xonecas.io
64875
Mc

mini-coder / commit 910f91c

docs: trim custom-agents.md to agents only

Sean2026-02-25 910f91cabea589339ca09bb3a078abbf5a94f315 parent 9560714

1 file changed

docs/custom-agents.md+10−79
@@ -1,15 +1,9 @@
1-# Custom Agents and Skills
2-
3-Two ways to extend mini-coder with reusable AI behaviour via `@` references.
4-
5----
6-
7-## Agents
1+# Custom Agents
82
93 An agent is a subagent with a custom system prompt and optional model override.
104 Use `@agent-name` anywhere in your prompt to route the message through it.
115
12-### Where to put them
6+## Where to put them
137
148 | Location | Scope |
159 |---|---|
@@ -18,7 +12,7 @@ Use `@agent-name` anywhere in your prompt to route the message through it.
1812
1913 Local agents override global ones with the same name.
2014
21-### Create an agent
15+## Create an agent
2216
2317 The filename becomes the agent name.
2418
@@ -46,18 +40,7 @@ The rest of the message (everything except the `@reviewer` token) becomes
4640 the prompt. The agent runs in its own context window and returns its output
4741 into the conversation.
4842
49-### Combining with skills
50-
51-Skills and files are resolved before the agent fires, so you can mix them:
52-
53-```
54-@reviewer @src/auth/session.ts check this file for issues
55-```
56-
57-The file content is injected into the prompt, then the whole thing is sent
58-to the reviewer agent.
59-
60-### Frontmatter fields
43+## Frontmatter fields
6144
6245 | Field | Required | Description |
6346 |---|---|---|
@@ -66,74 +49,22 @@ to the reviewer agent.
6649
6750 The markdown body (after frontmatter) is the agent's system prompt.
6851
69----
70-
71-## Skills
72-
73-A skill is a reusable instruction file injected inline into your prompt.
74-Use `@skill-name` to load it — the LLM sees the skill content as context
75-before your message.
76-
77-### Where to put them
78-
79-Each skill is a folder containing a `SKILL.md`:
80-
81-| Location | Scope |
82-|---|---|
83-| `.agents/skills/<name>/SKILL.md` | Current repo only |
84-| `~/.agents/skills/<name>/SKILL.md` | All projects (global) |
85-
86-Local skills override global ones with the same name.
52+## Combining with files
8753
88-### Create a skill
89-
90-`.agents/skills/conventional-commits/SKILL.md`:
91-
92-```md
93----
94-name: conventional-commits
95-description: Conventional commit message format rules
96----
97-
98-# Conventional Commits
99-
100-All commit messages must follow this format:
101-
102- <type>(<scope>): <short summary>
103-
104-Types: feat, fix, docs, refactor, test, chore
105-- Summary is lowercase, no period at the end
106-- Breaking changes: add `!` after type, e.g. `feat!:`
107-- Body is optional, wrapped at 72 chars
108-```
109-
110-Then in the REPL:
54+`@file` references are resolved before the agent fires:
11155
11256 ```
113-@conventional-commits write a commit message for my staged changes
57+@reviewer @src/auth/session.ts check this file for issues
11458 ```
11559
116-The skill content is wrapped in `<skill name="…">…</skill>` tags and
117-prepended to your message before it's sent to the LLM.
118-
119-### Frontmatter fields
120-
121-| Field | Required | Description |
122-|---|---|---|
123-| `name` | No | Skill name for `@` reference. Defaults to folder name. |
124-| `description` | No | Shown in `/help`. Defaults to name. |
125-
126----
127-
12860 ## Tab completion
12961
130-Type `@` and press `Tab` to autocomplete. Skills and agents are listed
131-first, then local files — up to 10 results total.
62+Type `@` and press `Tab` to autocomplete agent names alongside files.
13263
133-## Listing available agents and skills
64+## Listing agents
13465
13566 ```
13667 /help
13768 ```
13869
139-Agents are shown in magenta, skills in yellow, tagged `(local)` or `(global)`.
70+Agents are listed in magenta, tagged `(local)` or `(global)`.