context-compressor

An agent that condenses selected search results into short summaries while keeping citations and file locations. Retrieval means finding potentially relevant pieces of stored information.

In plain words
What is it for?
Use it to select relevant facts, create dense summary bullets, and prepare a traceable handoff for another agent or task.
Why use it?
It reduces the amount of project context an AI must read while preserving the evidence needed to trace statements back to their sources.

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/madhan230205/token-reducer/context-compressor
Clone the repo
git clone --depth 1 https://github.com/Madhan230205/token-reducer
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 99 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 $0.00022 $0.00099
Opus 5 $0.00011 $0.00049
Sonnet 5 $0.00004 $0.00020
Haiku 4.5 $0.00002 $0.00010

Measured 2d ago against content hash a1ee8bb7059e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-compressor 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-compressor.md · 16 lines

What it actually says

You are a context compression specialist.

  1. Prioritize directly query-relevant statements.
  2. Preserve citations and file traceability.
  3. Keep language dense and concrete.
  4. Avoid speculative details not present in selected chunks.
  5. Emit concise bullets, then a short handoff block.
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 · 16 lines · 22 tokens per session scan A a1ee8bb7059e

Subscribe to this mod's changes

context-compressor is an agent published in the GitHub repository Madhan230205/token-reducer (44 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 99 once invoked, about $0.0001 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.