@mxalbert/context-mode 2.0.0

package/configs/copilot-cli/README.md

@@ -0,0 +1,47 @@
+# context-mode — GitHub Copilot CLI plugin
+
+One-command install of the context-mode MCP server (and routing skill) into
+GitHub Copilot CLI, with **no `context-mode upgrade` / agent call required**:
+
+```sh
+copilot plugin install mxalbert1996/context-mode:configs/copilot-cli
+```
+
+This registers:
+
+- **MCP server** (`.mcp.json`) — exposes the `ctx_*` tools (`ctx_execute`,
+  `ctx_batch_execute`, `ctx_search`, `ctx_fetch_and_index`, …). The server is
+  launched with `CONTEXT_MODE_PLATFORM=copilot-cli`, so it self-identifies as
+  Copilot regardless of any other CLI installed on the machine — `ctx_upgrade`
+  and platform detection resolve `copilot-cli`, never a co-installed Claude Code.
+- **Routing skill** (`skills/context-mode/`) — the MANDATORY "Think in Code"
+  rules that keep raw bytes out of the context window.
+- **Capture hooks** (`hooks.json`) — `preToolUse`, `postToolUse`,
+  `sessionStart`, `userPromptSubmitted`, `agentStop`, `preCompact` (Copilot
+  CLI's camelCase event names — verified against the `@github/copilot` 1.0.60
+  binary; PascalCase keys are silently ignored and never fire), each dispatching
+  `context-mode hook copilot-cli <event>`. Byte-equivalent to what
+  `context-mode upgrade` writes to `~/.copilot/hooks/`, so the plugin registers
+  them with no `upgrade` / agent call.
+
+## Prerequisite
+
+The MCP server runs the global `context-mode` binary (it needs the native
+`better-sqlite3` dependency):
+
+```sh
+npm install -g @mxalbert/context-mode
+```
+
+## Alternative (no plugin)
+
+```sh
+copilot mcp add context-mode --env CONTEXT_MODE_PLATFORM=copilot-cli -- context-mode
+```
+
+Then, to also install the capture hooks, run the upgrade **from inside Copilot**
+(so it detects `copilot-cli` via the live MCP client) rather than standalone:
+
+```sh
+copilot -p "Use the context-mode ctx_upgrade tool to install context-mode's hooks." --allow-all
+```

package/configs/copilot-cli/hooks.json

@@ -0,0 +1,41 @@
+{
+  "version": 1,
+  "hooks": {
+    "preToolUse": [
+      {
+        "type": "command",
+        "command": "context-mode hook copilot-cli pretooluse"
+      }
+    ],
+    "postToolUse": [
+      {
+        "type": "command",
+        "command": "context-mode hook copilot-cli posttooluse"
+      }
+    ],
+    "sessionStart": [
+      {
+        "type": "command",
+        "command": "context-mode hook copilot-cli sessionstart"
+      }
+    ],
+    "userPromptSubmitted": [
+      {
+        "type": "command",
+        "command": "context-mode hook copilot-cli userpromptsubmit"
+      }
+    ],
+    "agentStop": [
+      {
+        "type": "command",
+        "command": "context-mode hook copilot-cli stop"
+      }
+    ],
+    "preCompact": [
+      {
+        "type": "command",
+        "command": "context-mode hook copilot-cli precompact"
+      }
+    ]
+  }
+}

package/configs/copilot-cli/skills/context-mode/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: context-mode
+description: MANDATORY routing rules for context-mode. Invoke whenever you analyze, count, filter, compare, search, parse, or transform data; fetch a URL; or run a data-heavy command — so raw bytes stay out of the context window.
+---
+
+# context-mode — MANDATORY routing rules
+
+context-mode MCP tools are available in GitHub Copilot CLI. These rules protect
+the context window from flooding — one unrouted command can dump tens of KB into
+the conversation. Follow them strictly.
+
+## Think in Code — MANDATORY
+
+Analyze / count / filter / compare / search / parse / transform data: **write
+code** via `ctx_execute(language, code)` and `console.log()` only the answer. Do
+NOT read raw data into context. PROGRAM the analysis, do not COMPUTE it by
+reading. One script replaces ten tool calls.
+
+## BLOCKED — do NOT use
+
+- **curl / wget** — dumps raw HTTP into context. Use
+  `ctx_fetch_and_index(url, source)` then `ctx_search(queries)`.
+- **Inline HTTP** (`node -e "fetch(...)"`, `python -c "requests.get(...)"`) — use
+  `ctx_execute(language, code)`; only stdout enters context.
+- **Reading large files to analyze** — use
+  `ctx_execute_file(path, language, code)`.
+
+## Tool selection
+
+1. **GATHER**: `ctx_batch_execute(commands, queries)` — runs all commands,
+   auto-indexes, returns search. One call replaces dozens.
+2. **PROCESS**: `ctx_execute` / `ctx_execute_file` — sandbox; only stdout enters
+   context.
+3. **WEB**: `ctx_fetch_and_index(url, source)` then `ctx_search(queries)` — raw
+   HTML never enters context.
+4. **SEARCH**: `ctx_search(queries: [...])` — all questions in one call.
+
+Write artifacts to FILES; return a path + one-line description, not inline dumps.

package/configs/cursor/context-mode.mdc

@@ -0,0 +1,76 @@
+---
+description: context-mode routing rules for context window protection
+alwaysApply: true
+---
+
+# context-mode
+
+Raw tool output floods context window. Use context-mode MCP tools to keep raw data in sandbox.
+
+## Think in Code — MANDATORY
+
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
+
+## Tool Selection
+
+0. **MEMORY**: `ctx_search(sort: "timeline")` — after resume, check prior context before asking user.
+1. **GATHER**: `ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, searches. ONE call replaces many steps.
+2. **FOLLOW-UP**: `ctx_search(queries: ["q1", "q2", ...])` — all follow-up questions, ONE call (default relevance mode).
+3. **PROCESSING**: `ctx_execute(language, code)` | `ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `ctx_fetch_and_index(url)` then `ctx_search(queries)` — never dump raw HTML.
+5. **INDEX**: `ctx_index(content, source)` — store in FTS5 for later search.
+
+## Parallel I/O batches
+
+For multi-URL fetches or multi-API calls, **always** include `concurrency: N` (1-8):
+
+- `ctx_batch_execute(commands: [3+ network commands], concurrency: 5)` — gh, curl, dig, docker inspect, multi-region cloud queries
+- `ctx_fetch_and_index(requests: [{url, source}, ...], concurrency: 5)` — multi-URL batch fetch
+
+**Use concurrency 4-8** for I/O-bound work (network calls, API queries). **Keep concurrency 1** for CPU-bound (npm test, build, lint) or commands sharing state (ports, lock files, same-repo writes).
+
+GitHub API rate-limit: cap at 4 for `gh` calls.
+
+## Forbidden Actions
+
+- DO NOT use Bash for >20 lines output — use `ctx_execute` or `ctx_batch_execute`.
+- DO NOT use Read for analysis — use `ctx_execute_file`. Read IS correct for Edit.
+- DO NOT use WebFetch — use `ctx_fetch_and_index`.
+- DO NOT use curl/wget in terminal — use `ctx_fetch_and_index`.
+- Bash ONLY for git, mkdir, rm, mv, navigation, short commands.
+- DO NOT use `ctx_execute`/`ctx_execute_file` to create/modify files. ctx_execute is for analysis and computation only.
+
+## File Writing Policy
+
+ALWAYS use native file editing tools to create/modify files. NEVER use `ctx_execute`, `ctx_execute_file`, or Bash to write file content.
+
+## Output
+
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+
+## Session Continuity
+
+Skills, roles, and decisions persist for the entire session. Do not abandon them as the conversation grows.
+
+## Memory
+
+Session history is persistent and searchable. On resume, search BEFORE asking the user:
+
+| Need | Command |
+|------|---------|
+| What did we decide? | `ctx_search(queries: ["decision"], source: "decision", sort: "timeline")` |
+| What constraints exist? | `ctx_search(queries: ["constraint"], source: "constraint")` |
+
+DO NOT ask "what were we working on?" — SEARCH FIRST.
+If search returns 0 results, proceed as a fresh session.
+
+## ctx Commands
+
+| Command | Action |
+|---------|--------|
+| `ctx stats` | Call ctx_stats MCP tool, display full output verbatim. |
+| `ctx doctor` | Call ctx_doctor MCP tool, run returned shell command, display as checklist. |
+| `ctx upgrade` | Call ctx_upgrade MCP tool, run returned shell command, display as checklist. |
+| `ctx purge` | Call ctx_purge MCP tool with confirm: true. Warn user this is irreversible. |
+
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.

package/configs/cursor/hooks.json

@@ -0,0 +1,21 @@
+{
+  "version": 1,
+  "hooks": {
+    "preToolUse": [
+      {
+        "command": "context-mode hook cursor pretooluse",
+        "matcher": "Shell|Read|Grep|WebFetch|mcp_web_fetch|mcp_fetch_tool|Task|MCP:ctx_execute|MCP:ctx_execute_file|MCP:ctx_batch_execute|MCP:(?!ctx_)"
+      }
+    ],
+    "postToolUse": [
+      {
+        "command": "context-mode hook cursor posttooluse"
+      }
+    ],
+    "stop": [
+      {
+        "command": "context-mode hook cursor stop"
+      }
+    ]
+  }
+}

package/configs/cursor/mcp.json

@@ -0,0 +1,7 @@
+{
+  "mcpServers": {
+    "context-mode": {
+      "command": "context-mode"
+    }
+  }
+}

package/configs/gemini-cli/GEMINI.md

@@ -0,0 +1,88 @@
+# context-mode — MANDATORY routing rules
+
+context-mode MCP tools available. Rules protect context window from flooding. One unrouted command dumps 56 KB into context.
+
+## Think in Code — MANDATORY
+
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `mcp__context-mode__ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
+
+## BLOCKED — do NOT attempt
+
+### curl / wget — BLOCKED
+Shell `curl`/`wget` intercepted and blocked. Do NOT retry.
+Use: `mcp__context-mode__ctx_fetch_and_index(url, source)` or `mcp__context-mode__ctx_execute(language: "javascript", code: "const r = await fetch(...)")`
+
+### Inline HTTP — BLOCKED
+`fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, `http.request(` — intercepted. Do NOT retry.
+Use: `mcp__context-mode__ctx_execute(language, code)` — only stdout enters context
+
+### WebFetch / web browsing — BLOCKED
+Use: `mcp__context-mode__ctx_fetch_and_index(url, source)` then `mcp__context-mode__ctx_search(queries)`
+
+## REDIRECTED — use sandbox
+
+### Shell (>20 lines output)
+Shell ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`.
+Otherwise: `mcp__context-mode__ctx_batch_execute(commands, queries)` or `mcp__context-mode__ctx_execute(language: "javascript", code: "...")`. Use `language: "shell"` only when code matches the host shell.
+
+### read_file (for analysis)
+Reading to **edit** → read_file correct. Reading to **analyze/explore/summarize** → `mcp__context-mode__ctx_execute_file(path, language, code)`.
+
+### grep / search (large results)
+Use `mcp__context-mode__ctx_execute(language: "javascript", code: "...")` in sandbox for portable filtering/counting.
+
+## Tool selection
+
+0. **MEMORY**: `mcp__context-mode__ctx_search(sort: "timeline")` — after resume, check prior context before asking user.
+1. **GATHER**: `mcp__context-mode__ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, returns search. ONE call replaces 30+. Each command: `{label: "header", command: "..."}`.
+2. **FOLLOW-UP**: `mcp__context-mode__ctx_search(queries: ["q1", "q2", ...])` — all questions as array, ONE call (default relevance mode).
+3. **PROCESSING**: `mcp__context-mode__ctx_execute(language, code)` | `mcp__context-mode__ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `mcp__context-mode__ctx_fetch_and_index(url, source)` then `mcp__context-mode__ctx_search(queries)` — raw HTML never enters context.
+5. **INDEX**: `mcp__context-mode__ctx_index(content, source)` — store in FTS5 for later search.
+
+## Parallel I/O batches
+
+For multi-URL fetches or multi-API calls, **always** include `concurrency: N` (1-8):
+
+- `mcp__context-mode__ctx_batch_execute(commands: [3+ network commands], concurrency: 5)` — gh, curl, dig, docker inspect, multi-region cloud queries
+- `mcp__context-mode__ctx_fetch_and_index(requests: [{url, source}, ...], concurrency: 5)` — multi-URL batch fetch
+
+**Use concurrency 4-8** for I/O-bound work (network calls, API queries). **Keep concurrency 1** for CPU-bound (npm test, build, lint) or commands sharing state (ports, lock files, same-repo writes).
+
+GitHub API rate-limit: cap at 4 for `gh` calls.
+
+## Output
+
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+Descriptive source labels for `search(source: "label")`.
+
+## Session Continuity
+
+Skills, roles, and decisions persist for the entire session. Do not abandon them as the conversation grows.
+
+## Memory
+
+Session history is persistent and searchable. On resume, search BEFORE asking the user:
+
+| Need | Command |
+|------|---------|
+| What were we working on? | `mcp__context-mode__ctx_search(queries: ["summary"], source: "compaction", sort: "timeline")` |
+| What did we decide? | `mcp__context-mode__ctx_search(queries: ["decision"], source: "decision", sort: "timeline")` |
+| What NOT to repeat? | `mcp__context-mode__ctx_search(queries: ["rejected"], source: "rejected-approach")` |
+| What constraints exist? | `mcp__context-mode__ctx_search(queries: ["constraint"], source: "constraint")` |
+
+Note: user-prompt history not available.
+
+DO NOT ask "what were we working on?" — SEARCH FIRST.
+If search returns 0 results, proceed as a fresh session.
+
+## ctx commands
+
+| Command | Action |
+|---------|--------|
+| `ctx stats` | Call `stats` MCP tool, display full output verbatim |
+| `ctx doctor` | Call `doctor` MCP tool, run returned shell command, display as checklist |
+| `ctx upgrade` | Call `upgrade` MCP tool, run returned shell command, display as checklist |
+| `ctx purge` | Call `purge` MCP tool with confirm: true. Warns before wiping knowledge base. |
+
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.

package/configs/gemini-cli/mcp.json

@@ -0,0 +1,7 @@
+{
+  "mcpServers": {
+    "context-mode": {
+      "command": "context-mode"
+    }
+  }
+}

package/configs/gemini-cli/settings.json

@@ -0,0 +1,60 @@
+{
+  "$schema": "https://raw.githubusercontent.com/google-gemini/gemini-cli/main/packages/core/src/schema/settings-schema.json",
+  "hooks": {
+    "BeforeTool": [
+      {
+        "matcher": "run_shell_command|read_file|read_many_files|grep_search|search_file_content|web_fetch|activate_skill|mcp__plugin_context-mode",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "context-mode hook gemini-cli beforetool"
+          }
+        ]
+      }
+    ],
+    "AfterTool": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "context-mode hook gemini-cli aftertool"
+          }
+        ]
+      }
+    ],
+    "AfterModel": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "context-mode hook gemini-cli aftermodel"
+          }
+        ]
+      }
+    ],
+    "PreCompress": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "context-mode hook gemini-cli precompress"
+          }
+        ]
+      }
+    ],
+    "SessionStart": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "context-mode hook gemini-cli sessionstart"
+          }
+        ]
+      }
+    ]
+  }
+}

package/configs/jetbrains-copilot/copilot-instructions.md

@@ -0,0 +1,80 @@
+# context-mode — MANDATORY routing rules
+
+context-mode MCP tools available. Rules protect context window from flooding. One unrouted command dumps 56 KB into context.
+
+## Think in Code — MANDATORY
+
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
+
+## BLOCKED — do NOT attempt
+
+### curl / wget — BLOCKED
+Terminal `curl`/`wget` intercepted and blocked. Do NOT retry.
+Use: `ctx_fetch_and_index(url, source)` or `ctx_execute(language: "javascript", code: "const r = await fetch(...)")`
+
+### Inline HTTP — BLOCKED
+`fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, `http.request(` — intercepted. Do NOT retry.
+Use: `ctx_execute(language, code)` — only stdout enters context
+
+### WebFetch / fetch — BLOCKED
+Use: `ctx_fetch_and_index(url, source)` then `ctx_search(queries)`
+
+## REDIRECTED — use sandbox
+
+### Terminal / run_in_terminal (>20 lines output)
+Terminal ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`.
+Otherwise: `ctx_batch_execute(commands, queries)` or `ctx_execute(language: "javascript", code: "...")`. Use `language: "shell"` only when code matches the host shell.
+
+### read_file (for analysis)
+Reading to **edit** → read_file correct. Reading to **analyze/explore/summarize** → `ctx_execute_file(path, language, code)`.
+
+### grep / search (large results)
+Use `ctx_execute(language: "javascript", code: "...")` in sandbox for portable filtering/counting.
+
+## Tool selection
+
+0. **MEMORY**: `ctx_search(sort: "timeline")` — after resume, check prior context before asking user.
+1. **GATHER**: `ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, returns search. ONE call replaces 30+. Each command: `{label: "header", command: "..."}`.
+2. **FOLLOW-UP**: `ctx_search(queries: ["q1", "q2", ...])` — all questions as array, ONE call (default relevance mode).
+3. **PROCESSING**: `ctx_execute(language, code)` | `ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `ctx_fetch_and_index(url, source)` then `ctx_search(queries)` — raw HTML never enters context.
+5. **INDEX**: `ctx_index(content, source)` — store in FTS5 for later search.
+
+### Parallel I/O batches
+Pass `concurrency: 4-8` to `ctx_batch_execute` and `ctx_fetch_and_index` for network/API batches. Keep `concurrency: 1` for CPU-bound work (test, build, lint). GitHub gh: cap at 4.
+
+## Output
+
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+Descriptive source labels for `ctx_search(source: "label")`.
+
+## Session Continuity
+
+Skills, roles, and decisions persist for the entire session. Do not abandon them as the conversation grows.
+
+## Memory
+
+Session history is persistent and searchable. On resume, search BEFORE asking the user:
+
+| Need | Command |
+|------|---------|
+| What were we working on? | `ctx_search(queries: ["summary"], source: "compaction", sort: "timeline")` |
+| What did we decide? | `ctx_search(queries: ["decision"], source: "decision", sort: "timeline")` |
+| What NOT to repeat? | `ctx_search(queries: ["rejected"], source: "rejected-approach")` |
+| What constraints exist? | `ctx_search(queries: ["constraint"], source: "constraint")` |
+
+Note: user-prompt history not available.
+
+DO NOT ask "what were we working on?" — SEARCH FIRST.
+If search returns 0 results, proceed as a fresh session.
+
+## ctx commands
+
+| Command | Action |
+|---------|--------|
+| `ctx stats` | Call `ctx_stats` MCP tool, display full output verbatim |
+| `ctx doctor` | Call `ctx_doctor` MCP tool, run returned shell command, display as checklist |
+| `ctx upgrade` | Call `ctx_upgrade` MCP tool, run returned shell command, display as checklist |
+| `ctx purge` | Call `ctx_purge` MCP tool with confirm: true. Warns before wiping knowledge base. |
+
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.

package/configs/jetbrains-copilot/hooks.json

@@ -0,0 +1,16 @@
+{
+  "hooks": {
+    "PreToolUse": [
+      { "type": "command", "command": "context-mode hook jetbrains-copilot pretooluse" }
+    ],
+    "PostToolUse": [
+      { "type": "command", "command": "context-mode hook jetbrains-copilot posttooluse" }
+    ],
+    "PreCompact": [
+      { "type": "command", "command": "context-mode hook jetbrains-copilot precompact" }
+    ],
+    "SessionStart": [
+      { "type": "command", "command": "context-mode hook jetbrains-copilot sessionstart" }
+    ]
+  }
+}

package/configs/jetbrains-copilot/mcp.json

@@ -0,0 +1,7 @@
+{
+  "servers": {
+    "context-mode": {
+      "command": "context-mode"
+    }
+  }
+}

package/configs/kilo/AGENTS.md

@@ -0,0 +1,84 @@
+# context-mode — MANDATORY routing rules
+
+context-mode MCP tools available. Rules protect context window from flooding. One unrouted command dumps 56 KB into context.
+
+## Think in Code — MANDATORY
+
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `context-mode_ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
+
+## BLOCKED — do NOT attempt
+
+### curl / wget — BLOCKED
+Shell `curl`/`wget` intercepted and blocked. Do NOT retry.
+Use: `context-mode_ctx_fetch_and_index(url, source)` or `context-mode_ctx_execute(language: "javascript", code: "const r = await fetch(...)")`
+
+### Inline HTTP — BLOCKED
+`fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, `http.request(` — intercepted. Do NOT retry.
+Use: `context-mode_ctx_execute(language, code)` — only stdout enters context
+
+### Direct web fetching — BLOCKED
+Use: `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)`
+
+## REDIRECTED — use sandbox
+
+### Shell (>20 lines output)
+Shell ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`.
+Otherwise: `context-mode_ctx_batch_execute(commands, queries)` or `context-mode_ctx_execute(language: "javascript", code: "...")`. Use `language: "shell"` only when code matches the host shell.
+
+### File reading (for analysis)
+Reading to **edit** → reading correct. Reading to **analyze/explore/summarize** → `context-mode_ctx_execute_file(path, language, code)`.
+
+### grep / search (large results)
+Use `context-mode_ctx_execute(language: "javascript", code: "...")` in sandbox for portable filtering/counting.
+
+## Tool selection
+
+0. **MEMORY**: `context-mode_ctx_search(sort: "timeline")` — after resume, check prior context before asking user.
+1. **GATHER**: `context-mode_ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, returns search. ONE call replaces 30+. Each command: `{label: "header", command: "..."}`.
+2. **FOLLOW-UP**: `context-mode_ctx_search(queries: ["q1", "q2", ...])` — all questions as array, ONE call (default relevance mode).
+3. **PROCESSING**: `context-mode_ctx_execute(language, code)` | `context-mode_ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)` — raw HTML never enters context.
+5. **INDEX**: `context-mode_ctx_index(content, source)` — store in FTS5 for later search.
+
+## Parallel I/O batches
+
+For multi-URL fetches or multi-API calls, **always** include `concurrency: N` (1-8):
+
+- `context-mode_ctx_batch_execute(commands: [3+ network commands], concurrency: 5)` — gh, curl, dig, docker inspect, multi-region cloud queries
+- `context-mode_ctx_fetch_and_index(requests: [{url, source}, ...], concurrency: 5)` — multi-URL batch fetch
+
+**Use concurrency 4-8** for I/O-bound work (network calls, API queries). **Keep concurrency 1** for CPU-bound (npm test, build, lint) or commands sharing state (ports, lock files, same-repo writes).
+
+GitHub API rate-limit: cap at 4 for `gh` calls.
+
+## Output
+
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+Descriptive source labels for `context-mode_ctx_search(source: "label")`.
+
+## Session Continuity
+
+Skills, roles, and decisions persist for the entire session. Do not abandon them as the conversation grows.
+
+## Memory
+
+Session history is persistent and searchable. On resume, search BEFORE asking the user:
+
+| Need | Command |
+|------|---------|
+| What did we decide? | `context-mode_ctx_search(queries: ["decision"], source: "decision", sort: "timeline")` |
+| What constraints exist? | `context-mode_ctx_search(queries: ["constraint"], source: "constraint")` |
+
+DO NOT ask "what were we working on?" — SEARCH FIRST.
+If search returns 0 results, proceed as a fresh session.
+
+## ctx commands
+
+| Command | Action |
+|---------|--------|
+| `ctx stats` | Call `stats` MCP tool, display full output verbatim |
+| `ctx doctor` | Call `doctor` MCP tool, run returned shell command, display as checklist |
+| `ctx upgrade` | Call `upgrade` MCP tool, run returned shell command, display as checklist |
+| `ctx purge` | Call `purge` MCP tool with confirm: true. Warns before wiping knowledge base. |
+
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.

package/configs/kilo/kilo.json

@@ -0,0 +1,6 @@
+{
+  "$schema": "https://app.kilo.ai/config.json",
+  "plugin": [
+    "context-mode"
+  ]
+}

package/configs/kimi/hooks.json

@@ -0,0 +1,54 @@
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Bash|Shell|Read|Edit|Write|WebFetch|Agent|ctx_execute|ctx_execute_file|ctx_batch_execute|ctx_fetch_and_index|ctx_search|ctx_index|mcp__",
+        "hooks": [
+          { "type": "command", "command": "context-mode hook kimi pretooluse" }
+        ]
+      }
+    ],
+    "PostToolUse": [
+      {
+        "hooks": [
+          { "type": "command", "command": "context-mode hook kimi posttooluse" }
+        ]
+      }
+    ],
+    "SessionStart": [
+      {
+        "hooks": [
+          { "type": "command", "command": "context-mode hook kimi sessionstart" }
+        ]
+      }
+    ],
+    "SessionEnd": [
+      {
+        "hooks": [
+          { "type": "command", "command": "context-mode hook kimi sessionend" }
+        ]
+      }
+    ],
+    "PreCompact": [
+      {
+        "hooks": [
+          { "type": "command", "command": "context-mode hook kimi precompact" }
+        ]
+      }
+    ],
+    "UserPromptSubmit": [
+      {
+        "hooks": [
+          { "type": "command", "command": "context-mode hook kimi userpromptsubmit" }
+        ]
+      }
+    ],
+    "Stop": [
+      {
+        "hooks": [
+          { "type": "command", "command": "context-mode hook kimi stop" }
+        ]
+      }
+    ]
+  }
+}