agentmods.dev

code-analysis-context-python-mcp: Agent for Claude Code

.claude/agents/dev-memory-manager.md

dev-memory-manager is an agent for Claude Code from andreahaku/code-analysis-context-python-mcp. It costs 121 tokens per session (371 once invoked), scanned A, original, MIT.

An agent for managing development knowledge in an LLM memory system, including important coding decisions, patterns, and work in progress. It can connect information across development sessions.

In plain words
What is it for?
Use it to check or install learning hooks, process queued knowledge from commits tagged #kb, save and search memories, mark critical information, and summarize ongoing work.
Why use it?
It helps preserve useful context before a conversation is shortened or ends, and can turn selected commits into searchable memories.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code.

This is andreahaku/code-analysis-context-python-mcp's own configuration. It tells Claude Code how to work on code-analysis-context-python-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything code-analysis-context-python-mcp configures →

not rated 1repo 1y ago A scan 121 tokens original MIT
View source ↗ andreahaku/code-analysis-context-python-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to andreahaku/code-analysis-context-python-mcp. 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/andreahaku/code-analysis-context-python-mcp/main/.claude/agents/dev-memory-manager.md
Clone the repo
git clone --depth 1 https://github.com/andreahaku/code-analysis-context-python-mcp

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.

agentmods badge for dev-memory-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/andreahaku/code-analysis-context-python-mcp/dev-memory-manager/github.svg)](https://agentmods.dev/agents/andreahaku/code-analysis-context-python-mcp/dev-memory-manager)
Your own site
<a href="https://agentmods.dev/agents/andreahaku/code-analysis-context-python-mcp/dev-memory-manager"><img src="https://agentmods.dev/badge/agents/andreahaku/code-analysis-context-python-mcp/dev-memory-manager/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.

agentmods 80×15 button for dev-memory-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/andreahaku/code-analysis-context-python-mcp/dev-memory-manager"><img src="https://agentmods.dev/badge/agents/andreahaku/code-analysis-context-python-mcp/dev-memory-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.00371
Opus 5.5 $0.00048 $0.00148
Sonnet 5.5 $0.00024 $0.00074
Haiku 4.5 $0.00012 $0.00037

Measured 2mo ago against content hash 7c1695ae08bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dev-memory-manager 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 2mo 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.

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/agents/dev-memory-manager.md · 38 lines

What it actually says

You are an expert Development Knowledge Manager specializing in intelligent curation and retrieval of programming knowledge using the LLM Memory MCP server.

Core Responsibilities

Auto-Learning Integration

  • Check if auto-learning hooks are installed (both git hooks and Claude Code hooks)
  • Install hooks automatically at project level on first use
  • Offer global hook installation if user requests it
  • Process auto-learning queue from git commits tagged with #kb
  • Convert captured commits into searchable memories

Context Preservation

  • Store current work-in-progress before conversation compacting
  • Create comprehensive summaries of complex discussions
  • Link current work to previous sessions
  • Maintain state of multi-session features

Knowledge Management

  • Use memory.upsert to create/update memories
  • Use memory.query to search for relevant knowledge
  • Use memory.pin for critical information
  • Use memory.tag for organization

Workflow

  1. On session start: Check for queued auto-learning events
  2. Process queue and present captured knowledge
  3. During development: Capture important insights
  4. Before context loss: Preserve session state
  5. Suggest adding #kb tag to important commits
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. 2mo ago First seen · 38 lines · 0 tokens per session scan A 7c1695ae08bb

Subscribe to this mod's changes

dev-memory-manager is an agent published in the GitHub repository andreahaku/code-analysis-context-python-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 121 tokens to every session and 371 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.

Memory and context
Related

dev-memory-manager compared with agents from other repositories

dev-memory-manager next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dev-memory-managerandreahaku/code-analysis-context-python-mcpAgent11y agoMITA121Claude Code
context-finderfuturegerald/futuregerald-claude-pluginAgent72d agononeA107Claude Code
wiki-ingestkarlorz/llm-wikiAgent5yesterdaynoneA64Claude Code
memory-curatorwbind-core/termpipe-mcpAgent04d agononeA45Claude Code
data scientistkhalilbenaz/MDANAgent023d agoMITA8Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code