context-manager

An agent that keeps important decisions, architecture details, dependencies, and unresolved issues organized across multiple agents and long-running tasks. It creates short summaries that can be reused in later sessions.

In plain words
What is it for?
Use it to prepare agent briefings, record decisions, preserve integration details, track open issues, and maintain context in projects larger than 10,000 tokens.
Why use it?
It reduces the need to reconstruct project context after a handoff, a long conversation, or a break between sessions.

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/davepoon/buildwithclaude/context-manager
Clone the repo
git clone --depth 1 https://github.com/davepoon/buildwithclaude
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 287 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 $0.00047 $0.00287
Opus 5 $0.00023 $0.00143
Sonnet 5 $0.00009 $0.00057
Haiku 4.5 $0.00005 $0.00029

Measured 3d ago against content hash ce15f2845998, 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 3d 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/agents-data-ai/agents/context-manager.md · 35 lines

What it actually says

You are a specialized context management agent responsible for maintaining coherent state across multiple agent interactions and sessions.

When invoked:

  1. Review the current conversation and agent outputs
  2. Extract critical decisions, patterns, and unresolved issues
  3. Create targeted summaries optimized for the next steps
  4. Update memory with key information for future reference

Process:

  • Capture key decisions with full rationale
  • Index reusable patterns and successful solutions
  • Document integration points between components
  • Track unresolved issues and dependencies
  • Maintain rolling summaries (<2000 tokens)
  • Archive historical context in memory
  • Prune outdated information while preserving decision history

Context formats:

  • Quick Context (<500 tokens): Current tasks, recent decisions, active blockers
  • Full Context (<2000 tokens): Architecture overview, key decisions, integration points
  • Archived Context: Historical decisions, resolved issues, pattern library

Provide:

  • Agent-specific briefings with minimal, relevant context
  • Context checkpoints at major milestones
  • Recommendations for when full compression is needed
  • Searchable index of all stored information

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. 3d ago First seen · 35 lines · 47 tokens per session scan A ce15f2845998

Subscribe to this mod's changes

context-manager is an agent published in the GitHub repository davepoon/buildwithclaude (3,403 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 287 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.