Context Mode Output Sandbox

What it does

When your agent uses it

• Analyzing a large log file without printing it into the conversation
• Summarizing test, build or coverage output
• Inspecting a Playwright page snapshot or accessibility tree
• Fetching and indexing documentation for later search

Example prompts

• “Analyze error.log and list the five most frequent errors.”
• “Run the test suite and summarize only the failures.”
• “Fetch the React docs, index them, then answer from the index.”

Requirements

• The context-mode MCP tools, such as ctx_execute and ctx_execute_file

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Always console.log/print your findings. stdout is all that enters context. No output = wasted call.
2. 2Write analysis code, not just data dumps. Don't console.log(JSON.stringify(data)) — analyze first, print findings.
3. 3Be specific in output. Print bug details with IDs, line numbers, exact values — not just counts.
4. 4For files you need to EDIT: Use the normal Read tool. context-mode is for analysis, not editing.
5. 5For Bash whitelist commands only: Use Bash for file mutations, git writes, navigation, process control, package install, and echo…
6. 6Never use ctx_index(content: large_data). Use ctx_index(path: ...) to read files server-side. The content parameter sends data through…
7. 7Always use filename parameter on Playwright tools (browser_snapshot, browser_console_messages, browser_network_requests). Without it, the…
8. 8Don't re-index data already in context. If an MCP tool returned data in a previous response, it's already loaded — use it directly or save…

What it can do on your machine

Read from SKILL.md and the folder at commit 2a7a92a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git
  • npm
  • gh
  • kubectl
  • pip
  • aws
  • go
  • docker
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • raw.githubusercontent.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Context Mode Output Sandbox loads about 4.1k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 240 tokens; SKILL.md has 1,306 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~240

When it runs · the whole SKILL.md, loaded when a task matches

~4.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~13k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,306 words (~4,090 tokens).

name

context-mode

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (references) in skills/context-mode of mksglu/context-mode.

• SKILL.md
• references/anti-patterns.md
• references/patterns-javascript.md
• references/patterns-python.md
• references/patterns-shell.md

Open the folder on GitHubat commit 2a7a92a