Borrowing it
Nothing to install: this file belongs to vishnu2kmohan/mcp-server-langgraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vishnu2kmohan/mcp-server-langgraph/main/.claude/commands/refresh-context.mdgit clone --depth 1 https://github.com/vishnu2kmohan/mcp-server-langgraphWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/refresh-context)<a href="https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/refresh-context"><img src="https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/refresh-context/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/refresh-context"><img src="https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/refresh-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.01393 |
| Opus 5.5 | $0.00004 | $0.00557 |
| Sonnet 5.5 | $0.00002 | $0.00279 |
| Haiku 4.5 | $0.00001 | $0.00139 |
Grade B, and why
refresh-context scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
head -10 .claude/context/recent-work.md How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Context Files
Usage: /refresh-context or /refresh-context --full
Purpose: Manually refresh Claude Code context files from current repository state
📋 What This Command Does
Refreshes context files in .claude/context/ by analyzing current repository state:
- recent-work.md: Updates from git commit history (last 15 commits)
- Repository stats: Current file counts, test counts, branch info
- Recent file activity: Files changed in last 7 days
- Commit categorization: Automatic categorization by type
🚀 Execution
Step 1: Run Update Script
# Quick refresh (recent-work.md only - FAST)
python scripts/workflow/update-context-files.py --recent-work
# View what changed
git diff .claude/context/recent-work.md
Step 2: Verify Update
Check that recent-work.md was updated:
# Check last updated timestamp
head -10 .claude/context/recent-work.md
# View recent commits section
grep -A 20 "Recent Commits" .claude/context/recent-work.md
Step 3: Report Status
Provide user with summary:
- ✅ Context Refreshed
Updated:
- recent-work.md: Last 15 commits, 7 days of file activity
- Repository stats: X commits, Y files, Z tests
- Hot spots identified: [top directories]
Last commit: [hash] - [message]
Branch: [current branch]
Context is now up-to-date with repository state.
🔧 Options
Quick Refresh (Default)
Updates only recent-work.md (fast, ~2-5 seconds):
python scripts/workflow/update-context-files.py --recent-work
Full Refresh (Slower)
Note: testing-patterns.md and code-patterns.md updates are not yet automated (too complex). Only recent-work.md is auto-updated currently.
Future expansion will include:
- Testing patterns extraction
- Code patterns analysis
- ADR indexing
📊 What Gets Updated
recent-work.md
Repository Overview:
- Total commits
- Contributors count
- Current branch
- Source/test file counts
- Total test count
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 279 lines · 11 tokens per session scan B 4a05754f3ff2
refresh-context is a command published in the GitHub repository vishnu2kmohan/mcp-server-langgraph (4 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 1,393 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
catchup
A command that rebuilds an agent's working context from project notes and recent Git activity.
tree
Show the Tau Git Memory tree as a visual schema.
sync
Sync memory between your local machine and GitHub backup — both directions.
status
Run Tau Git Memory status now.
sync-from-github
Sync one vault or the whole fleet straight from the GitHub skeleton (plugins, themes, snippets, root docs) — no dev repo or local .template needed. Same guards as --sync-plugins (credential-leak refusal, BRAT anti-downgrade) plus hardened archive extraction. (Skill sync-from-github carries the full procedure.).
full-check
Run a thorough scan of the entire memory ecosystem. Recommended weekly or after major changes.