update-context
/update-context
Update the current directory's .agentcontext file with what happened in this conversation (work completed, work still to do) and prune anything that's gone stale. Works in any project. Use when the user says "update context", "save this to context", "update the agent context".
- Author
- ducky8x ↗
- Repository
- session-kit ↗
- Licence
- MIT
- Last repository change
- 06.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 06.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Update the current directory's .agentcontext file with what happened in this conversation (work completed, work still to do) and prune anything that's gone stale. Works in any project. Use when the user says "update context", "save this to context", "update the agent context".
Triggers from the description
Original author description
Update the current directory's .agentcontext file with what happened in this conversation (work completed, work still to do) and prune anything that's gone stale. Works in any project. Use when the user says "update context", "save this to context", "update the agent context".
How it works
- Steps
SKILL.md preview
--- name: update-context description: Update the current directory's .agentcontext file with what happened in this conversation (work completed, work still to do) and prune anything that's gone stale. Works in any project. Use when the user says "update context", "save this to context", "update the agent context". --- Keep the current project's `.agentcontext` file accurate so a future session can pick up where this one left off without being briefed again. ## Steps 1. Look for a `.agentcontext` file in the current working directory. - If there isn't one, tell the user there's nothing to update and suggest running the `create-context` skill (`/session-kit:create-context`) first. Don't create one here. 2. Read it in full. 3. Scan this conversation for: - **Work completed**: what got done, fixed, shipped, or decided this session. - **Work still to do**: the next steps, in enough detail that a new session could continue without asking what's next. - **New conventions or gotchas**: standing rules found this session that would trip up a future session the same way twice. - **Stale content**: anything already in the file that this conversation resolved, replaced, or made irrelevant. 4. Edit the file: - Update the status section to reflect the current state: replace stale facts and finished work instead of appending to a growing log. - Delete anything superseded or no longer relevant. The file should stay lean, not collect history. - Add new conventions only if they're repeatable rules, not one-off facts. - Keep the existing terse, one-line-per-fact style. 5. Never touch the README or other docs. This skill only maintains `.agentcontext`. 6. Show the user a short diff-style summary of what changed (added, removed, updated), not just "done." If nothing in the conversation is worth keeping, say so instead of editing.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · ducky8x/session-kit | 86 | MIT |
| Mosin112/pm-harness | 100 | MIT |
Database snapshot: 13.11.2026 · package version 70085418440d (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 86create-context
Create the .agentcontext file (a hidden per-project brief that load-context reads and update-context maintains) for the project in the current working directory. Use when the user says "make agent context", "create agent context file", "set up context for this project", or when… - 96load-context
Load the standing project context for the current working directory so you can start work right away without being re-briefed. Reads every .agentcontext file (a hidden per-project brief) found in the current directory and its ancestors, plus whatever README each one points to.… - 100agents-md-generator
Generate or update an AGENTS.md / CLAUDE.md / context file for a repo. Use when the user says "set up CLAUDE.md", "generate AGENTS.md", "write a context file for this repo", "document this codebase for AI agents", or when a fresh repo has none. Also use when an existing context… - 90refresh-context
Review and refresh an existing personal-context.md or company-context.md — check what has gone stale, fill gaps against the current template, and update the file. Use when the user says "refresh my context", "review my context", "is my context still up to date", "my context is… - 90clean-claude-memory
Audit, prune, rewrite, or relocate Claude Code project memory. Use when the user asks to review, clean, update, or remove Claude memory files, eliminate stale project memories, or rebuild MEMORY.md. - 90gds-generate-project-context
Create optimized project-context.md for AI agent consistency. Use when the user says "project context" or "generate context