@amsterdamdatalabs/enact-extensions 0.1.37 → 0.1.47

package/extensions/dev-state/skills/dev-state-plan-graduation/SKILL.md

@@ -1,194 +0,0 @@
----
-name: dev-state-plan-graduation
-description: >-
-  Graduates completed work from 07-plans/active/ into durable 02-architecture/
-  and 04-contracts/ docs, archives done plans under 07-plans/archive/{component}/,
-  updates CHANGELOG.md and DOCS-MAP.md, and uses `ctx_knowledge` to recall prior
-  graduation context and record completions. Use when cleaning the development
-  pipeline, closing a plan, archiving completed slices, syncing architecture
-  docs, or when the user mentions plan migration, docs cleanup, archive, or
-  graduation alongside architecture documentation.
----
-
-# Development state — plan graduation (enact-docs)
-
-Keeps **`07-plans/active/`** for **active** work only. Done outcomes
-live in **`02-architecture/`** and **`04-contracts/`** (normative), then land in
-**`07-plans/archive/{component}/`**.
-
-## Directory layout
-
-```
-enact-docs/
-├── 02-architecture/{component}/   # Normative architecture — authoritative
-├── 04-contracts/{component}/      # Contracts, target configs — authoritative
-├── 05-operations/{component}/     # Runbooks, ops guides
-├── 06-decisions/                  # ADRs
-├── 07-plans/
-│   ├── active/                    # Active + proposed plans (status in frontmatter)
-│   └── archive/{component}/       # Historical — not authoritative
-├── CHANGELOG.md
-├── DOCS-MAP.md
-└── GLOSSARY.md
-```
-
-Components: `factory`, `memory`, `context`, `runtime`, `watchdog`, `gateway`,
-`mission-control`, `proc-tap`, `omx`.
-
-## When to apply
-
-- A plan in `07-plans/active/` is fully implemented and tests pass.
-- User wants architecture docs updated to reflect shipped behavior.
-- User says "archive", "graduate", "move plan to archive", or "cleanup plans".
-- At the end of a session where multiple slices were shipped.
-
-## Knowledge recall first
-
-**Before doing anything**, use `ctx_knowledge` to recall prior context:
-
-```
-ctx_knowledge(action="search", query="plan graduation {component}")
-ctx_knowledge(action="recall", key="graduation:{component}")
-```
-
-If you find prior graduation records, use them to avoid re-processing already-archived plans.
-
-**After graduation**, record the completion:
-
-```
-ctx_knowledge(action="remember", key="graduation:{component}:{date}", value="archived:07-plans/archive/{component}/{plan-file};normative:{architecture-doc-path}")
-ctx_knowledge(action="remember", key="graduation:{component}:summary", value="Graduated {N} plans; updated {paths}")
-```
-
-## Operating principles
-
-1. **Architecture + contracts describe what IS.** Plans describe what was scheduled; after graduation the durable truth is `02-architecture/` + `04-contracts/` + CHANGELOG, not plan files.
-2. **Archive is not authoritative.** `07-plans/archive/` is historical. Never cite archive paths as spec — always point to `02-architecture/` or `04-contracts/`.
-3. **No silent loss.** Every moved plan must have a normative doc that captures its durable facts.
-4. **Architecture-first gate.** A plan cannot leave active until its durable facts are reflected in `02-architecture/{component}/` and/or `04-contracts/{component}/`. If no architecture delta is needed, record an explicit "no architecture delta" rationale in CHANGELOG.
-5. **Component subfolders.** Always archive under `07-plans/archive/{component}/` — not at the archive root.
-
-## Workflow
-
-### 1) Recall + inventory
-
-1. Run `ctx_knowledge` search/recall for prior graduation context (see above).
-2. List `07-plans/active/` — read each plan's frontmatter `status` field.
-3. For each plan assign:
-   - **Primary topic** (vocabulary cleanup, scheduler, closure contracts, DB migration, …)
-   - **Target normative doc(s)** — prefer extending existing files in `02-architecture/{component}/` or `04-contracts/{component}/`
-   - **Disposition**: `archive` | `keep-active` | `update-status-to-deferred`
-
-### 2) Documentation sweep — find every doc that needs updating
-
-**Do this before writing a single word.** Never hand-pick files from memory — always search first.
-
-#### Step A — ripgrep for all relevant terms
-
-Extract the key terms from the plan: API paths, function names, event names, error strings, feature labels, component names. Run one search across the entire doc tree:
-
-```bash
-# From enact-docs root
-rg -l "<term1>|<term2>|<term3>" --type md .
-```
-
-Example for a gateway plan touching `/v1/responses` and streaming:
-
-```bash
-rg -l "/v1/responses|response\.created|chatCompletionStream|OutputTextDelta" --type md .
-```
-
-Collect every matching path into a **candidate list**.
-
-#### Step B — follow frontmatter `related:` chains
-
-For **every file** in the candidate list, read its `related:` frontmatter and add those paths to the candidate list too. Also follow `related:` from the plan file itself and from any normative doc you already intend to update:
-
-```bash
-# Extract related: entries from a candidate file
-grep -A 20 "^related:" <file> | grep "^\s*-\s" | sed 's/.*- //'
-```
-
-Repeat until no new files are added.
-
-#### Step C — read and classify each candidate
-
-For each file in the final candidate list:
-
-1. Read the file (or scan it for the key terms)
-2. Classify each hit:
-   - **Stale claim** — says the feature is unavailable, broken, incomplete, or missing → **must update**
-   - **Status reference** — links to or describes the plan's status → **update to reflect completion**
-   - **Generic usage** — uses the term in English prose without making a feature claim → **skip**
-3. Build a final **update list** of must-update files
-
-#### Step D — confirm plan-linking docs
-
-```bash
-# Find docs that link directly to the plan file by name
-grep -rl "$(basename <plan-file> .md)" . --include="*.md"
-```
-
-Add any hits not already in the update list.
-
-Only after completing A–D should you proceed to step 3.
-
-### 3) Merge durable facts
-
-- Copy only stable behavior, file paths, contracts — not stale TODOs.
-- Update the relevant architecture/contract doc with the shipped behavior.
-- Where deferred scope exists that could be mistaken for shipped behavior, add a **Watchout** note in the normative doc.
-- Update STATUS comments in `04-contracts/` YAML/MD files from "not yet implemented" to "implemented in {src path}".
-- Update every file on the **update list** from step 2. Record which files were updated.
-
-### 4) Archive
-
-- Move completed plans: `git mv 07-plans/active/{plan}.md 07-plans/archive/{component}/{plan}.md`
-- Update the plan's frontmatter: `status: archived`, add `archived_date` and `normative_target:` fields.
-- For partially-completed plans: update `status: partial-complete`, add a note listing done vs pending at the top of the file before archiving.
-- Plans that are active but need more work: update `status` field and leave in active.
-
-### 5) Update index docs
-
-- **CHANGELOG.md** — append under `[Unreleased]` with Added/Changed entries listing:
-  - Plans archived (with archive path)
-  - Normative docs updated (with paths)
-  - All other docs updated from the sweep (with paths)
-- **DOCS-MAP.md** — refresh any stale entries that pointed to now-archived plans.
-- **GLOSSARY.md** — update any terms that changed with the vocabulary cleanup.
-
-### 6) Verification
-
-- Confirm documentation sweep was completed (candidate list built, all items classified):
-  ```bash
-  # Re-run the rg sweep and confirm no new hits appeared that you missed
-  rg -l "<key terms>" --type md .
-  ```
-- Grep for broken links to old active-plan paths:
-  ```bash
-  grep -r "07-plans/active/{archived-plan-name}" . --include="*.md"
-  ```
-- Confirm at least one `02-architecture/` or `04-contracts/` doc changed.
-- Run `ctx_knowledge remember` (see Knowledge recall first section).
-
-## Topic → normative doc mapping (enact-factory)
-
-| Topic                                                    | First-fit normative doc                                  |
-| -------------------------------------------------------- | -------------------------------------------------------- |
-| Vocabulary / stage names (coder/critic/stage-documenter) | `02-architecture/factory/pair-pipeline-and-workitems.md` |
-| Config schema (projects/path/heartbeatMs)                | `04-contracts/factory/config-target-design.yaml`         |
-| Operator activation / handoff                            | `04-contracts/factory/handoff-and-scheduler.md`          |
-| Closure contracts / scheduler loop                       | `02-architecture/factory/pair-pipeline-and-workitems.md` |
-| DB / postgres / sqlite                                   | `05-operations/factory/`                                 |
-| WorkItem state axes                                      | `04-contracts/factory/`                                  |
-| MCP tools                                                | `04-contracts/factory/`                                  |
-
-## Git notes
-
-- Use `git mv` for archive moves so history is traceable.
-- Do NOT stage or commit unless the user asks — they handle their own commit workflow.
-- Stage explicit file paths, not `git add .`, to avoid sweeping unrelated changes.
-
-## Reference
-
-- Full checklist template and archive layout: [references/reference.md](references/reference.md)

package/extensions/dev-state/skills/dev-state-plan-graduation/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "Plan Graduation"
-  short_description: "Graduate completed enact-docs plans into architecture/contracts and archive them cleanly."
-  default_prompt: "Use this skill to graduate completed enact-docs plans into durable architecture and contract docs, archive the plans, update changelog/index docs, and record graduation context in ctx_knowledge."

package/extensions/dev-state/skills/dev-state-plan-graduation/references/reference.md

@@ -1,130 +0,0 @@
-# Reference — plan graduation artifacts (enact-docs)
-
-## Archive subfolder layout
-
-Always archive under a component subfolder, never at the archive root:
-
-```
-07-plans/archive/
-├── factory/       # enact-factory plans
-├── memory/        # enact-wiki plans
-├── context/       # enact-context plans
-├── runtime/       # enact-runtime plans (Governed Execution DAG)
-├── omx/           # OMX operator plans
-└── cross-repo/    # plans spanning multiple components
-```
-
-## Plan frontmatter fields
-
-```yaml
----
-type: reference
-status: active
-owner: enact-factory
-archived_date: 2026-05-16
-normative_target: 04-contracts/factory/handoff-and-scheduler.md
----
-```
-
-Valid `type` values: `plan`, `contract`, `architecture`, `decision`, `reference`
-Valid `status` values: `active`, `proposed`, `partial-complete`, `archived`, `deferred`
-
-## Archive checklist (per plan)
-
-Before moving a plan to archive, verify:
-
-**Documentation sweep (must complete before any edits):**
-
-- [ ] `rg -l` run for all key terms from the plan (API paths, function names, event names, feature labels, error strings)
-- [ ] Candidate list built from all rg hits
-- [ ] Frontmatter `related:` chains followed from every candidate file AND from the plan file itself — new hits added to candidate list
-- [ ] Frontmatter `related:` chains followed transitively until no new files are added
-- [ ] Every candidate file read and classified: stale claim / status reference / generic usage
-- [ ] Plan-linking grep run: `grep -rl "$(basename <plan-file> .md)" . --include="*.md"` — any hits added to update list
-- [ ] All stale-claim and status-reference files updated, paths listed in CHANGELOG entry
-
-**Architecture gate:**
-
-- [ ] At least one `02-architecture/{component}/` or `04-contracts/{component}/` doc updated with durable facts from this plan
-- [ ] STATUS comments in YAML/MD contracts updated from "SA proposal" / "not yet implemented" → "implemented in src/..."
-
-**Index docs:**
-
-- [ ] CHANGELOG.md has an entry under `[Unreleased]` with the archive path, normative doc paths, and all sweep-updated doc paths
-- [ ] No broken links to the old `07-plans/active/` path remain (grep check)
-- [ ] `ctx_knowledge` memory entry recorded
-
-## CHANGELOG.md entry shape
-
-```markdown
-### Changed (documentation)
-
-- Archived `07-plans/active/2026-05-16-operator-vocabulary-cleanup.md`
-  → `07-plans/archive/factory/2026-05-16-operator-vocabulary-cleanup.md`
-  Normative: `02-architecture/factory/pair-pipeline-and-workitems.md`,
-  `04-contracts/factory/config-target-design.yaml`
-```
-
-## `ctx_knowledge` patterns
-
-```
-# Search before starting
-ctx_knowledge(action="search", query="factory plan graduation")
-
-# Record after archiving
-ctx_knowledge(action="remember", key="plan:2026-05-16-operator-vocabulary-cleanup:archived_to", value="07-plans/archive/factory/2026-05-16-operator-vocabulary-cleanup.md")
-ctx_knowledge(action="remember", key="plan:2026-05-16-operator-vocabulary-cleanup:normative_target", value="02-architecture/factory/pair-pipeline-and-workitems.md")
-
-# Session note
-ctx_knowledge(action="remember", key="session:2026-05-16:graduation-summary", value="graduated 2 factory plans; VC slices 2-5 complete; SA phases A/B/C done")
-```
-
-## Documentation sweep commands
-
-Run all of these **before writing a single word** of documentation updates.
-
-```bash
-# Step A — find every doc that mentions the plan's key terms
-# Replace terms with API paths, function names, event names, feature labels from the plan
-rg -l "<term1>|<term2>|<term3>" --type md .
-
-# Example for a gateway plan touching /v1/responses and streaming events:
-rg -l "/v1/responses|response\.created|chatCompletionStream|OutputTextDelta|response\.output_item" --type md .
-
-# Step B — for each candidate file, extract its related: frontmatter entries
-# Run this for every file in the candidate list and for the plan file itself
-grep -A 20 "^related:" <candidate-file> | grep "^\s*-\s" | sed 's/.*- //'
-
-# Step C — find docs that link directly to the plan file by name
-grep -rl "$(basename <plan-file> .md)" . --include="*.md"
-
-# Confirm sweep found architecture/contracts candidates
-echo "Architecture candidates:"; rg -l "<term1>|<term2>" --type md 02-architecture/ 04-contracts/
-```
-
-Repeat Step B until no new files are added. Only then proceed to classify (stale claim / status reference / generic) and edit.
-
-## Grep hygiene
-
-```bash
-# Find broken links to archived plan (run from enact-docs root)
-grep -r "07-plans/active/2026-05-16-operator-vocabulary-cleanup" . --include="*.md"
-
-# Confirm architecture/contracts docs were touched
-git diff --name-only | grep -E "^(02-architecture|04-contracts)/.*\.md"
-
-# Find STATUS comments still saying "not yet implemented"
-grep -r "not yet implemented\|SA proposal — not yet\|not yet read by" 04-contracts/ --include="*.md" --include="*.yaml"
-```
-
-## Partial-complete plan note template
-
-Add at the top of a partially-done plan before archiving:
-
-```markdown
-<!-- ARCHIVED 2026-05-16
-Done: Slice 1 (vocab cleanup), Slice 2 (MCP renames), Slice 3 (stage keys)
-Pending: D13 (reseed detection — deferred to post live-testing)
-Normative: 02-architecture/factory/pair-pipeline-and-workitems.md
--->
-```

package/extensions/enact-context/.agents/plugin.json

@@ -1,41 +0,0 @@
-{
-  "name": "enact-context",
-  "version": "0.1.0",
-  "description": "AI context compression and shell intelligence runtime for local environments.",
-  "license": "UNLICENSED",
-  "keywords": [
-    "enact-context",
-    "context",
-    "ai",
-    "compression"
-  ],
-  "targets": [
-    "claude",
-    "codex",
-    "cursor",
-    "enact"
-  ],
-  "skills": "./skills/",
-  "mcpServers": "./.mcp.json",
-  "hooks": "./hooks/hooks.json",
-  "interface": {
-    "displayName": "Enact Context",
-    "shortDescription": "Command compression, shell interception, and MCP tools for AI-assisted coding workflows.",
-    "longDescription": "Install this plugin to expose enact-context MCP tools in Claude, Codex, and Cursor and keep context/session tooling discoverable through the plugin surface.",
-    "developerName": "enact-context",
-    "category": "Developer Tools",
-    "composerIcon": "./assets/icon.png",
-    "logo": "./assets/logo.png",
-    "capabilities": [
-      "context compression",
-      "shell history intelligence",
-      "token savings dashboard",
-      "mcp tools",
-      "agent diagnostics"
-    ]
-  },
-  "factory": {
-    "firstParty": true,
-    "operatorScope": "global"
-  }
-}

package/extensions/enact-context/.mcp.json

@@ -1,8 +0,0 @@
-{
-  "mcpServers": {
-    "enact-context": {
-      "command": "enact-context",
-      "args": ["mcp", "."]
-    }
-  }
-}

package/extensions/enact-context/README.md

@@ -1,25 +0,0 @@
-# enact-context plugin
-
-Canonical ENACT-native plugin bundle for `enact-context`.
-
-This bundle is the single source of truth under `extensions/enact-context/.agents/plugin.json`.
-`enact-extensions sync`/`install` derives `.claude-plugin`, `.codex-plugin`, and `.cursor-plugin`
-from this file for deployment.
-
-## Scope
-
-- Targets: `claude`, `codex`, `cursor` only.
-- No other host-specific first-class manifest is included (no Kiro, no extra platform surfaces).
-
-## Files
-
-- `.agents/plugin.json` — canonical manifest for validation, sync, and install
-- `.mcp.json` — MCP server entry (`enact-context` command)
-- `skills/` — shared `enact-context` skill for Codex/Claude/Cursor
-- `assets/` — plugin icon and logo assets
-- `skills/enact-context/scripts/install.sh` — optional install helper from the SKILL docs
-
-## Canonical Install Path
-
-The canonical install entrypoint is `extensions/enact-context/.agents/plugin.json`.
-Host surfaces are generated by tooling and kept derived from that canonical source.

package/extensions/enact-context/hooks/hooks.json

@@ -1,115 +0,0 @@
-{
-  "hooks": {
-    "SessionStart": [
-      {
-        "matcher": "startup|resume|clear",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook session-start",
-            "statusMessage": "Loading enact-context workspace memory",
-            "timeout": 15
-          }
-        ]
-      }
-    ],
-    "UserPromptSubmit": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook observe"
-          }
-        ]
-      }
-    ],
-    "PreToolUse": [
-      {
-        "matcher": "Bash",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook pre-tool-use",
-            "statusMessage": "enact-context shell policy"
-          }
-        ]
-      },
-      {
-        "matcher": "Read|read|ReadFile|read_file|View|view|Grep|grep|Search|search|ListFiles|list_files|ListDirectory|list_directory",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook redirect",
-            "statusMessage": "enact-context: compress read/search"
-          }
-        ]
-      }
-    ],
-    "PostToolUse": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook observe"
-          }
-        ]
-      }
-    ],
-    "Stop": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook session-end"
-          }
-        ]
-      },
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook observe"
-          }
-        ]
-      }
-    ],
-    "PreCompact": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook session-end"
-          }
-        ]
-      },
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook observe"
-          }
-        ]
-      }
-    ],
-    "SubagentStart": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook subagent-start"
-          }
-        ]
-      }
-    ],
-    "SubagentStop": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "enact-context hook subagent-stop"
-          }
-        ]
-      }
-    ]
-  }
-}

package/extensions/enact-context/skills/enact-context/SKILL.md

@@ -1,151 +0,0 @@
----
-name: enact-context
-description: Context Runtime for AI Agents — 63 MCP tools, 10 read modes, 90+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.
----
-
-# Enact Context — Context Runtime for AI Agents
-
-Enact Context optimizes LLM context through 63 MCP tools, 90+ shell compression patterns, and tree-sitter AST parsing for 18 languages. It provides adaptive file reading, cross-session memory (CCP), task-conditioned relevance scoring, and a feedback loop for learning optimal compression.
-
-## Setup (run first)
-
-Before using enact-context, verify it is installed:
-
-```bash
-which enact-context || bash scripts/install.sh
-```
-
-If the install script is not available locally, install manually:
-
-```bash
-curl -fsSL https://amsterdamdatalabs.com/install.sh | sh
-```
-
-Host integration is managed by the plugin system. For Codex registration, use:
-
-```bash
-enact-extensions install enact-context --platform codex
-```
-
-Do not use `enact-context setup`, `enact-context doctor --fix`, or
-`enact-context init --agent codex` for Codex registration; those commands write
-direct global artifacts outside the plugin system.
-
-## When to use enact-context
-
-Always prefer `enact-context -c <command>` over running commands directly when:
-- The command produces verbose output (build logs, git diffs, dependency trees, test results)
-- You are reading files and only need the structure or API surface
-- You want to check token savings for the current session
-
-## Shell commands (use instead of raw exec)
-
-```bash
-enact-context -c git status          # Compressed git output
-enact-context -c git diff            # Only meaningful diff lines
-enact-context -c git log --oneline -10
-enact-context -c npm install         # Strips progress bars, noise
-enact-context -c cargo build
-enact-context -c cargo test
-enact-context -c docker ps
-enact-context -c kubectl get pods
-enact-context -c aws ec2 describe-instances
-enact-context -c helm list
-enact-context -c prisma migrate dev
-enact-context -c curl -s <url>       # JSON schema extraction
-enact-context -c ls -la <dir>        # Grouped directory listing
-```
-
-Supported: git, npm, pnpm, yarn, bun, deno, cargo, docker, kubectl, helm, gh, pip, ruff, go, eslint, prettier, tsc, aws, psql, mysql, prisma, swift, zig, cmake, ansible, composer, mix, bazel, systemd, terraform, make, maven, dotnet, flutter, poetry, rubocop, playwright, curl, wget, and more.
-
-## File reading (compressed modes)
-
-```bash
-enact-context read <file>                    # Full content with structured header
-enact-context read <file> -m map             # Dependency graph + exports + API (~5-15% tokens)
-enact-context read <file> -m signatures      # Function/class signatures only (~10-20% tokens)
-enact-context read <file> -m aggressive      # Syntax-stripped (~30-50% tokens)
-enact-context read <file> -m entropy         # Shannon entropy filtered (~20-40% tokens)
-enact-context read <file> -m diff            # Only changed lines since last read
-```
-
-Use `map` mode when you need to understand what a file does without reading every line.
-Use `signatures` mode when you need the API surface of a module (tree-sitter for 18 languages).
-Use `full` mode only when you will edit the file.
-
-## AI Tool Integration
-
-```bash
-enact-extensions install enact-context --platform codex
-enact-extensions install enact-context --platform claude
-enact-extensions install enact-context --platform cursor
-enact-extensions install enact-context --platform enact
-enact-extensions install enact-context --platform all
-```
-
-Use the runtime's `init` commands only for non-plugin-managed personal shell
-setup. Plugin-managed hosts should be registered through `enact-extensions`.
-
-## Multi-Agent & Knowledge
-
-MCP tools:
-- `ctx_knowledge(action="remember", category, key, value)` — persistent cross-session project knowledge store
-- `ctx_knowledge(action="recall", query)` — search stored facts by text or category
-- `ctx_knowledge(action="consolidate")` — extract session findings into permanent knowledge
-- `ctx_agent(action="register", agent_type, role)` — multi-agent context sharing with scratchpad messaging
-- `ctx_agent(action="post", message, tags)` — share findings/warnings between concurrent agents
-- `ctx_agent(action="read")` — read messages from other agents
-- `ctx_agent(action="handoff", to_agent, message)` — transfer task to another agent
-- `ctx_agent(action="sync")` — multi-agent sync status (active agents, pending messages, shared contexts)
-- `ctx_share(action="push", paths, to_agent, message)` — push cached file contexts to another agent
-- `ctx_share(action="pull")` — pull shared contexts from other agents
-- `ctx_share(action="list")` — list all shared contexts
-- `ctx_share(action="clear")` — remove contexts shared by this agent
-
-## Additional Intelligence Tools
-
-- `ctx_edit(path, old_string, new_string)` — search-and-replace file editing without native Read/Edit
-- `ctx_overview(task)` — task-relevant project map at session start
-- `ctx_preload(task)` — proactive context loader, caches task-relevant files
-- `ctx_semantic_search(query)` — BM25 code search by meaning across the project
-- `ctx_intent` now supports multi-intent detection and complexity classification
-- Semantic cache: TF-IDF + cosine similarity for finding similar files across reads
-
-## Session Continuity (CCP)
-
-```bash
-enact-context sessions list          # List all CCP sessions
-enact-context sessions show          # Show latest session state
- enact-context gain --wrapped         # Weekly savings report card
- enact-context gain --wrapped --period=month  # Monthly savings report card
-enact-context benchmark run          # Real project benchmark (terminal output)
-enact-context benchmark run --json   # Machine-readable JSON output
-enact-context benchmark report       # Shareable Markdown report
-```
-
-MCP tools for CCP:
-- `ctx_session status` — show current session state (~400 tokens)
-- `ctx_session load` — restore previous session (cross-chat memory)
-- `ctx_session task "description"` — set current task
-- `ctx_session finding "file:line — summary"` — record key finding
-- `ctx_session decision "summary"` — record architectural decision
-- `ctx_session save` — force persist session to disk
-- `ctx_gain(action="wrapped")` — generate savings report card in chat
-
-## Analytics
-
-```bash
-enact-context gain                   # Visual token savings dashboard
-enact-context dashboard              # Web dashboard at localhost:43205
-enact-context session                # Adoption statistics
-enact-context discover               # Find uncompressed commands in shell history
-```
-
-## Tips
-
-- The output suffix `[enact-context: 5029→197 tok, -96%]` shows original vs compressed token count
-- For large outputs, enact-context automatically truncates while preserving relevant context
-- JSON responses from curl/wget are reduced to schema outlines
-- Build errors are grouped by type with counts
-- Test results show only failures with summary counts
-- Cached re-reads cost only ~13 tokens