context-mode
Use Context Mode for large command, test, log, API, document, data, browser, or MCP output that would otherwise flood the model context.
Skill by som1shi
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/som1shi-context-mode-331333
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, backend, testing, data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/context-mode
What's inside
- Skill name
context-mode- Description
- Use Context Mode for large command, test, log, API, document, data, browser, or MCP output that would otherwise flood the model context. Keep small reads and ordinary code discovery in normal Pi tools.
- License
- MIT
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Context Mode Use Context Mode for genuinely large raw output that would flood the conversation or for substantial extraction or aggregation where the full input must be processed but only a compact result belongs in the conversation. Do not route ordinary discovery or small exact reads through MCP merely because they span more than 20 lines. Good targets include: - builds, tests, logs, dependency reports, and broad Git output; - large JSON, API responses, datasets, and documents; - browser snapshots, console messages, and network requests; - broad MCP results that need filtering, comparison, or synthesis. Keep normal Pi tools for small file reads, narrow searches, source navigation, and short command output. ## Choose the path Use the `context-mode` MCP server through the `mcp` gateway. - Use `context_mode_ctx_execute` when a command, fetch, or script can process the data directly in the sandbox. - Use `context_mode_ctx_execute_file` when the data already exists in a file. - Use `context_mode_ctx_index` with a file path when the source needs repeated search, then use `context_mode_ctx_search` for focused retrieval. - Use the `ctx-doctor` skill only for Context Mode setup or runtime diagnostics. Print only the result needed for the current decision. Do not truncate the input before analysis merely to reduce output. ## File-first flow When a browser or another tool can save large output directly, save it under `.scratch/`, then give the path to `context_mode_ctx_execute_file` or `context_mode_ctx_index`. Do not return the large result to the model and then pass the same content back through an inline `content` argument. Use the same file-first flow for large console output, network requests, generated reports, and local data. An explicit no-file or no-artifact instruction overrides `.scratch/` permission. ## Boundaries Context Mode changes how output is processed, not what actions are authorized. Read-only, mutation, external-effect, credential, and protected-action rules remain unchanged.
From som1shi/pi-config, MIT.
More from som1shi/pi-config
- 0.524score
commit
som1shi
Git commit and branch naming conventions only — ss/ branch prefix, terse imperative commit messages.
SkillBFreshness: BClaude Code +9 - 0.521score
brainstorming
som1shi
Use for unclear intent or a material goal, behavior, placement, or design choice unresolved after inspection.
SkillBFreshness: BClaude Code +9 - 0.521score
delegation
som1shi
Use subagents for nontrivial work, review support, research, reconnaissance, validation, and exceptional isolated implementation.
SkillBFreshness: BClaude Code +9 - 0.521score
code-quality-review
som1shi
Deep code-quality and simplification review for explicit review requests or concrete useful background quality checks.
SkillBFreshness: BClaude Code +9 - 0.521score
code-intelligence
som1shi
Use for code ownership, structure, symbols, types, references, call relationships, structural patterns, and diagnostics.
SkillBFreshness: BClaude Code +9 - 0.471score
behavioral-proof
som1shi
Selects proportionate evidence for material behavior changes and bug fixes.
SkillCFreshness: CClaude Code +9 - 0.455score
diagnose
som1shi
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: CClaude Code +9 - 0.450score
improve-codebase-architecture
som1shi
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.
SkillCFreshness: CClaude Code +9 - 0.450score
tdd
som1shi
Test-driven development with red-green-refactor loop.
SkillCFreshness: CClaude Code +9 - 0.450score
grill-with-docs
som1shi
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as…
SkillCFreshness: CClaude Code +9 - 0.445score
grill-me
som1shi
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 15, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/som1shi/pi-config
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from som1shi
- 0.524score
commit
som1shi
Git commit and branch naming conventions only — ss/ branch prefix, terse imperative commit messages.
SkillBFreshness: BClaude Code +9 - 0.521score
brainstorming
som1shi
Use for unclear intent or a material goal, behavior, placement, or design choice unresolved after inspection.
SkillBFreshness: BClaude Code +9 - 0.521score
delegation
som1shi
Use subagents for nontrivial work, review support, research, reconnaissance, validation, and exceptional isolated implementation.
SkillBFreshness: BClaude Code +9 - 0.521score
code-quality-review
som1shi
Deep code-quality and simplification review for explicit review requests or concrete useful background quality checks.
SkillBFreshness: BClaude Code +9 - 0.521score
code-intelligence
som1shi
Use for code ownership, structure, symbols, types, references, call relationships, structural patterns, and diagnostics.
SkillBFreshness: BClaude Code +9 - 0.471score
behavioral-proof
som1shi
Selects proportionate evidence for material behavior changes and bug fixes.
SkillCFreshness: CClaude Code +9
Cite this page
context-mode skill. Agent Mart. https://agentmart.dev/skills/som1shi-context-mode-331333 (last updated 2026-10-24)