Skip to content
Slipstream agents

Agents for Claude Code, Codex and Cursor

Slipstream agents are specialist agents for Claude Code, Codex, Cursor and other MCP clients. Each does one job with your ContextStream workspace's context, declines anything else, and returns a short, cited result. They run on ContextStream, and a run is charged its price in credits only when it succeeds.

10 in ContextStream today, 2 of them free. 7 more built and tested, not offered yet. Updated

In ContextStream today

10 agents you can turn on now.

Each page has what the agent does and declines, its price, the access it gets, how to call it, and a real run with its input, output, time and cost.

Code

Code Oracle

code search agent

Code Oracle answers one question about where code is, what calls it, how it flows or where to change it, from the workspace's code index.

FreeEvals 202/212v0.2.0
Code

Docs Drift

documentation drift agent

Docs Drift finds statements in a repository's docs that its code no longer matches and proposes the edits as a diff.

800 credits a runEvals 7/7v0.1.0
Workspace

Lens

screenshot and image explainer agent

Lens explains an image a person shared: what it shows, the text in it, what in their workspace it relates to, and what to do next, with citations.

400 credits a runEvals 6/6v0.2.0
Mail and briefings

Mail

inbox triage and reply drafting agent

Mail reads the person's recent inbox, lists what needs a reply, the commitments made by them or to them and the deadlines in it, and saves reply drafts in their Drafts for them to send.

500 credits a runEvals 13/13v0.1.0
Workspace

Memory Gardener

workspace cleanup agent

The Memory Gardener finds duplicate or conflicting decisions and lessons and stale open items, and proposes merging, superseding or closing them.

400 credits a runEvals 12/12v0.1.0
Documents

PDF

docs to PDF agent

PDF lays out a source the person names (a doc, a plan, notes or markdown) as a PDF and stores it in the workspace.

600 credits a runEvals 11/11v0.1.0
Workspace

Plans & Tasks Keeper

plans and tasks status agent

Plans & Tasks Keeper answers one question about the status of the workspace's plans and tasks, citing their ids.

FreeEvals 106/106v0.1.0
Code

PR Reviewer

pull request review agent

PR Reviewer reviews one pull request's diff for bugs and for breaches of the workspace's decisions, lessons and preferences, citing the line and the constraint for each finding.

1,200 credits a runEvals 13/13v0.1.0
Code

Release Notes

release notes agent

Release Notes writes user-facing release notes for the changes between two refs of a connected repository, from its merged pull requests and commits, and saves them as a doc.

900 credits a runEvals 13/13v0.1.0
Code

Repo Guide

repository onboarding guide agent

Repo Guide writes an onboarding guide for an indexed repository, citing the files it describes.

500 credits a runEvals 7/7v0.1.0
Built and tested

7 agents ContextStream does not offer yet.

5 need a sandbox, which ContextStream's Slipstream worker does not have yet. 2 run only on Slipstream's own API, which is not open for accounts. Each page says why.

Code

CI Fixer

failing test fix agent

CI Fixer reproduces a failing test command in a public repository and returns the smallest change to the project's code that makes it pass, with the passing output.

5,000 credits a runEvals 13/13v0.1.0
Mail and briefings

Daily Briefing

RSS feed briefing agent

Daily Briefing returns the newest items from RSS and Atom feeds, without duplicates, quoting sentences word for word from each item's article.

Not priced yetEvals 8/8v1.0.0
Data

Data Analyst

CSV and Excel analysis agent

Data Analyst answers questions about one CSV or Excel table, in plain English or structured, with charts, and recomputes every number a second way before it reports it.

800 credits a runEvals 9/9v1.1.0
Code

Dependency Upgrader

dependency upgrade agent

Dependency Upgrader upgrades a public GitHub repository within its semver ranges, fixes the project's code when that breaks its tests, and returns the diff and the results.

8,000 credits a runEvals 10/10v1.0.0
Mail and briefings

Research Brief

feed research brief agent

Research Brief writes a short brief of the newest stories in RSS and Atom feeds, each point backed by a quote checked word for word against its article.

1,500 credits a runEvals 7/7v1.0.0
Code

Security Audit

dependency vulnerability audit agent

Security Audit finds known vulnerabilities in a public repository's locked dependencies and judges, citing the code, whether the project uses the vulnerable part of each.

2,500 credits a runEvals 9/9v0.1.0
Web

Site Auditor

Lighthouse page audit agent

Site Auditor runs Lighthouse, axe-core included, on one public web page and ranks the fixes by the score each would add.

Not priced yetEvals 9/9v1.0.0
How it works

Your coding agent hands off the job. The specialist does only that.

  1. Turn it onAn owner or admin turns each agent on in the workspace's specialist library.
  2. Ask from your agentClaude Code, Codex or Cursor calls it through ContextStream's MCP, or runs ss run in its shell.
  3. Get a short resultThe agent works with your workspace's decisions, lessons, docs and code, and returns a cited result.
  4. Pay for successA priced run starts only once its price is accepted. Declined and failed runs are free.
Connect Claude Code, Codex, Cursor and other MCP clients:
curl -fsSL https://contextstream.io/scripts/mcp.sh | bash
Or install ss, with ContextStream's command line:
curl -fsSL https://contextstream.io/cs/install.sh | sh
Questions

About the agents.

What are Slipstream agents?

Slipstream agents are specialist agents for Claude Code, Codex, Cursor and other MCP clients. Each does one job with your ContextStream workspace's context, declines anything else, and returns a short, cited result. They run on ContextStream, and a run is charged its price in credits only when it succeeds. Slipstream is part of ContextStream and billed in ContextStream credits.

Which agents work with Claude Code and Codex?

All of them. ContextStream's MCP gives Claude Code, Codex, Cursor and other MCP clients a slipstream tool that finds an agent, runs it and follows the run, and ss run <agent> does the same from a terminal or an agent's shell. 10 run in ContextStream today; 7 more are built and not offered yet.

Is there a code search agent?

Yes: Code Oracle. Code Oracle answers one question about where code is, what calls it, how it flows or where to change it, from the workspace's code index. It is free: a run costs no credits. More about Code Oracle

Is there a pull request review agent?

Yes: PR Reviewer. PR Reviewer reviews one pull request's diff for bugs and for breaches of the workspace's decisions, lessons and preferences, citing the line and the constraint for each finding. A run costs 1,200 credits, charged only when the run succeeds. More about PR Reviewer

Is there a release notes agent?

Yes: Release Notes. Release Notes writes user-facing release notes for the changes between two refs of a connected repository, from its merged pull requests and commits, and saves them as a doc. A run costs 900 credits, charged only when the run succeeds. More about Release Notes

What do the agents cost?

Each agent has a price per run in ContextStream credits, charged only when the run succeeds; a declined, failed, cancelled or timed-out run costs nothing. Code Oracle and Plans & Tasks Keeper are free. The others in ContextStream cost 400 to 1,200 credits a run. Credits come with every plan; Starter is free with 10,000 a month.

How do I turn an agent on?

An owner or admin of your ContextStream workspace turns each agent on in the specialist library of the web app. Specialist agents are opening workspace by workspace; if yours is not open yet, the library says so.