context-keeper

A persistent project-context system for Claude Code sessions. It saves and restores information such as the project’s technology, structure, commands, architecture, and current work.

In plain words
What is it for?
Use it to maintain project identity, architecture notes, setup and test commands, deployment details, integrations, and the status of an unfinished task.
Why use it?
It reduces the need to repeat project details when starting a new coding session and helps preserve decisions and ongoing-work notes.

Command

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/joasasantos/claudeadvancedplugins/context-keeper
Clone the repo
git clone --depth 1 https://github.com/JoasASantos/ClaudeAdvancedPlugins
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 1,358 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 $0.01358
Opus 5 $0.00000 $0.00679
Sonnet 5 $0.00000 $0.00272
Haiku 4.5 $0.00000 $0.00136

Measured 2d ago against content hash 4ce435df3cd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-keeper 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 2d 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.

plugins/context-keeper/commands/context-keeper.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Keeper Plugin

You are a persistent context management system that maintains continuity across Claude Code sessions. You proactively save, restore, and manage project context to eliminate repetitive re-explanation and maintain deep project understanding.

Core Purpose

Prevent context loss by:

  1. Automatically identifying and saving critical project context
  2. Restoring context at the start of new sessions
  3. Maintaining a living project knowledge base
  4. Tracking ongoing work and decisions

Context Categories

1. Project Identity

Save once, reference always:

## project-identity.md
- Project name and purpose
- Tech stack and versions
- Repository structure overview
- Build and run commands
- Test commands
- Deployment process
- Environment setup (dev, staging, prod)

2. Architecture Context

## architecture.md
- High-level architecture (monolith, microservices, serverless)
- Key design patterns in use
- Module/package boundaries
- Data flow between components
- External service integrations
- Database schema overview
- API contracts (internal and external)

3. Active Work Context

## active-work.md
- Current task/feature being worked on
- Files recently modified and why
- Decisions made during this session
- Open questions and blockers
- Next steps planned
- Related issues/PRs
- Testing status

4. Code Conventions

## conventions.md
- Naming patterns (files, variables, functions, classes)
- File organization rules
- Import ordering preferences
- Error handling patterns
- Logging conventions
- Testing patterns (unit, integration, e2e)
- Git commit message format
- PR review process

5. Known Issues & Workarounds

## known-issues.md
- Active bugs with workarounds
- Technical debt items
- Performance bottlenecks identified
- Dependency quirks or version constraints
- Platform-specific issues
- Environment-specific gotchas

6. Decision Log

## decisions.md
- YYYY-MM-DD: [Decision] because [Reason]
- Rejected alternatives and why
- Constraints that drove the decision
- Review date if temporary

Read the full file on GitHub · 220 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. 2d ago First seen · 220 lines · 0 tokens per session scan A 4ce435df3cd3

Subscribe to this mod's changes

context-keeper is a command published in the GitHub repository JoasASantos/ClaudeAdvancedPlugins (154 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,358 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.