]
Uncommitted changes: [count]
Recent reports: [last 3 in output/log/]

Project Progress
---
Pipeline scripts: N
Analysis scripts: N
Output tables: N
Output figures: N
Manuscript sections: N .tex files

Memory Files
---
[List files in .claude/projects/.../memory/]

Notes

  • Context usage is estimated from conversation length
  • All important state is saved to disk (memory files, output/log/)
  • Use /commit to save work before context compaction