researcher-context-compression

researcher-context-compression is a skill for Cursor from budagov-lab/DreamTeam. It costs 41 tokens per session (335 once invoked), scanned A, original, MIT.

A project-memory maintenance skill that condenses recent coding work and keeps the system’s architecture notes current.

In plain words
What is it for?
Use it after every 20 completed tasks, or when the system signals it. It reads and updates summaries and architecture information through the project database.
Why use it?
It reduces clutter when project context becomes too large or unclear, while preserving important design decisions.

Skill for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it after every 20 completed tasks, or when the system signals it. It reads and updates summaries and architecture information through the project database.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/budagov-lab/dreamteam/researcher-context-compression
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.

Any agent
npx skills add budagov-lab/DreamTeam --skill researcher-context-compression
Clone the repo
git clone --depth 1 https://github.com/budagov-lab/DreamTeam

Made for: Cursor.

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 researcher-context-compression

README.md
[![agentmods](https://agentmods.dev/badge/skills/budagov-lab/dreamteam/researcher-context-compression/github.svg)](https://agentmods.dev/skills/budagov-lab/dreamteam/researcher-context-compression)
Your own site
<a href="https://agentmods.dev/skills/budagov-lab/dreamteam/researcher-context-compression"><img src="https://agentmods.dev/badge/skills/budagov-lab/dreamteam/researcher-context-compression/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 researcher-context-compression

Your own site · 80×15
<a href="https://agentmods.dev/skills/budagov-lab/dreamteam/researcher-context-compression"><img src="https://agentmods.dev/badge/skills/budagov-lab/dreamteam/researcher-context-compression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 335 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 $0.00041 $0.00335
Opus 5 $0.00020 $0.00168
Sonnet 5 $0.00008 $0.00067
Haiku 4.5 $0.00004 $0.00034

Measured 10d ago against content hash 534afd7fb774, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

researcher-context-compression 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 10d 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.

.cursor/skills/researcher-context-compression/SKILL.md · 34 lines

What it actually says

Researcher Context Compression

When to Use

  • When python -m dreamteam update-task <id> done prints TRIGGER_RESEARCHER (source of truth)
  • After every 20 completed tasks
  • When context feels noisy or architecture is unclear

Workflow

  1. Read from DB: Terminal → python -m dreamteam memory-get summaries, python -m dreamteam memory-get architecture, python -m dreamteam recent-tasks 20 (or MCP dreamteam_*)
  2. Summarize: Condense last 20 tasks into a brief summary
  3. Update architecture: Add new modules, dependencies, ownership
  4. Compress: Remove redundant or outdated content (see Researcher agent compression rules)
  5. Write to DB: Draft to .dreamteam/temp/, then Terminal → python -m dreamteam memory-set summaries <file>, python -m dreamteam memory-set architecture <file> (or MCP dreamteam_set_memory)

CRITICAL: Read and write memory ONLY via DB (memory-get, memory-set). Do NOT read/write .dreamteam/memory/*.md directly.

Output

  • Updated summaries and architecture in DB (via memory-set)
  • Orchestrator runs memory-to-files after Researcher

Rules

  • Keep summaries concise
  • Preserve critical architectural decisions
  • Document module → owner mapping
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. 10d ago First seen · 34 lines · 41 tokens per session scan A 534afd7fb774

Subscribe to this mod's changes

researcher-context-compression is a skill published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 335 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 2026-08-31.