What is claude-context-manager CLAUDE.md?

Repository instructions for claude-context-manager, a Claude Code plugin that records tool interactions in a searchable SQLite database and exports important notes to Claude Code memory files.

Developing the plugin, following its branch strategy, and understanding its tests, hooks, and session-history features.

They explain the project's development process, including which branch to use and how checks protect stable releases.

How mrlesmithjr/claude-context-manager configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mrlesmithjr/claude-context-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mrlesmithjr/claude-context-manager/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mrlesmithjr/claude-context-manager

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mrlesmithjr/claude-context-manager/claude-md/github.svg)](https://agentmods.dev/instructions/mrlesmithjr/claude-context-manager/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mrlesmithjr/claude-context-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/mrlesmithjr/claude-context-manager/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mrlesmithjr/claude-context-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/mrlesmithjr/claude-context-manager/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,210 This file is loaded in full into every session.

When invoked 7,210 The same file — it is already loaded in full.

Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.07210	$0.07210
Opus 5	$0.03605	$0.03605
Sonnet 5	$0.01442	$0.01442
Haiku 4.5	$0.00721	$0.00721

Measured 8d ago against content hash 9ebcf3d86555, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-context-manager CLAUDE.md scanned grade A with 2 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**New tools return "Tool not found":** The HTTP server is running an older version. Run `make update` to rebuild and restart it. Check `curl http://localhost:4000/health` to confirm the version matches the plugin version

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| 30 | Branch-aware capture | Opt-in via `CONTEXT_MANAGER_BRANCH_AWARE` (default off). When enabled: `getCurrentBranch()` via `spawnSync`; branch stored on observations and sessions; soft-rank boost in search; filter on

CLAUDE.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working in this repository.

Status: ACTIVE Last Updated: June 3, 2026 (v0.8.159)

Project Overview

claude-context-manager is a Claude Code plugin that provides structured session history and searchable context. It automatically captures tool interactions in SQLite with full-text search, and exports high-importance observations to Claude Code's auto-memory topic files.

Owner: Larry Smith Jr. | Email: [email protected] Repository: github.com/mrlesmithjr/claude-context-manager

Branch Strategy

Two branches. All development happens on develop. main is release-only.

Branch	Purpose	Direct push
`develop`	Active development, all commits land here	Yes
`main`	Stable releases only	NEVER — PRs only

Rules enforced at three layers:

GitHub ruleset (protect-main, ID 16896369) — blocks any direct push to main, requires the test status check to pass before merge. No bypass, including for the repo owner.
Local pre-push hook (scripts/pre-push-hook.sh) — installed automatically by npm install via the prepare script. Aborts git push immediately if the destination ref is main.
This document — if you find yourself about to commit to main, stop. Push to develop and open a PR.

Release workflow (develop to main):

make ship

make ship is the correct end-to-end release command. It: bumps the patch version, runs make update (build, commit artifacts, push develop, restart server), then runs make release (open PR, poll CI, squash-merge, tag, create GitHub Release). Do not run make release directly — it skips the build step. After make ship completes, run /plugin update context-manager inside Claude Code.

Development Workflow

This is a TypeScript Claude Code plugin. All code changes follow the mandatory multi-agent sequence:

Feature or fix: claude-code-plugin-developer → code-reviewer → doc-writer → make ship

Read the full file on GitHub · 346 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.

8d ago First seen · 346 lines · 7,210 tokens per session scan A 9ebcf3d86555

Subscribe to this mod's changes

claude-context-manager CLAUDE.md is an instructions file published in the GitHub repository mrlesmithjr/claude-context-manager (7 stars, last pushed 1mo ago), licensed MIT. It adds 7,210 tokens to every session, about $0.0360 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-context-manager: Instructions file for Claude Code