lcode-cli 0.9.0__tar.gz → 0.11.0__tar.gz

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/CHANGELOG.md

@@ -6,6 +6,44 @@ All notable changes to lcode are documented here. The format follows
 
 ## [Unreleased]
 
+## [0.11.0] - 2026-10-05
+
+### Added
+
+- Ready-made MCP servers for data and ML platforms:
+  - `lcode mcp add metabase` connects to the MCP server built into Metabase 60 and later, with browser
+    sign-in, so the model sees your data with your Metabase permissions.
+  - `lcode mcp add encord` and `lcode mcp add valohai`: those platforms have no MCP server of their own,
+    so lcode now ships `lcode-mcp-encord` (projects, datasets, ontologies, labeling progress, tasks and
+    labels, built on the Encord SDK) and `lcode-mcp-valohai` (executions with their logs, metrics and
+    outputs, pipelines). Both are read-only unless started with `--allow-writes`, which adds
+    assigning tasks and setting priorities (Encord) or starting and stopping executions (Valohai), and
+    both work with other MCP clients too. See [MCP servers](https://nasser1941.github.io/lcode/mcp/#encord).
+- Catalog questions that ask for an address now accept it without `https://`.
+
+## [0.10.0] - 2026-10-05
+
+### Added
+
+- Custom commands: prompt templates in `.lcode/commands/<name>.md` or
+  `~/.config/lcode/commands/`, run as `/name args`, with `$ARGUMENTS` and `$1`…`$9`, and an
+  optional frontmatter for the description, an argument hint and the tools allowed for the
+  request.
+- Skills in the [Agent Skills](https://agentskills.io) format, from `.lcode/skills/`,
+  `.agents/skills/` and `.claude/skills/` (in the repository and in your home folder). Only their
+  names and descriptions are in the system prompt; the model loads a skill's instructions with the
+  new `skill` tool when a task matches, and its scripts and reference files when the instructions
+  call for them. `/name` starts a skill yourself. `/help` lists commands and skills and where each
+  comes from. The `skills` setting limits them to lcode's own folders (`lcode`) or turns them off.
+  An example command and skill are in `examples/`. See
+  [Commands and skills](https://nasser1941.github.io/lcode/commands/).
+
+### Changed
+
+- A repository's own commands, skills and agents are used only after you approve them; lcode asks
+  the first time and again when they change, like a project's `.mcp.json`. Custom agents from a
+  repository (new in 0.8.0) used to load without asking.
+
 ## [0.9.0] - 2026-10-05
 
 ### Added
@@ -264,7 +302,9 @@ First public release.
 - `AGENTS.md` project instructions and `/init` to generate them.
 - One-line installer for Linux and macOS.
 
-[Unreleased]: https://github.com/nasser1941/lcode/compare/v0.9.0...HEAD
+[Unreleased]: https://github.com/nasser1941/lcode/compare/v0.11.0...HEAD
+[0.11.0]: https://github.com/nasser1941/lcode/compare/v0.10.0...v0.11.0
+[0.10.0]: https://github.com/nasser1941/lcode/compare/v0.9.0...v0.10.0
 [0.9.0]: https://github.com/nasser1941/lcode/compare/v0.8.0...v0.9.0
 [0.8.0]: https://github.com/nasser1941/lcode/compare/v0.7.0...v0.8.0
 [0.7.0]: https://github.com/nasser1941/lcode/compare/v0.6.1...v0.7.0

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: lcode-cli
-Version: 0.9.0
+Version: 0.11.0
 Summary: A local-first terminal coding agent powered by open-weight models on your own GPU or Mac, via Ollama.
 Project-URL: Homepage, https://nasser1941.github.io/lcode/
 Project-URL: Documentation, https://nasser1941.github.io/lcode/
@@ -30,6 +30,8 @@ Requires-Dist: prompt-toolkit>=3.0.43
 Requires-Dist: requests>=2.31
 Requires-Dist: rich>=13.7
 Requires-Dist: tomli>=2.0; python_version < '3.11'
+Provides-Extra: encord
+Requires-Dist: encord>=0.1.200; extra == 'encord'
 Description-Content-Type: text/markdown
 
 <p align="center">
@@ -80,6 +82,8 @@ through [Ollama](https://ollama.com), and when it needs current information it c
   your approval. `auto-edit` and `yolo` modes when you want speed.
 - **Sandbox (optional).** `lcode --sandbox` runs the model's shell commands in a container (Docker or
   Podman) that only sees your project, without network access unless you allow it.
+- **Commands and skills.** Your own `/commands` as prompt templates, and skills in the
+  [Agent Skills](https://agentskills.io) format that the model loads only when a task needs them.
 - **Plan mode.** `/plan <request>` or Shift+Tab: the model explores read-only and presents a plan;
   you approve, edit or send it back before anything changes.
 - **Undo.** lcode saves a checkpoint before the model changes files; `/undo` takes back the last
@@ -93,7 +97,7 @@ through [Ollama](https://ollama.com), and when it needs current information it c
 - **Bring your own model.** Eight curated open-weight models, all tested end to end, or any Ollama model
   with tool calling.
 - **MCP servers, ready to go.** Connect Jira and Confluence, GitHub, AWS, Google Drive, Grafana,
-  Google Cloud, Sentry, Linear, Notion, Postgres, Kubernetes and more with one command
+  Google Cloud, Sentry, Linear, Notion, Postgres, Kubernetes, Metabase, Encord, Valohai and more with one command
   (`lcode mcp add atlassian`), image generation with ComfyUI, or any other MCP server. Browser sign-in (OAuth) is built in.
 - **Sees images.** Attach a screenshot or mockup with `@path` and lcode looks at it, using the
   vision part of your model. With ComfyUI (`lcode mcp add comfyui`) it can also generate and edit
@@ -197,9 +201,10 @@ fills up. Details: [How it works](https://nasser1941.github.io/lcode/how-it-work
 
 See the pinned [Roadmap issue](https://github.com/nasser1941/lcode/issues/10). Next up:
 
-- [Custom commands and skills](https://github.com/nasser1941/lcode/issues/42)
-- [Ready-made MCP for Metabase, Encord and Valohai](https://github.com/nasser1941/lcode/issues/53)
-- Then: [smarter context for small windows](https://github.com/nasser1941/lcode/issues/46), [language servers](https://github.com/nasser1941/lcode/issues/44), [a repository map with local embeddings](https://github.com/nasser1941/lcode/issues/45), [hooks](https://github.com/nasser1941/lcode/issues/43)
+- [Smarter context for small windows](https://github.com/nasser1941/lcode/issues/46)
+- [Code intelligence with language servers](https://github.com/nasser1941/lcode/issues/44)
+- [A repository map and semantic search with local embeddings](https://github.com/nasser1941/lcode/issues/45)
+- [Hooks and permission rules](https://github.com/nasser1941/lcode/issues/43)
 - More models in the catalog, and test reports from your hardware ([report one](https://github.com/nasser1941/lcode/issues/new?template=model_request.yml))
 
 ## Contributing

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/README.md

@@ -46,6 +46,8 @@ through [Ollama](https://ollama.com), and when it needs current information it c
   your approval. `auto-edit` and `yolo` modes when you want speed.
 - **Sandbox (optional).** `lcode --sandbox` runs the model's shell commands in a container (Docker or
   Podman) that only sees your project, without network access unless you allow it.
+- **Commands and skills.** Your own `/commands` as prompt templates, and skills in the
+  [Agent Skills](https://agentskills.io) format that the model loads only when a task needs them.
 - **Plan mode.** `/plan <request>` or Shift+Tab: the model explores read-only and presents a plan;
   you approve, edit or send it back before anything changes.
 - **Undo.** lcode saves a checkpoint before the model changes files; `/undo` takes back the last
@@ -59,7 +61,7 @@ through [Ollama](https://ollama.com), and when it needs current information it c
 - **Bring your own model.** Eight curated open-weight models, all tested end to end, or any Ollama model
   with tool calling.
 - **MCP servers, ready to go.** Connect Jira and Confluence, GitHub, AWS, Google Drive, Grafana,
-  Google Cloud, Sentry, Linear, Notion, Postgres, Kubernetes and more with one command
+  Google Cloud, Sentry, Linear, Notion, Postgres, Kubernetes, Metabase, Encord, Valohai and more with one command
   (`lcode mcp add atlassian`), image generation with ComfyUI, or any other MCP server. Browser sign-in (OAuth) is built in.
 - **Sees images.** Attach a screenshot or mockup with `@path` and lcode looks at it, using the
   vision part of your model. With ComfyUI (`lcode mcp add comfyui`) it can also generate and edit
@@ -163,9 +165,10 @@ fills up. Details: [How it works](https://nasser1941.github.io/lcode/how-it-work
 
 See the pinned [Roadmap issue](https://github.com/nasser1941/lcode/issues/10). Next up:
 
-- [Custom commands and skills](https://github.com/nasser1941/lcode/issues/42)
-- [Ready-made MCP for Metabase, Encord and Valohai](https://github.com/nasser1941/lcode/issues/53)
-- Then: [smarter context for small windows](https://github.com/nasser1941/lcode/issues/46), [language servers](https://github.com/nasser1941/lcode/issues/44), [a repository map with local embeddings](https://github.com/nasser1941/lcode/issues/45), [hooks](https://github.com/nasser1941/lcode/issues/43)
+- [Smarter context for small windows](https://github.com/nasser1941/lcode/issues/46)
+- [Code intelligence with language servers](https://github.com/nasser1941/lcode/issues/44)
+- [A repository map and semantic search with local embeddings](https://github.com/nasser1941/lcode/issues/45)
+- [Hooks and permission rules](https://github.com/nasser1941/lcode/issues/43)
 - More models in the catalog, and test reports from your hardware ([report one](https://github.com/nasser1941/lcode/issues/new?template=model_request.yml))
 
 ## Contributing

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/docs/agents.md

@@ -134,7 +134,9 @@ Report bugs first, with `path:line`, then missing tests, then style. Don't fix a
 | `~/.config/lcode/agents/<name>.md` | For every repository |
 
 The file name is the agent's name. A repository's agent overrides one of yours with the same name,
-and both override the built-in types. `/agents` and `lcode doctor` point out files that couldn't be
+and both override the built-in types. A repository's agents are used only after you
+[approve them](commands.md#approving-a-repositorys-commands-skills-and-agents), together with its
+commands and skills. `/agents` and `lcode doctor` point out files that couldn't be
 read.
 
 ## Settings

lcode_cli-0.11.0/docs/commands.md

@@ -0,0 +1,131 @@
+# Commands and skills
+
+Teams repeat the same requests: "review this diff against our checklist", "write a migration the
+way we do it", the release steps. `AGENTS.md` can't hold all of that, because it goes into every
+request and every line costs context. lcode has two ways to keep such instructions ready without
+paying for them until they're used.
+
+| | Command | Skill |
+|---|---|---|
+| What it is | A prompt template | Instructions, plus scripts and reference files if needed |
+| Who starts it | You, with `/name args` | The model, when a task matches its description, or you with `/name` |
+| Context cost until used | Nothing | Its name and one-line description |
+| Format | `<name>.md` | A folder with a `SKILL.md`, in the [Agent Skills](https://agentskills.io) format |
+
+## Commands
+
+A command is a markdown file whose body is the request to send. `$ARGUMENTS` becomes everything
+you type after the command's name, and `$1` to `$9` single words. If the template has no
+placeholder, what you type is added at the end.
+
+```markdown
+---
+description: review the uncommitted changes for bugs and missing tests
+argument-hint: "[path or what to focus on]"
+allowed-tools: read_file grep glob list_dir bash
+---
+Review the uncommitted changes in this repository. $ARGUMENTS
+
+Run `git diff` and `git diff --cached` to see them, and read the code around them where needed.
+Report bugs first, with `path:line`, then missing tests. Don't change any files.
+```
+
+```text
+❯ /review the parser changes
+```
+
+| Frontmatter (all optional) | |
+|---|---|
+| `description` | Shown in `/help` and completion (default: the first line) |
+| `argument-hint` | Shown after the name in `/help`, e.g. `[path]` |
+| `allowed-tools` | The only tools the model gets for this request, e.g. `read_file grep bash` (lcode's tool names) |
+
+| Folder | Commands |
+|---|---|
+| `.lcode/commands/<name>.md` in the repository | For this repository; commit them to share them |
+| `~/.config/lcode/commands/<name>.md` | For every repository |
+
+The file name is the command's name. A repository's command overrides one of yours with the same
+name; built-in commands such as `/help` can't be replaced.
+
+## Skills
+
+A skill is a folder with a `SKILL.md`: a frontmatter with a `name` and a `description` that says
+what the skill does and when to use it, then instructions. Scripts, templates and reference files
+can sit next to it.
+
+```text
+.lcode/skills/commit-message/
+├── SKILL.md
+└── scripts/
+    └── staged.sh
+```
+
+```markdown
+---
+name: commit-message
+description: Writes a git commit message for the staged changes, in the style the repository
+  already uses. Use when the user asks for a commit message, or asks you to commit their changes.
+---
+# Commit messages
+
+1. Run `scripts/staged.sh` from this skill's folder. It prints the staged files and the subjects
+   of the last 15 commits.
+2. Match the style of the recent subjects …
+```
+
+How lcode uses them, step by step, so they cost almost nothing until needed:
+
+1. At the start of a session, the model gets only each skill's name and description.
+2. When a task matches a description, the model calls the `skill` tool. It gets the instructions,
+   the skill's folder and the list of files in it, but not their contents.
+3. The model reads or runs those files when the instructions call for them. Files in a skill's
+   folder can be read even when the [sandbox](sandbox.md) limits the model to the project.
+
+You can also start a skill yourself: `/commit-message` or `/commit-message only the parser
+changes`. After the conversation is compacted, the model is told which skills were in use, so it
+can load them again.
+
+lcode reads skills from these folders; a repository's skill overrides one of yours with the same
+name:
+
+| Folder | |
+|---|---|
+| `.lcode/skills/`, `.agents/skills/`, `.claude/skills/` in the repository | For this repository |
+| `~/.config/lcode/skills/`, `~/.agents/skills/`, `~/.claude/skills/` | For every repository |
+
+`.agents/skills/` is the folder agents share by convention, and `.claude/skills/` is read too, so
+skills you already have for other agents work in lcode. If other agents installed many skills you
+don't need here, `lcode config set skills lcode` limits lcode to its own folders (`skills off` turns
+skills off). However many there are, the list in the model's instructions stays within about 5% of
+the context window: with many skills, each description is shortened so that all of them stay
+listed. The same skill installed in two folders is used once. The format is the
+[Agent Skills specification](https://agentskills.io/specification); like other agents, lcode is
+lenient with skills that bend its rules (a name with capital letters, an unquoted colon in a
+description) and skips only those without a description. `/help` lists the skills it found and
+any it skipped.
+
+## Approving a repository's commands, skills and agents
+
+A repository's commands, skills and [agents](agents.md#custom-agents) steer the model, and skills
+can bring scripts. A freshly cloned repository shouldn't be able to do that silently, so the first
+time you start lcode in a repository that has any, it asks:
+
+```text
+This repository brings its own commands, skills or agents:
+  commands: /review
+  skills: commit-message
+They can steer the model and include scripts it may run (commands still ask first, unless you
+allow them).
+  Use them? [y/N]
+```
+
+lcode asks again whenever any of their files change. Until you say yes, only your own commands and
+skills are used. `lcode -p` never asks and doesn't use them.
+
+## Examples
+
+The lcode repository has a ready-made command and skill in
+[`examples/`](https://github.com/nasser1941/lcode/tree/main/examples): `/review` and the
+`commit-message` skill above. Copy them into `.lcode/` of a repository, or into
+`~/.config/lcode/` to have them everywhere.

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/docs/configuration.md

@@ -31,6 +31,7 @@ lcode config path                      # print the file location
 | `vision_model` | `auto` | The model that [looks at images](usage.md#images): `auto`, `off` or an Ollama model that can see |
 | `mcp_tools` | `auto` | How [MCP](mcp.md#context) tool definitions reach the model: `auto`, `direct` or `search` (on demand) |
 | `memory` | `ask` | [Notes that carry over](memory.md) to later sessions: `ask` (confirm each), `auto` or `off` |
+| `skills` | `all` | Which [skills](commands.md#skills) the model is offered: `all` (lcode's folders and the ones other agents share), `lcode` (only `.lcode/skills/` and `~/.config/lcode/skills/`) or `off` |
 | `subagents` | `true` | Let the model hand tasks to [subagents](agents.md) with their own context |
 | `max_parallel_agents` | `1` | Subagents that run at the same time; more needs `OLLAMA_NUM_PARALLEL` on the Ollama server ([details](agents.md#several-at-once)) |
 | `checkpoints` | `true` | Save a checkpoint before the model changes files, so [`/undo`](usage.md#undo-and-checkpoints) can restore them |
@@ -74,6 +75,8 @@ Environment variables override the file, which is useful for one-off runs and CI
 | `~/.local/state/lcode/mcp-logs/` | Error output of local MCP servers |
 | `~/.local/state/lcode/checkpoints/` | Checkpoints for `/undo` (copies of your project's files; deleted after 14 days) |
 | `~/.local/state/lcode/memory/` | [Memory](memory.md) notes: `user/` for every repository, `projects/<repository>/` for each one |
+| `~/.config/lcode/commands/`, `~/.config/lcode/skills/` | Your [commands and skills](commands.md) (a repository's go in `.lcode/`) |
+| `~/.local/state/lcode/extensions-approved.json` | Repositories whose commands, skills and agents you approved |
 | `~/.config/lcode/agents/` | Your [custom agents](agents.md#custom-agents) (a repository's go in `.lcode/agents/`) |
 | `~/.local/state/lcode/limits.json` | Context sizes that ran out of GPU memory on this machine (safe to delete) |
 

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/docs/how-it-works.md

@@ -85,10 +85,13 @@ the Ollama server you configure, it only contacts the web when the model searche
 | `agent.py` | System prompt, streaming, tool loop, compaction, sessions |
 | `tools.py` | Tool schemas and implementations |
 | `permissions.py` | Approval prompts and the read-only allowlist |
+| `servers/` | The MCP servers lcode ships for services without one: Encord, Valohai |
 | `mcp/` | MCP client: stdio and HTTP transports, OAuth sign-in, server settings, the catalog, `lcode mcp` |
 | `bench.py` | `lcode bench`: the benchmark tasks, their checks and the reports |
 | `vision.py` | Looking at images with a model that can see |
 | `subagents.py` | Subagents: agent types, running them (also in parallel), worktrees for workers |
+| `extensions.py` | Custom commands and skills, and approving a repository's own |
+| `frontmatter.py` | The `---` headers of notes, agents, commands and skills |
 | `planning.py` | Plan mode: what it allows, presenting a plan and approving it |
 | `memory.py` | Notes that carry over between sessions, and the end-of-session check |
 | `sandbox.py` | The optional container for shell commands |

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/docs/mcp.md

@@ -35,13 +35,16 @@ and find the code for the top one."*
 | `kubernetes` | Pods, deployments, logs and events, read-only | `npx` and a kubeconfig |
 | `linear` | Issues, projects and cycles | a Linear account (browser sign-in) |
 | `notion` | Pages and databases | a Notion account (browser sign-in) |
+| `metabase` | Explore your data and ask questions through Metabase's semantic layer | Metabase 60 or later with MCP on ([below](#metabase)) |
+| `encord` | Projects, datasets, ontologies, labeling progress, tasks and labels, read-only | `uvx`, an SSH key registered in Encord ([below](#encord)) |
+| `valohai` | ML executions with their logs, metrics and outputs, and pipelines, read-only | `uvx`, a Valohai API token ([below](#valohai)) |
 
 `npx` comes with [Node.js](https://nodejs.org) (18 or newer) and `uvx` with
 [uv](https://docs.astral.sh/uv/getting-started/installation/). `lcode mcp catalog` shows what's missing
 on your machine.
 
 Servers that can change things start read-only where the server supports it (`aws`, `postgres`,
-`kubernetes`); the setup note tells you which setting to change to allow writes.
+`kubernetes`, `encord`, `valohai`); the setup note tells you which setting to change to allow writes.
 
 ### Signing in
 
@@ -134,6 +137,51 @@ size, prompt), which can take several minutes of trial and error. Once an image
 lcode to save that workflow in your project (for example `assets/icon.workflow.json`) and reuse it:
 later images are a single `run_workflow` call.
 
+### Metabase
+
+Metabase has its own MCP server inside every instance (Metabase 60 and later), at
+`/api/metabase-mcp`. An admin switches it on under **Admin > AI > MCP**. Then:
+
+```bash
+lcode mcp add metabase        # asks for your Metabase address, then signs in in the browser
+```
+
+You sign in with your Metabase account, and the model sees exactly the data your Metabase
+permissions allow. See [Metabase's MCP docs](https://www.metabase.com/docs/latest/ai/mcp).
+
+### Encord
+
+Encord has no MCP server of its own, so lcode ships one: `lcode-mcp-encord`, built on the Encord SDK
+and run with `uvx --from "lcode-cli[encord]"`. It signs in with an SSH key that you register in
+Encord under **Settings > Public keys**; `lcode mcp add encord` asks for the key file's path.
+
+| Tool | |
+|---|---|
+| `list_projects`, `list_datasets` | What you can see |
+| `get_project`, `get_ontology` | A project's datasets, ontology classes and workflow stages |
+| `workflow_progress` | How many tasks are in each workflow stage, by status |
+| `list_tasks` | Data units with their stage, status and last edit, filtered by stage or title |
+| `get_labels` | The labels on one data unit: counts per class and the label JSON |
+| `assign_task`, `set_priority` | Only with `--allow-writes` in the server's `args` in `mcp.json` |
+
+### Valohai
+
+Valohai has no MCP server of its own either, so lcode ships `lcode-mcp-valohai`, which talks to
+Valohai's REST API. It needs an API token (**My Profile > Authentication > Manage tokens**), and the
+address of a self-hosted installation if you use one; `lcode mcp add valohai` asks for both.
+
+| Tool | |
+|---|---|
+| `list_projects`, `list_pipelines` | Projects and their pipelines |
+| `list_executions`, `get_execution` | Executions with their status, parameters, metrics, outputs and errors |
+| `get_execution_logs` | The last lines of an execution's log, optionally only stderr |
+| `list_outputs` | The files an execution produced, with `datum://` URIs to use as inputs |
+| `compare_executions` | Metrics and differing parameters of several executions side by side |
+| `start_execution`, `stop_execution` | Only with `--allow-writes` in the server's `args` in `mcp.json` |
+
+Both servers are ordinary MCP servers: other MCP clients can use them too, for example
+`uvx --from lcode-cli lcode-mcp-valohai` with `VALOHAI_TOKEN` set.
+
 ## Adding your own servers
 
 Any MCP server works. For a remote server, give its URL; for a local one, the command that starts it:

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/docs/quickstart.md

@@ -12,7 +12,7 @@ lcode
 
 ```text
 ╭──────────────────────────────────────────────╮
-│ lcode v0.9.0 — local coding agent            │
+│ lcode v0.11.0 — local coding agent           │
 │                                              │
 │ model    lcode-qwen3.6-35b                   │
 │ context  256K tokens                         │

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/docs/usage.md

@@ -59,6 +59,7 @@ reasoning is on.
 | `/undo` | Undo the file changes of the last request ([details](#undo-and-checkpoints)) |
 | `/rewind [N]` | Go back to before request N: its files, and optionally the conversation |
 | `/checkpoints` | List the requests that changed files, and which files |
+| `/name [args]` | Run one of your [commands or skills](commands.md); `/help` lists them |
 | `/agents [N]` | [Subagent](agents.md) types, and what this session's subagents did |
 | `/remember [-g] TEXT` | Save a [note](memory.md) for later sessions (`-g`: for every repository) |
 | `/memory [show\|edit\|delete N]` | The [notes](memory.md) lcode remembers |
@@ -92,6 +93,7 @@ reasoning is on.
 | `view_image` | Look at an image: a model that can see describes it ([Images](#images)) |
 | `agent` | Hand a task to a [subagent](agents.md) with its own context; only its report comes back |
 | `memory` | Save, update or delete [notes](memory.md) that later sessions load |
+| `skill` | Load a [skill](commands.md#skills)'s instructions when a task matches it |
 | `present_plan` | In [plan mode](#plan-mode): show the plan and ask for approval |
 
 lcode refuses to edit a file the model hasn't read in the session, or one that changed on disk since
@@ -276,6 +278,9 @@ At startup lcode reads `AGENTS.md` (or `LCODE.md`, or `CLAUDE.md`) from the work
 adds it to the model's instructions. Use it for build and test commands, architecture notes and
 conventions. `/init` writes a first version for you.
 
+Instructions that are only needed for some tasks fit better in a [command or skill](commands.md),
+which costs no context until it's used.
+
 What doesn't belong in `AGENTS.md` but should carry over, such as your corrections and preferences,
 goes into lcode's [memory](memory.md): short notes the model, you (`/remember`) or a short check at
 the end of a session save, and that every later session in the repository loads.

lcode_cli-0.11.0/examples/README.md

@@ -0,0 +1,17 @@
+# Examples
+
+Ready-made extensions for lcode. Copy them into a repository (or into `~/.config/lcode/` to use
+them everywhere):
+
+| Example | Copy to | Use it |
+|---|---|---|
+| [`commands/review.md`](commands/review.md) | `.lcode/commands/review.md` | `/review` or `/review the parser` |
+| [`skills/commit-message/`](skills/commit-message/) | `.lcode/skills/commit-message/` | ask for a commit message, or `/commit-message` |
+
+```bash
+mkdir -p .lcode/commands .lcode/skills
+cp examples/commands/review.md .lcode/commands/
+cp -r examples/skills/commit-message .lcode/skills/
+```
+
+See [Commands and skills](https://nasser1941.github.io/lcode/commands/) for the format.

lcode_cli-0.11.0/examples/commands/review.md

@@ -0,0 +1,15 @@
+---
+description: review the uncommitted changes for bugs and missing tests
+argument-hint: "[path or what to focus on]"
+allowed-tools: read_file grep glob list_dir bash
+---
+Review the uncommitted changes in this repository. $ARGUMENTS
+
+Run `git diff` and `git diff --cached` to see them, and read the code around them where needed.
+
+Report, most important first:
+1. Bugs: wrong behavior, unhandled errors and edge cases, with `path:line`.
+2. Missing or weak tests for the changed behavior.
+3. Anything that doesn't match the code around it.
+
+Don't change any files.

lcode_cli-0.11.0/examples/skills/commit-message/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: commit-message
+description: Writes a git commit message for the staged changes, in the style the repository already uses. Use when the user asks for a commit message, or asks you to commit their changes.
+license: MIT
+---
+# Commit messages
+
+1. Run `scripts/staged.sh` from this skill's folder (with its absolute path). It prints the staged
+   files and the subjects of the last 15 commits.
+2. If nothing is staged, tell the user and stop. Don't stage files yourself unless they asked.
+3. Read the staged diff (`git diff --cached`) of the files that matter.
+4. Match the style of the recent subjects: imperative mood or not, prefixes such as `feat:` or
+   `fix(scope):` only if the repository uses them, capitalization and length.
+5. Write a subject under 72 characters that says what the change does. For anything but a trivial
+   change, add a blank line and a short body that says why, wrapped at 72 characters.
+6. Show the message. Commit only if the user asked you to: `git commit -F -` with the message on
+   standard input.

lcode_cli-0.11.0/examples/skills/commit-message/scripts/staged.sh

@@ -0,0 +1,8 @@
+#!/bin/sh
+# The staged changes and recent commit subjects, for a commit message in the repository's style.
+set -e
+echo "Staged files:"
+git diff --cached --stat
+echo
+echo "Recent commit subjects:"
+git log --format='%s' -15

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/mkdocs.yml

@@ -94,6 +94,7 @@ nav:
       - Using lcode: usage.md
       - Memory: memory.md
       - Subagents: agents.md
+      - Commands and skills: commands.md
       - Models & context windows: models.md
       - Benchmarking models: bench.md
       - MCP servers: mcp.md

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/pyproject.toml

@@ -35,6 +35,9 @@ dependencies = [
     "tomli>=2.0; python_version < '3.11'",
 ]
 
+[project.optional-dependencies]
+encord = ["encord>=0.1.200"]  # for lcode-mcp-encord
+
 [project.urls]
 Homepage = "https://nasser1941.github.io/lcode/"
 Documentation = "https://nasser1941.github.io/lcode/"
@@ -44,6 +47,8 @@ Changelog = "https://github.com/nasser1941/lcode/blob/main/CHANGELOG.md"
 
 [project.scripts]
 lcode = "lcode.cli:main"
+lcode-mcp-valohai = "lcode.servers.valohai:main"
+lcode-mcp-encord = "lcode.servers.encord:main"
 
 [dependency-groups]
 dev = ["pytest>=8", "ruff>=0.6"]
@@ -72,6 +77,7 @@ ignore = [
 "src/lcode/memory.py" = ["E501"]
 "src/lcode/subagents.py" = ["E501"]
 "src/lcode/planning.py" = ["E501"]
+"src/lcode/extensions.py" = ["E501"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/src/lcode/__init__.py

@@ -1,3 +1,3 @@
 """lcode — a local-first terminal coding agent powered by open-weight models via Ollama."""
 
-__version__ = "0.9.0"
+__version__ = "0.11.0"

{lcode_cli-0.9.0 → lcode_cli-0.11.0}/src/lcode/agent.py

@@ -21,7 +21,7 @@ from rich.markup import escape
 from rich.panel import Panel
 from rich.text import Text
 
-from lcode import catalog, limits, planning, sessions, subagents, vision, web
+from lcode import catalog, extensions, limits, planning, sessions, subagents, vision, web
 from lcode import memory as memory_notes
 from lcode.checkpoints import Checkpoints
 from lcode.config import format_tokens
@@ -78,7 +78,7 @@ SYSTEM_PROMPT = """You are lcode, an autonomous software-engineering agent runni
 
 # Top-level layout of the working directory
 {tree}
-{web}{agents}{project}{notes}"""
+{web}{agents}{skills}{project}{notes}"""
 
 WEB_PROMPT = """
 # Web access
@@ -171,6 +171,8 @@ class Settings:
     vision_model: str = "auto"  # auto, off or an Ollama model that can see images
     memory: str = "off"  # off, ask or auto: notes that carry over to later sessions (lcode.memory)
     subagents: bool = False  # the agent tool (lcode.subagents)
+    trust_project: bool = False  # use the repository's own commands, skills and agents (lcode.extensions)
+    skills: str = "off"  # all, lcode (only lcode's own skill folders) or off
     max_parallel_agents: int = 1
 
 
@@ -200,6 +202,8 @@ class Agent:
         self._agent_types: tuple[Path, dict[str, subagents.AgentType], list[str]] | None = None
         self.agent_runs: list[subagents.Record] = []  # subagents run in this session, for /agents
         self.plan = ""  # the plan the user approved; kept through compaction
+        self._extensions: tuple[Path, extensions.Extensions] | None = None
+        self.skills_loaded: set[str] = set()  # skills whose instructions are in the conversation
         # Set on subagents (see lcode.subagents):
         self.allowed_tools: set[str] | None = None  # None: every tool
         self.read_only = False  # only read-only shell commands
@@ -236,8 +240,15 @@ class Agent:
             notes=self.memory().prompt(self.settings.context) if self.settings.memory != "off" else "",
             web=self.web_prompt(),
             agents=self.agents_prompt(),
+            skills=extensions.skills_prompt(self.extensions().skills, self.settings.context),
         )
 
+    def extensions(self) -> extensions.Extensions:
+        """Custom commands and skills for the current folder (a repository's only once approved)."""
+        if self._extensions is None or self._extensions[0] != self.cwd:
+            self._extensions = (self.cwd, extensions.load(self.cwd, self.settings.trust_project, self.settings.skills))
+        return self._extensions[1]
+
     def agents_prompt(self) -> str:
         if not self.settings.subagents:
             return ""
@@ -252,7 +263,7 @@ class Agent:
     def agent_types(self) -> dict[str, subagents.AgentType]:
         """Built-in and custom agent types for the current folder."""
         if self._agent_types is None or self._agent_types[0] != self.cwd:
-            types, problems = subagents.load_types(self.cwd)
+            types, problems = subagents.load_types(self.cwd, self.settings.trust_project)
             self._agent_types = (self.cwd, types, problems)
         return self._agent_types[1]
 
@@ -290,6 +301,8 @@ class Agent:
             schemas.append(subagents.schema(self.agent_types(), self.settings.max_parallel_agents))
         if self.planning():
             schemas.append(PRESENT_PLAN_SCHEMA)
+        if self.extensions().skills:
+            schemas.append(extensions.schema(self.extensions().skills))
         if self.mcp:
             schemas += self.mcp.schemas(self.settings.context)
         if self.allowed_tools is not None:
@@ -409,6 +422,7 @@ class Agent:
 
     def new_session(self) -> None:
         self.reset()
+        self.skills_loaded.clear()
         self.session_id = self.new_session_id()
         self.session_name = ""
         self.session_title = ""
@@ -606,6 +620,8 @@ class Agent:
             return f"list_dir({args.get('path', '.')})"
         if name == "memory":
             return f"memory({' '.join(str(args.get(k) or '') for k in ('action', 'name')).strip()})"
+        if name == "skill":
+            return f"skill({args.get('name', '')})"
         if name == "agent":
             return f"agent({args.get('type', '')}: {args.get('description') or str(args.get('task', ''))[:50]})"
         if name == "bash":
@@ -787,6 +803,12 @@ class Agent:
         ]
         if self.plan:  # the approved plan stays word for word
             self.messages[1]["content"] += f"\n\n[The plan the user approved; keep following it]\n\n{self.plan}"
+        if self.skills_loaded:  # their instructions were in the old messages: load them again when needed
+            names = ", ".join(sorted(self.skills_loaded))
+            self.messages[1]["content"] += (
+                f"\n\n[Skills in use before the summary: {names}. Load them again with the skill tool if you still need them.]"
+            )
+            self.skills_loaded.clear()
         self.ctx_used = sum(len(m["content"]) for m in self.messages) // 3
         self.reflected = len(self.messages)
         self.console.print(Panel(Markdown(summary), title="Compacted summary", border_style="blue"))