agentmods.dev

review-context7-updates

A review command for comparing a package's documentation tool with newer changes in the official Context7 server. Context7 is a service that provides library and package documentation to coding tools.

In plain words
What is it for?
Use it to inspect the repository documentation and implementation, compare them with the Context7 server, and decide which new features or changes are worth reproducing.
Why use it?
It helps identify documentation features or improvements that the package's own tool may be missing, without starting the review without first understanding the relevant code.

Command for Claude Code

159 yesterday A scan 0 tokens original Apache-2.0
View the source file sammcj/mcp-devtools
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/sammcj/mcp-devtools/review-context7-updates
Clone the repo
git clone --depth 1 https://github.com/sammcj/mcp-devtools

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 911 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00911
Opus 5 $0.00000 $0.00456
Sonnet 5 $0.00000 $0.00182
Haiku 4.5 $0.00000 $0.00091

Measured yesterday against content hash 9a26643f38fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-context7-updates scanned grade A with 0 findings 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/review-context7-updates.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

My package documentation tool provides context7 functionality so you don't have to use the official context7 mcp server as well.

There were some updates to the official context7 mcp server since I last looked and it and I'd like to task you with determining if any new features or improvements were added to it that we should consider replicating in our package-documentation tool.

The official context7 server is located at: $HOME/git/mcp/context7 (you may need to do a git pull to get the latest changes) Your package documentation tool is located at: $HOME/git/sammcj/mcp-devtools/internal/tools/packagedocs/

Key Files to Review

Your Implementation:

  • $HOME/git/sammcj/mcp-devtools/internal/tools/packagedocs/client.go - API client and HTTP operations
  • $HOME/git/sammcj/mcp-devtools/internal/tools/packagedocs/resolve_library_id.go - Library ID resolution tool
  • $HOME/git/sammcj/mcp-devtools/internal/tools/packagedocs/get_library_documentation.go - Documentation fetching tool

Context7 Reference:

  • $HOME/git/mcp/context7/src/index.ts - Main MCP server implementation
  • $HOME/git/mcp/context7/src/lib/api.ts - API client and HTTP operations
  • $HOME/git/mcp/context7/src/lib/types.ts - Type definitions
  • $HOME/git/mcp/context7/src/lib/utils.ts - Utility functions
  • $HOME/git/mcp/context7/src/lib/encryption.ts - Security/encryption features (if exists)
  • Also check to see there's no other new files added since the last check that may be relevant

Please first review my package documentation tool to understand its capabilities, then review the changes in context7 to see if there are any gaps. If there are gaps or improvements we should look at please provide a summary and list of them here for me to consider, if we should implement them, and if so how we should do it ensuring we align with my projects existing code, patterns and configuration.

<EXAMPLE_SUMMARY note="Do not modify this section">

Changes since 479473a to 784ef42 (current) in context7:

  • Proxy Support, new proxy support was added to context7 allowing it to work in enterprise environments
  • Trust Score Prioritisation, context7 now allows prioritising sources based on trust scores using github stars and other metrics
  • Client IP Encryption, context7 added support for encrypting client IPs for privacy
  • HTTP Transport, context7 mcp server added support for HTTP transport in addition to STDIO
  • Auth Headers, context7 added support for more complex authentication headers for various auth schemes

Recommendation

Implement:

  1. ✅ Proxy Support - Aligns with your enterprise-focused architecture
  2. ✅ Trust Score Prioritisation - Simple text changes
  3. ✅ Source Header - One line addition

Skip:

  1. ❌ Client IP Encryption - Adds complexity without clear benefit for your use case
  2. ❌ HTTP Transport - Your tool focuses on STDIO MCP integration
  3. ❌ Complex Auth Headers - Your current auth handling is sufficient

Implementation Steps (if approved):

  • Add proxy configuration options to , ensuring we follow existing config patterns, e.g.
  • ....

</EXAMPLE_SUMMARY>

Read the full file on GitHub · 81 lines

Changes

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.

  1. yesterday First seen · 81 lines · 0 tokens per session scan A 9a26643f38fa

Subscribe to this mod's changes

review-context7-updates is a command published in the GitHub repository sammcj/mcp-devtools (159 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 911 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code reviewData and AILLMWriting and docsagenticaiclinecodingdevtools
Related

Other commands, from other repositories

compact-prep

Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.

sammcj/agentic-coding · 30 tokens

execute

Execute queued goal chunks with capacity-aware workers.

simonrowland/goal-flight · 9 tokens

init

Initialize goal-flight state for a project.

simonrowland/goal-flight · 8 tokens

update

Refresh goal-flight itself + the worker CLIs it dispatches to. Two sweeps in one command: pull latest goal-flight from origin, then run each CLI's built-in update mechanism. Reports a diff table for both. Sweep 2 swaps worker binaries; its idle gate below protects those binary swaps specifically. Sweep 1 plugin pulls…

simonrowland/goal-flight · 0 tokens

controller-behavior-test

Run scripted orchestrator behavior scenarios (Codex-first bash-tail harness).

simonrowland/goal-flight · 14 tokens

doctor

Run procedural readiness checks for goal-flight.

simonrowland/goal-flight · 8 tokens