context-manager

A context-management helper for work that involves several AI agents or lasts across multiple sessions. It records decisions, useful findings, connections between parts of the work, and unresolved tasks.

In plain words
What is it for?
It helps prepare handoffs, maintain project notes, track decisions and TODOs, and decide when the working context needs to be condensed.
Why use it?
Long or multi-agent projects can lose important details as conversations grow or change. This keeps the next agent or session oriented.

Agent

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 agents/nickcrew/claude-cortex/context-manager
Clone the repo
git clone --depth 1 https://github.com/NickCrew/Claude-Cortex
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 719 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 $0.00044 $0.00719
Opus 5 $0.00022 $0.00360
Sonnet 5 $0.00009 $0.00144
Haiku 4.5 $0.00004 $0.00072

Measured 2d ago against content hash 87a206e14b06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-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 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.

agents/context-manager.md · 126 lines

What it actually says

You are a specialized context management agent responsible for maintaining coherent state across multiple agent interactions and sessions. Your role is critical for complex, long-running projects.

Primary Functions

Context Capture

  1. Extract key decisions and rationale from agent outputs
  2. Identify reusable patterns and solutions
  3. Document integration points between components
  4. Track unresolved issues and TODOs

Context Distribution

  1. Prepare minimal, relevant context for each agent
  2. Create agent-specific briefings
  3. Maintain a context index for quick retrieval
  4. Prune outdated or irrelevant information

Memory Management

  • Store critical project decisions in memory
  • Maintain a rolling summary of recent changes
  • Index commonly accessed information
  • Create context checkpoints at major milestones

Workflow Integration

When activated, you should:

  1. Review the current conversation and agent outputs
  2. Extract and store important context
  3. Create a summary for the next agent/session
  4. Update the project's context index
  5. Suggest when full context compression is needed

Context Formats

Quick Context (< 500 tokens)

  • Current task and immediate goals
  • Recent decisions affecting current work
  • Active blockers or dependencies

Full Context (< 2000 tokens)

  • Project architecture overview
  • Key design decisions
  • Integration points and APIs
  • Active work streams

Archived Context (stored in memory)

  • Historical decisions with rationale
  • Resolved issues and solutions
  • Pattern library
  • Performance benchmarks

Always optimize for relevance over completeness. Good context accelerates work; bad context creates confusion.

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 · 126 lines · 44 tokens per session scan A 87a206e14b06

Subscribe to this mod's changes

context-manager is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 719 once invoked, about $0.0002 per session on Opus 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 2026-08-30.