scout

Name: scout
Author: Rune-kit

80stars21forks

How to install scout?

rune-kit/rune/scout

$npx -y skills add Rune-kit/rune --skill scout

Installs into the current project.

Summary

Fast codebase scanner. Use when any skill needs codebase context. Finds files, patterns, dependencies, project structure. Pure read-only — never modifies files.

Files · 1

View on GitHub

SKILL.md

1	# scout
2
3	Fast, lightweight codebase scanning. Scout is the eyes of the Rune ecosystem.
4
5	## Instructions
6
7	When invoked, perform these steps:
8
9	### Phase 1: Structure Scan
10
11	Map the project layout:
12
13	1. Use `Glob` with `*/` to understand directory structure
14	2. Use `Bash` to run `ls` on key directories (root, src, lib, app)
15	3. Identify framework by detecting these files:
16	- `package.json` → Node.js/TypeScript
17	- `Cargo.toml` → Rust
18	- `pyproject.toml` / `setup.py` → Python
19	- `go.mod` → Go
20	- `pom.xml` / `build.gradle` → Java
21
22	```
23	TodoWrite: [
24	{ content: "Scan project structure", status: "in_progress" },
25	{ content: "Run targeted file search", status: "pending" },
26	{ content: "Map dependencies", status: "pending" },
27	{ content: "Detect conventions", status: "pending" },
28	{ content: "Generate codebase map (if full scan)", status: "pending" },
29	{ content: "Generate scout report", status: "pending" }
30	]
31	```
32
33	### Phase 2: Targeted Search (Search-First)
34
35	Search-first principle: Before building anything new, scout checks if a solution already exists — in the codebase, in package registries, or in available MCP servers.
36
37	Adopt / Extend / Compose / Build decision matrix:
38
39	When scout finds the caller's target domain, classify the situation:
40
41	```
42	ADOPT — Exact match exists (in codebase, npm, PyPI, MCP). Use as-is.
43	EXTEND — Partial match exists. Extend/configure existing solution.
44	COMPOSE — Multiple pieces exist. Wire them together.
45	BUILD — Nothing suitable exists. Build from scratch.
46	```
47
48	Report the classification to the calling skill. This informs Phase 2 (PLAN) in cook — ADOPT and EXTEND are vastly cheaper than BUILD.
49
50	Quick checks before deep search:
51	1. `Grep` the codebase for existing implementations of the target functionality
52	2. Check `package.json` / `pyproject.toml` / `Cargo.toml` for relevant installed packages
53	3. If the task involves external data/APIs: note available MCP servers that might help
54
55	Based on the scan request, run focused searches:
56
57	1. Use `Glob` to find files matching the target domain:
58	- Auth domain: `*/auth`, `/login`, `/session*`
59	- API domain: `*/.controller.`, `/.route.`, `/.handler.*`
60	- Data domain: `*/.model.`, `/.schema.`, `/.entity.*`
61	2. Use `Grep` to search for specific patterns:
62	- Function names: `pattern: "function <name>"` or `"def <name>"`
63	- Class definitions: `pattern: "class <Name>"`
64	- Import statements: `pattern: "import.*<module>"` or `"from <module>"`
65	3. Use `Read` to examine the most relevant files (max 10 files, prioritize by relevance)
66
67	Verification gate: At least 1 relevant file found, OR confirm the target does not exist.
68
69	#### Info Saturation Detection (Know When to Stop)
70
71	Scout's default is "max 10 file reads" — but the real question is whether additional reads are productive. Track saturation across Phase 2 searches:
72
73	Entity tracking: As you scan files, extract key entities (function names, class names, imports, API endpoints, config keys). Maintain a running set of discovered entities.
74
75	\| Signal \| Threshold \| Meaning \| Action \|
76	\|--------\|-----------\|---------\|--------\|
77	\| New entity ratio \| Last 2 file reads added <2 new entities \| Search is exhausted for this domain \| STOP scanning, move to Phase 3 \|
78	\| Content similarity \| Last 2 files share >70% of the same imports/patterns \| Files are in the same module, redundant reads \| Skip remaining files in this directory \|
79	\| Query variation \| 3+ Glob/Grep queries with different patterns all return the same files \| All search angles converge \| Domain is fully mapped, proceed \|
80
81	When saturation detected: Emit in Scout Report:
82	```
83	### Saturation
84	- Reached after [N] file reads — last 2 reads added [M] new entities
85	- Recommendation: synthesize_and_report (further scanning unlikely to yield new insights)
86	```
87
88	Why: Without saturation detection, scout reads its full budget of 10 files even when 3 files already contain everything needed. This wastes context tokens and delays the calling skill. Early saturation detection returns control faster.
89
90	### Phase 3: Dependency Mapping
91
92	1. Use `Grep` to find import/require/use statements in identified files
93	2. Map which modules depend on which (A → imports → B)
94	3. Identify the blast radius of potential changes: which files import the target file
95
96	### Phase 4: Convention Detection
97
98	1. Check for config files using `Glob`:
99	- `.eslintrc`, `eslint.config.` → ESLint rules
100	- `tsconfig.json` → TypeScript config
101	- `.prettierrc*` → Prettier config
102	- `ruff.toml`, `.ruff.toml` → Python linter
103	2. Check naming conventions by r

People who liked this also viewed

6 picks

Type

azure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector searSkillsJul 2026472k1.3k
just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON fromSkillsJul 2026245k37
firecrawlCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agentsSkillsJul 202694k531
firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "SkillsJul 202676k531
firecrawl-agentAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, producSkillsJul 202674k531
firecrawl-mapDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where sSkillsJul 202674k531

scout

80stars21forks

View on GitHub

How to install scout?

rune-kit/rune/scout

$npx -y skills add Rune-kit/rune --skill scout

Installs into the current project.

Summary

Fast codebase scanner. Use when any skill needs codebase context. Finds files, patterns, dependencies, project structure. Pure read-only — never modifies files.

Files · 1

View on GitHub

SKILL.md

1	# scout
2
3	Fast, lightweight codebase scanning. Scout is the eyes of the Rune ecosystem.
4
5	## Instructions
6
7	When invoked, perform these steps:
8
9	### Phase 1: Structure Scan
10
11	Map the project layout:
12
13	1. Use `Glob` with `*/` to understand directory structure
14	2. Use `Bash` to run `ls` on key directories (root, src, lib, app)
15	3. Identify framework by detecting these files:
16	- `package.json` → Node.js/TypeScript
17	- `Cargo.toml` → Rust
18	- `pyproject.toml` / `setup.py` → Python
19	- `go.mod` → Go
20	- `pom.xml` / `build.gradle` → Java
21
22	```
23	TodoWrite: [
24	{ content: "Scan project structure", status: "in_progress" },
25	{ content: "Run targeted file search", status: "pending" },
26	{ content: "Map dependencies", status: "pending" },
27	{ content: "Detect conventions", status: "pending" },
28	{ content: "Generate codebase map (if full scan)", status: "pending" },
29	{ content: "Generate scout report", status: "pending" }
30	]
31	```
32
33	### Phase 2: Targeted Search (Search-First)
34
35	Search-first principle: Before building anything new, scout checks if a solution already exists — in the codebase, in package registries, or in available MCP servers.
36
37	Adopt / Extend / Compose / Build decision matrix:
38
39	When scout finds the caller's target domain, classify the situation:
40
41	```
42	ADOPT — Exact match exists (in codebase, npm, PyPI, MCP). Use as-is.
43	EXTEND — Partial match exists. Extend/configure existing solution.
44	COMPOSE — Multiple pieces exist. Wire them together.
45	BUILD — Nothing suitable exists. Build from scratch.
46	```
47
48	Report the classification to the calling skill. This informs Phase 2 (PLAN) in cook — ADOPT and EXTEND are vastly cheaper than BUILD.
49
50	Quick checks before deep search:
51	1. `Grep` the codebase for existing implementations of the target functionality
52	2. Check `package.json` / `pyproject.toml` / `Cargo.toml` for relevant installed packages
53	3. If the task involves external data/APIs: note available MCP servers that might help
54
55	Based on the scan request, run focused searches:
56
57	1. Use `Glob` to find files matching the target domain:
58	- Auth domain: `*/auth`, `/login`, `/session*`
59	- API domain: `*/.controller.`, `/.route.`, `/.handler.*`
60	- Data domain: `*/.model.`, `/.schema.`, `/.entity.*`
61	2. Use `Grep` to search for specific patterns:
62	- Function names: `pattern: "function <name>"` or `"def <name>"`
63	- Class definitions: `pattern: "class <Name>"`
64	- Import statements: `pattern: "import.*<module>"` or `"from <module>"`
65	3. Use `Read` to examine the most relevant files (max 10 files, prioritize by relevance)
66
67	Verification gate: At least 1 relevant file found, OR confirm the target does not exist.
68
69	#### Info Saturation Detection (Know When to Stop)
70
71	Scout's default is "max 10 file reads" — but the real question is whether additional reads are productive. Track saturation across Phase 2 searches:
72
73	Entity tracking: As you scan files, extract key entities (function names, class names, imports, API endpoints, config keys). Maintain a running set of discovered entities.
74
75	\| Signal \| Threshold \| Meaning \| Action \|
76	\|--------\|-----------\|---------\|--------\|
77	\| New entity ratio \| Last 2 file reads added <2 new entities \| Search is exhausted for this domain \| STOP scanning, move to Phase 3 \|
78	\| Content similarity \| Last 2 files share >70% of the same imports/patterns \| Files are in the same module, redundant reads \| Skip remaining files in this directory \|
79	\| Query variation \| 3+ Glob/Grep queries with different patterns all return the same files \| All search angles converge \| Domain is fully mapped, proceed \|
80
81	When saturation detected: Emit in Scout Report:
82	```
83	### Saturation
84	- Reached after [N] file reads — last 2 reads added [M] new entities
85	- Recommendation: synthesize_and_report (further scanning unlikely to yield new insights)
86	```
87
88	Why: Without saturation detection, scout reads its full budget of 10 files even when 3 files already contain everything needed. This wastes context tokens and delays the calling skill. Early saturation detection returns control faster.
89
90	### Phase 3: Dependency Mapping
91
92	1. Use `Grep` to find import/require/use statements in identified files
93	2. Map which modules depend on which (A → imports → B)
94	3. Identify the blast radius of potential changes: which files import the target file
95
96	### Phase 4: Convention Detection
97
98	1. Check for config files using `Glob`:
99	- `.eslintrc`, `eslint.config.` → ESLint rules
100	- `tsconfig.json` → TypeScript config
101	- `.prettierrc*` → Prettier config
102	- `ruff.toml`, `.ruff.toml` → Python linter
103	2. Check naming conventions by r

People who liked this also viewed

6 picks

Type