Keep your project’s context. Pick up where you left off.
Context Docs helps people who do not yet have a way to save and maintain project context. Give your AI coding agent a reusable workflow for recording decisions, current work and next steps in readable Markdown—with as little setup and manual organization as possible.
Get started · See an example · User guide · Evidence · Contribute
Status: experimental, core skill v0.1.6 and adoption skill v0.1.7. For Codex and Claude Code · Plain Markdown · MIT licensed
You should not have to invent a documentation system before you can preserve your work. Context Docs gives your agent instructions to:
- Save what matters: decisions and their reasons, current state, blockers and next steps.
- Keep it useful: update stale sections, consolidate repetition and distinguish facts from proposals.
- Fit your project: use existing documents and choose content for their audience.
- Help the next session start: make the context discoverable from the README or documentation index.
For example, after working on an export feature, your project context might contain:
## Current work
CSV export is implemented; empty-input behavior still needs testing.
## Decision (maintainer-approved)
Keep the existing export API to preserve compatibility.
## Next step
Test empty input before calling the feature complete.Illustrative content, not a required template. The agent should derive entries from your actual work and evidence. You review the changes; the next session reads the saved context. See a fuller before-and-after example.
Install both skills, then adopt them in the project you want to maintain. Already installed? Skip to Use it.
Ask Codex:
Use $skill-installer to install both skills from jaredchu/context-docs:
- skills/context-docs
- skills/adopt-context-docs
Install them together in ~/.agents/skills/.
Preserve existing installations and local customizations; report version
mismatches before upgrading.
Manual installation and project-only setup →
For a first installation, run these commands in a terminal:
git clone https://github.com/jaredchu/context-docs.git
cd context-docs
mkdir -p ~/.claude/skills
cp -r skills/context-docs skills/adopt-context-docs ~/.claude/skills/If either skill is already installed, review the upgrade guidance before copying files. Project-only setup and instruction loading →
Open your project in your coding agent and invoke:
| Codex | Claude Code |
|---|---|
$adopt-context-docs |
/adopt-context-docs |
The adoption skill applies the context workflow and adds or reuses a maintenance rule in the project instructions your agent loads. It preserves equivalent existing rules and the project’s documentation layout, and reports when it cannot confirm instruction loading.
After meaningful work, ask your agent:
Use context-docs to update this project's context from the work we just completed.
Review the resulting diff. You do not need to keep a session diary or log every interaction. To inspect documentation without changing it, ask:
Use context-docs to audit this project's context documents without editing files.
Start a new session with:
Read this project's context entry point and its relevant linked documents,
then continue with the next task.
Find the entry point in your README, documentation index, or the adoption marker’s
Entry point: field. Explicitly
ask the agent to read it: a saved file alone does not ensure that a new session
loads it. More usage examples and setup details →
| Skill | When to use it |
|---|---|
| adopt-context-docs | Set up the workflow and ongoing maintenance rule in a project. Requires the sibling core skill. |
| context-docs | Create, maintain or audit project context. Can also be used on its own. |
Ordinary maintenance requires no background service, cloud account or runtime dependency. The agent works when invoked; this is not automatic conversation capture or unlimited memory. Your project keeps ordinary, reviewable files.
Most users can start with Markdown context alone. An optional event journal can record significant history for later investigation. It is off by default unless you explicitly enable it or select the auto preference, which applies only outside Git when no project logging setting exists. Installing the skills does not enable it. The journal helper requires Python 3.9+.
Logging setup, upgrades and auto preference →
The goal is useful, accurate context with less effort for people who lack an established workflow. The project has packaging checks and recorded agent studies, including failures and reviewer disagreements. Those studies do not yet establish effort savings for the intended users or a skill-specific correctness advantage. Comparisons with competent ordinary maintenance are quality diagnostics, not a requirement to beat experts.
The skill guides an agent; it cannot guarantee factual correctness or complete preservation, and it cannot prevent concurrent editing conflicts. Review consequential claims and edits. It provides no automatic scheduler and grants no permission to publish documents or change other systems. Native integration remains experimental.
Results, methods and limitations →
- Installation and usage · Release notes · Changelog
- Context standard · Context template · Decision template
- Contributing · Case and review templates
- Evaluation scenarios · This project’s context
Created and maintained by Jared Chu. OpenAI Codex is the primary AI development contributor, covering implementation, documentation and evaluations; Claude also contributes. See the contribution and attribution policy.
Released under the MIT license.