mini-coder 0.0.17 β†’ 0.0.19

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (9) hide show
  1. package/README.md +23 -27
  2. package/dist/mc.js +4507 -4104
  3. package/docs/configs.md +40 -8
  4. package/docs/custom-agents.md +14 -13
  5. package/docs/custom-commands.md +4 -9
  6. package/docs/mini-coder.1.md +158 -0
  7. package/docs/skills.md +5 -3
  8. package/package.json +1 -1
  9. package/docs/chatgpt-subscription-auth.md +0 -68
package/README.md CHANGED
@@ -6,6 +6,8 @@
6
6
 
7
7
  > _Small. Fast. Gets out of your way._
8
8
 
9
+ [πŸ“– Read the Full Manual](https://sacenox.github.io/mini-coder/)
10
+
9
11
  Hey there! I'm **mini-coder** β€” a CLI coding agent built for developers who want a sharp tool, not a bloated IDE plugin. Think of me as the pocket knife of AI coding assistants: lightweight, reliable, and always ready.
10
12
 
11
13
  ---
@@ -16,16 +18,7 @@ I'm `mc` β€” your new terminal companion. I live in your shell, speak to large l
16
18
 
17
19
  I was built with a simple philosophy: **dev flow first**. No slow startup. No clunky GUI. No vendor lock-in. Just you, your terminal, and an AI that keeps up.
18
20
 
19
- ```
20
- $ mc
21
- β”Œβ”€ mini-coder ──────────────────────────────────────────┐
22
- β”‚ What would you like to work on today? β”‚
23
- β”‚ β”‚
24
- β”‚ > _ β”‚
25
- β”‚ β”‚
26
- β”‚ [zen/claude-sonnet-4-6] [~/src/my-project] [main] ...β”‚
27
- β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
28
- ```
21
+ ![Minicoder Preview](./assets/preview.gif)
29
22
 
30
23
  ---
31
24
 
@@ -56,10 +49,10 @@ Need more firepower? I connect to **MCP servers** over HTTP or stdio β€” bolt on
56
49
  - **Built-in web search** β€” set `EXA_API_KEY` and I expose `webSearch` + `webContent` tools.
57
50
  - **Session memory** β€” conversations are saved in a local SQLite database. Resume where you left off with `-c` or pick a specific session with `-r <id>`.
58
51
  - **Shell integration** β€” prefix with `!` to run shell commands inline. Use `@` to reference files in your prompt (with Tab completion).
59
- - **Slash commands** β€” `/model` or `/models` to list/switch models, `/model effort <low|medium|high|xhigh|off>` for reasoning effort, `/plan` for read-only thinking mode, `/ralph` for autonomous looping, `/review` for a code review (global custom command, auto-created at `~/.agents/commands/review.md`), `/agent [name]` to set or clear an active primary agent, `/undo` to roll back a turn, `/new` for a clean session, `/mcp list|add|remove` to manage MCP servers, and `/exit` (`/quit`, `/q`) to leave. See all with `/help`.
52
+ - **Slash commands** β€” `/model` or `/models` to list/switch models, `/model effort <low|medium|high|xhigh|off>` for reasoning effort, `/reasoning [on|off]` to toggle reasoning display, `/context` to inspect or tune pruning/tool-result caps, `/plan` for read-only thinking mode, `/ralph` for autonomous looping, `/review` for a code review (global custom command, auto-created at `~/.agents/commands/review.md`), `/agent [name]` to set or clear an active primary agent, `/undo` to roll back a turn, `/new` for a clean session, `/mcp list|add|remove` to manage MCP servers, and `/exit` (`/quit`, `/q`) to leave. See all with `/help`.
60
53
 
61
54
  - **Custom commands** β€” drop a `.md` file in `.agents/commands/` and it becomes a `/command`. Claude-compatible `.claude/commands/` works too. Supports argument placeholders (`$ARGUMENTS`, `$1`…`$9`) and shell interpolation (`` !`cmd` ``). Global commands live in `~/.agents/commands/` and `~/.claude/commands/`. Custom commands take precedence over built-ins. β†’ [docs/custom-commands.md](docs/custom-commands.md)
62
- - **Custom agents** β€” drop a `.md` file in `.agents/agents/` (or `~/.agents/agents/` globally) and reference it with `@agent-name` in your prompt. The agent runs in its own context window with a custom system prompt and optional model override. β†’ [docs/custom-agents.md](docs/custom-agents.md)
55
+ - **Custom agents** β€” drop a `.md` file in `.agents/agents/` or `.claude/agents/` (or `~/.agents/agents/` / `~/.claude/agents/` globally) and activate it with `/agent [name]`. Agent definitions are also exposed to subagent delegation unless `mode: primary`. `@agent-name` is supported for completion and is a useful prompt convention. β†’ [docs/custom-agents.md](docs/custom-agents.md)
63
56
  - **Skills** β€” place a `SKILL.md` in `.agents/skills/<name>/` and inject it into any prompt with `@skill-name`. Claude-compatible `.claude/skills/<name>/SKILL.md` works too. Skills are _never_ auto-loaded β€” always explicit. β†’ [docs/skills.md](docs/skills.md)
64
57
  - **Post-tool hooks** β€” drop an executable at `.agents/hooks/post-<tool>` (or `~/.agents/hooks/post-<tool>` globally) and I'll run it after matching built-in tool calls. β†’ [docs/tool-hooks.md](docs/tool-hooks.md)
65
58
  - **Beautiful, minimal output** β€” diffs for edits, formatted trees for file searches, a live status bar with model, git branch, and token counts.
@@ -73,28 +66,32 @@ Need more firepower? I connect to **MCP servers** over HTTP or stdio β€” bolt on
73
66
  - **I'm tiny but mighty.** The whole runtime is [Bun.js](https://bun.com) β€” fast startup, native TypeScript, and a built-in SQLite driver.
74
67
  - **I respect existing conventions.** Hook scripts live in `.agents/hooks/`, context in `AGENTS.md` or `CLAUDE.md`, commands in `.agents/commands/`, agents in `.agents/agents/`, skills in `.agents/skills/` β€” I follow the ecosystem instead of inventing new standards.
75
68
  - **I spin while I think.** ⠋⠙⠹⠸⠼⠴⠦⠧⠇⠏ (It's the little things.)
76
- - **I can clone myself.** The `subagent` tool lets me spin up parallel instances of myself to tackle independent subtasks simultaneously. Divide and conquer! (Up to 3 levels deep.)
69
+ - **I can clone myself.** The `subagent` tool lets me spin up parallel instances of myself to tackle independent subtasks simultaneously. Divide and conquer! (Up to 10 levels deep.)
77
70
 
78
71
  ---
79
72
 
80
73
  ## πŸ“ Config folders
81
74
 
82
- I follow the [`.agents` convention](https://github.com/agentsmd/agents) β€” the shared standard across AI coding tools β€” and I also speak Claude Code's `.claude` format for **commands** and **skills**. Best of both worlds.
75
+ I follow the [`.agents` convention](https://github.com/agentsmd/agents) β€” the shared standard across AI coding tools β€” and I also understand `.claude` layouts for **commands**, **skills**, and **agents**.
83
76
 
84
- | Path | What it does |
85
- | -------------------------------- | ------------------------------------------------- |
86
- | `.agents/commands/*.md` | Custom slash commands (`/name`) |
87
- | `.claude/commands/*.md` | Claude-compatible custom commands |
88
- | `.agents/agents/*.md` | Custom agents (`@name`) |
89
- | `.agents/skills/<name>/SKILL.md` | Reusable skill instructions (`@name`) |
90
- | `.claude/skills/<name>/SKILL.md` | Claude-compatible skills |
91
- | `.agents/hooks/post-<tool>` | Scripts run after supported built-in tool calls |
92
- | `AGENTS.md` | Project context injected into every system prompt |
93
- | `CLAUDE.md` | Fallback project context if `AGENTS.md` is absent |
94
- | `~/.agents/AGENTS.md` | Global fallback context |
77
+ | Path | What it does |
78
+ | -------------------------------- | ----------------------------------------------------- |
79
+ | `.agents/commands/*.md` | Custom slash commands (`/name`) |
80
+ | `.claude/commands/*.md` | Claude-compatible custom commands |
81
+ | `.agents/agents/*.md` | Custom agents |
82
+ | `.claude/agents/*.md` | Alternate `.claude` path for custom agents |
83
+ | `.agents/skills/<name>/SKILL.md` | Reusable skill instructions (`@name`) |
84
+ | `.claude/skills/<name>/SKILL.md` | Claude-compatible skills |
85
+ | `.agents/hooks/post-<tool>` | Scripts run after supported built-in tool calls |
86
+ | `.agents/AGENTS.md` | Preferred local project context |
87
+ | `CLAUDE.md` | Local fallback context if `.agents/AGENTS.md` is absent |
88
+ | `AGENTS.md` | Local fallback context if `.agents/AGENTS.md` and `CLAUDE.md` are absent |
89
+ | `~/.agents/AGENTS.md` | Preferred global context, prepended before local context |
90
+ | `~/.agents/CLAUDE.md` | Global fallback context if `~/.agents/AGENTS.md` is absent |
95
91
 
92
+ Global commands, agents, and skills also work from `~/.agents/...` and `~/.claude/...`.
96
93
 
97
- The pecking order is straightforward: local beats global, and `.agents` beats `.claude` at the same scope. Worth noting: custom agents are mini-coder-only β€” `.claude` compatibility is for commands and skills only. β†’ [docs/configs.md](docs/configs.md)
94
+ For commands, skills, and agents: local overrides global, and `.agents` overrides `.claude` at the same scope. Context files are combined differently: global context is injected first, then local context. β†’ [docs/configs.md](docs/configs.md)
98
95
 
99
96
  ---
100
97
 
@@ -148,7 +145,6 @@ Everything I remember lives in `~/.config/mini-coder/` β€” here's what I'm holdi
148
145
  - `sessions.db` β€” your full session history, `/undo` snapshots, MCP server config, and model metadata, all in one tidy SQLite file
149
146
  - `api.log` β€” a request/response log for every provider call this run, if you want to peek under the hood
150
147
  - `errors.log` β€” anything that went sideways, caught and written down so you can actually debug it
151
- - `AGENTS.md` β€” your global context fallback, quietly injected whenever a repo doesn't bring its own `AGENTS.md` or `CLAUDE.md`
152
148
 
153
149
  ---
154
150