xonecas.io
64875
Mc

mini-coder / commit 21556e0

feat: consolidate everything into skills

xonecas2026-03-19 21556e0a32a2cdcf7f3647818034996354b93c5d parent 10ebd01

8 files changed

.agents/agents/blogger.md+0−43
@@ -1,43 +0,0 @@
1----
2-description: Writes blog posts drafts.
3-mode: subagent
4----
5-
6-# Blog Writer Agent
7-
8-You write short, personal, informal blog posts. Your output is a markdown draft only at the repo root.
9-
10-## Style
11-
12-- Personal, conversational, and informal. Write like you are talking to a friend.
13-- Use simple sentences, contractions, and first-person voice.
14-- Keep it punchy: around 500 words unless the topic demands less.
15-
16-## Inputs
17-
18-- If given a topic, research it using web search and fetch.
19-- If given resources (links or notes), use them as primary sources.
20-- Prefer the provided resources over outside sources when both exist.
21-
22-## Structure
23-
24-1. Hook: a short opening that pulls the reader in.
25-2. Main points: 2-4 short sections with clear headings.
26-3. Takeaway: a short closing that wraps the idea.
27-4. Sources: always list the sources you used.
28-
29-## Writing clearly and concisely
30-
31-- Eliminate repetition; do not say the same idea twice.
32-- Use straightforward language; cut unneeded words.
33-- Prefer specific and concrete words over general or abstract ones.
34-- Choose words for connotation as well as definition.
35-- Avoid jargon, slang, and cliches unless the audience expects them.
36-- Use figurative language sparingly; only when it adds clarity or energy.
37-
38-## Output format
39-
40-- Markdown only.
41-- Start with an H1 title.
42-- Use headings and short paragraphs.
43-- In a markdown file at repo root: `<title>.draft.md`
.agents/commands/n8n-blog-post.md+0−15
@@ -1,15 +0,0 @@
1----
2-description: Trigger the n8n workflow to create a blog post using title and content as seeds.
3-model: zen/claude-haiku-4-5
4-context: fork
5----
6-
7-
8-Arguments: $ARGUMENTS
9-
10-Make a GET cURL request to the URL in the `$N8N_BLOG_WEBHOOK_URL` env var with query string params `title` and `content`. Pass the values exactly as given — do not expand or rewrite the content.
11-
12-If `title` or `content` are not explicitly provided, infer them from the arguments given.
13-
14-Print the response body after the request completes.
15-
.agents/skills/idea-check/SKILL.md+1−0
@@ -1,4 +1,5 @@
11 ---
2+name: idea-check
23 description: Check the codebase for correctness acording to the original idea.
34 ---
45
.agents/skills/orc/SKILL.md+8−9
@@ -1,9 +1,9 @@
11 ---
2-description: Orchestrator — decomposes complex tasks and coordinates a fleet of subagents
3-mode: primary
2+name: orc
3+description: Orchestrator mode - decomposes complex tasks and coordinates a fleet of subagents
44 ---
55
6-You are in **Orchestration** mode, behave like an expert orchestration agent. Your superpower is breaking complex problems into well-scoped subtasks and delegating each to the right specialist subagent via the `subagent` tool.
6+You are in **Orchestration** mode, behave like an expert orchestration agent. Your superpower is breaking complex problems into well-scoped subtasks and delegating each via the `mc` shell tool to other agents.
77
88 ## Core principles
99
@@ -12,20 +12,20 @@ You are in **Orchestration** mode, behave like an expert orchestration agent. Yo
1212 - **Stay the coordinator.** You own the big picture. Subagents handle the details. Synthesise their results, resolve conflicts, and report back clearly.
1313 - **Parallelise when possible.** If two subtasks don't depend on each other, dispatch them concurrently.
1414 - **Fail fast.** If a subagent reports failure or returns unexpected output, stop and reassess before continuing.
15-- **Custom subagents**: Use these if appropriate, otherwise a normal subagent is preffered.
15+- **Custom agents**: Use these if appropriate, otherwise a normal agent is preffered.
1616
1717 ## How to orchestrate
1818
1919 1. Read the user's goal carefully.
2020 2. Identify the 2–5 discrete subtasks needed to complete it.
21-3. Write a tight, self-contained prompt for each — include all context the subagent needs; it has no shared memory with you.
22-4. Dispatch subagents (in parallel where safe) and capture their outputs.
23-5. Synthesise results. If something is missing or wrong, spawn a follow-up subagent to fix it.
21+3. Write a tight, self-contained prompt for each — include all context the agent needs; it has no shared memory with you.
22+4. Dispatch agents (in parallel where safe) and capture their outputs.
23+5. Synthesise results. If something is missing or wrong, spawn a follow-up agent to fix it.
2424 6. Report the final outcome clearly to the user.
2525
2626 ## Subagent prompt hygiene
2727
28-- Be explicit about _what the subagent should produce_ (a file, a code change, a summary, a decision).
28+- Be explicit about _what the agent should produce_ (a file, a code change, a summary, a decision).
2929 - Include relevant paths, constraints, and acceptance criteria in every prompt.
3030 - Never give a vague brief — ambiguity leads to rework and wasted tokens.
3131
@@ -33,4 +33,3 @@ You are in **Orchestration** mode, behave like an expert orchestration agent. Yo
3333
3434 - Trivial lookups or single-file reads: do them directly with your own tools.
3535 - Tasks that require continuous back-and-forth with the user: handle interactively.
36-- Secret or credential-sensitive work: handle yourself; never expose secrets in subagent prompts.
.agents/skills/release/SKILL.md+1−0
@@ -1,4 +1,5 @@
11 ---
2+name: release
23 description: Create a new tagged npm release (patch/minor/major)
34 ---
45
.agents/skills/ui-probe/SKILL.md+1−0
@@ -1,4 +1,5 @@
11 ---
2+name: ui-probe
23 description: Run one-shot mc sessions across all SDK paths, capture output, and write a UI/UX analysis report to UI-REPORT.md.
34 ---
45
TODO.md+1−2
@@ -1,8 +1,7 @@
11 # TODO
22
3-- Need to review our parity with opencode and claude code configs (skills, agents, and commands). Identify gaps and missing functionality. use online docs for both to assert functionality
3+- Codebase is hurting from fast iteration and adding/removing features as well as core fundamental changes. We need to do a large refactoring based on the updated idea and remove the extra complexity and fragments of all the experimentation we did with other features.
44 - CTRL+d hangs sometimes and doesn't exit.
5-- Codebase is hurting from fast iteration and adding/removing features as well as core fundamental changes.
65
76 ---
87
mini-coder-idea.md+39−26
@@ -9,8 +9,6 @@ A coding agent via a augmented shell prompt, small and fast that doesn't get in
99 - Codex: https://github.com/openai/codex Powerful and open source, focused on heavy open-ai integration
1010 - Opencode: https://opencode.ai/ The open source standard. Similar to oh-my-pi but with a different aesthetic
1111
12-We want to do our best to support their configs, try to find the common api and auto load them along with the community .agents conventions.
13-
1412 ## Philosophy:
1513
1614 **Fast and performant**, instant feedback shell like output. Performance first style second.
@@ -19,39 +17,54 @@ Very focused on dev flow, simple setup steps and fast to coding.
1917 Elegant output that focus on the conversation with the agent and their actions. Ensure an accurate cronological conversation log that is very readable for the user. Keep a visible hierchy of actions -> results and assistant reasoning and responses.
2018 Accurate and reliable and fast core set of features.
2119 Community oriented, all of the inspirations have their own dotfile format, try to follow the existing
22-conventions and not introduce more specs. (`.agents` / `AGENTS.md`, while also supporting adjacent conventions like `.claude`)
20+conventions and not introduce more specs. We want to do our best to support and autodiscover community config standards:
21+
22+- AGENTS.md -> https://agents.md/
23+ - CLAUDE.md (same as AGENTS.md)
24+- Skills -> https://agentskills.io/client-implementation/adding-skills-support
25+ - Claude skills too. They claim to follow the spec, we should only need to discover them too.
2326
2427 ## Features:
2528
2629 - Auto discovery of providers via ENV (Example: OPENCODE_API_KEY), or local servers (Example: ollama)
30+ - `/login` shows OAuth login status. `/login <provider>` starts browser-based OAuth login. `/logout <provider>` clears saved tokens. Currently supports Anthropic. (Both pi and opencode support this too)
31+ - `/model` (alias `/models`) command allows the user to pick a model from connected providers. As well as thinking effort for the model if supported. Selection persists accross sessions. Must have autocomplete support for ease of use when changing models
32+
2733 - Session management and command to create new/resume/list with local sqlite file.
28-- Rich line editing/history/image paste
29-- Seamless shell integration with `!` in prompt input.
30-- Reference files and skills from the working directory and global configs with `@` in prompt input, plus autocomplete for files, skills, to include in the prompt. Skills should have their respective tools and implementation to match other coding agents
31-- Press `ESC` at any point during an assistant response to interrupt it: the partial response is preserved in history with an interrupt stub appended (so the LLM retains context), and the user is returned to the prompt silently. `ctrl+c` exits forcefully. `ctrl+d` (EOF) gracefully exits.
32-- Elegantly handles hitting max context size for the model using regular pruning.
33-- No max steps or max tool calls. user can interrupt, this is not needed.
34-- Support prompt caching via the used sdks.
35-- Feature parity with community configs like custom agents, skill and commands.
36-- Shell-first tool surface for LLMs: `shell`, `listSkills`, and `readSkill`, plus connected MCP tools and optional web tools when configured. Keep the core surface small and easy to use so it actually reduces friction for the LLMs.
37-- File work should follow a simple flow: inspect with shell, mutate with `mc-edit`, verify with shell.
38-- Large shell outputs should be truncated automatically for the llm, to avoid context explosions and encourage targetted reads.
39-- `mc-edit` should stay narrow and reliable: exact-text edits only, deterministic failures on stale or ambiguous state, diff and machine-friendly output while staying human readable.
40-- Optional `webSearch` and `webContent` tools when `EXA_API_KEY` is set.
41-- Commands in CLI prompt:
42- - `/model` (alias `/models`) command allows the user to pick a model from connected providers. As well as thinking effort for the model if supported. Selection persists accross sessions.
34+ - `/session` command to interactively manage sessions as well as cli flags.
35+ - `/new` starts a new session with clean context. Clean UI and fresh session display
36+
37+- Enriched user prompt:
38+ - Rich line editing/history/image paste
39+ - Seamless shell integration with `!` in prompt input. Runs command in subprocess and sends the output to the llm as user message.
40+ - Reference skills from the working directory and global configs with `/` in prompt input, plus autocomplete for skills to include in the prompt.
41+ - Press `ESC` at any point during an assistant response to interrupt it: the partial response is preserved in history with an interrupt stub appended (so the LLM retains context), and the user is returned to the prompt silently. `ctrl+c` exits forcefully. `ctrl+d` (EOF) gracefully exits.
42+ - Image support in prompt input, including pasted image data URLs and pasted image file paths.
43+ - Shell like autocomplete for filepaths, `@` embeds a file into the prompt and autocompletes filepaths
44+
45+- Context handling:
46+ - Elegantly handles hitting max context size for the model using regular pruning.
47+ - No max steps or max tool calls. user can interrupt, this is not needed.
48+ - Support prompt caching via the used sdks.
49+ - Rolling context pruning with a balanced default. (Must not break caching!)
50+ - Recover from errors returning the user to the prompt with clear messaging
4351 - `/undo` removes the last turn from conversation history, it does not restore filesystem state.
52+
53+- Shell-first tool surface for LLMs: `shell`, `listSkills`, and `readSkill`, plus connected MCP tools and optional web tools when configured. Keep the core surface small and easy to use so it actually reduces friction for the LLMs.
54+ - File work should follow a simple flow: inspect with shell, mutate with `mc-edit`, verify with shell.
55+ - Large shell outputs should be truncated automatically for the llm, to avoid context explosions and encourage targetted reads.
56+ - `mc-edit` should stay narrow and reliable: exact-text edits only, deterministic failures on stale or ambiguous state, diff and machine-friendly output while staying human readable.
57+ - Optional `webSearch` and `webContent` tools when `EXA_API_KEY` is set.
58+ - Cross model system prompt with clear descriptions of the expected dev flow and guidance as a code agent focused on shell first.
59+
60+-Other Commands in CLI prompt:
4461 - `/reasoning` toggles display of model reasoning output.
4562 - `/verbose` toggles output truncation. Tuncates large outputs keeping start and end sections and truncating the rest when verbose is off. This controls truncation for the user output, it's a visibility UI concern
46- - `/context` configures context pruning and tool-result caps.
47- - `/review` reviews recent changes via a global custom command installed at app start (`~/.agents/commands/review.md`), and can be customized or shadowed locally.
48- - `/agent` sets or clears the active agent.
49- - `/mcp` list/add/remove mcp servers. servers are stored in sqlite
50- - `/login` shows OAuth login status. `/login <provider>` starts browser-based OAuth login. `/logout <provider>` clears saved tokens. Currently supports Anthropic.
51- - `/new` starts a new session with clean context. Clean UI and fresh session display
63+ - `/review` reviews recent changes via a global custom skill installed at app start (`~/.agents/skills/review.md`), and can be customized or shadowed locally.
64+
5265 - Connect to MCP servers over Streamable HTTP / SSE fallback or stdio.
53-- Image support in prompt input, including pasted image data URLs and pasted image file paths.
54-- Excellent auto complete for all commands, subtituitions. The user should also be able to reference files with autocomplete wihtout including them into the prompt like `@` does with TAB
66+ - `/mcp` list/add/remove mcp servers. servers are stored in sqlite
67+
5568
5669 ## UI/Output