indexion-agent-orient — Claude Code skill: what it does
indexion-agent-orient is a Claude Code skill that maps code ownership before edits, showing agents who owns a function and what files to read.
Apache-2.0 4,900 installs ★ 2 updated 2026-09-22
npx skills add trkbt10/indexion-skills --skill indexion-agent-orient -a claude-codeWhat indexion-agent-orient does
Skill runs indexion agent orient — a command that scans the codebase, identifies which packages own the requested function, and outputs a brief with likely owners, files to read before patching, and unsafe edit locations. The brief goes into CLAUDE.md, .claude/commands/, or gets passed to a subagent as context.
Inside — an incremental map .indexion/cache/agent/orient-map.json that refreshes only changed files and owner profiles. The --no-update flag gives an instant answer from the prebuilt map without rescanning. Requires installed indexion CLI with the built-in agent orient command. If indexion agent orient --help fails, the binary is outdated.
What it helps with
- Identify who owns a function before starting edits
- Avoid patching CLI or adapters instead of the core package
- Pass ownership structure context to a subagent
- Build a code map for a zero-knowledge agent with no history
- Prevent edits to critical files without verification
Example prompts for the agent
- Build an ownership map for the task in
task.mdwithindexion agent orient --task-file task.md --output=.indexion/cache/agent/orient.md . - Identify the owner of a name/content drift audit function via
indexion agent orient --task "detect drift between names and implementation contents" . - Show a brief on owners from the prebuilt map with
indexion agent orient --no-update --task "name/content drift scoring" .
How to install indexion-agent-orient
1Skills CLI (Vercel)
npx skills add trkbt10/indexion-skills --skill indexion-agent-orient -a claude-code2Manually: put the files in place
~/.claude/skills/indexion-agent-orient/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/indexion-agent-orient/
1Skills CLI (Vercel)
npx skills add trkbt10/indexion-skills --skill indexion-agent-orient -a codex2Manually: put the files in place
.agents/skills/indexion-agent-orient/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add trkbt10/indexion-skills --skill indexion-agent-orient -a cursor2Manually: put the files in place
.cursor/skills/indexion-agent-orient/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install trkbt10/indexion-skills skills/indexion-agent-orient2Manually: put the files in place
.github/skills/indexion-agent-orient/SKILL.md1Skills CLI (Vercel)
npx skills add trkbt10/indexion-skills --skill indexion-agent-orient -a gemini-cli2Platform CLI
gemini skills install https://github.com/trkbt10/indexion-skills --path skills/indexion-agent-orientManually: put the files in place
.devin/skills/indexion-agent-orient/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add trkbt10/indexion-skills --skill indexion-agent-orient -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about indexion-agent-orient
How to install indexion-agent-orient in Claude Code?
Run npx skills add trkbt10/indexion-skills --skill indexion-agent-orient -a claude-code, the brief will appear in ~/.claude/skills/indexion-agent-orient/SKILL.md.
What does indexion-agent-orient do?
Builds a code ownership map, identifies likely function owners, files to read before patching, and unsafe edit locations. The brief goes into CLAUDE.md or gets passed to a subagent.
What is required for indexion-agent-orient to work?
Installed indexion CLI with the built-in agent orient command. Check with indexion agent orient --help — if the command is missing, update the binary.
Source text
SKILL.md · Apache-2.0
---
name: indexion-agent-orient
description: Generate and use a pre-edit structure brief so coding agents learn likely owners, consumer surfaces, and unsafe edit locations before implementing.
---
# Agent Orientation Workflow
Use this skill before starting implementation in an unfamiliar or ambiguous part
of a codebase.
## Why
Coding agents often anchor on the path or noun in the user prompt and start
editing before they have learned the repository's ownership structure. `indexion
agent orient` builds an incremental orientation map across the selected
codebase, then renders a short, evidence-backed brief that can be pasted into
AGENTS.md, CLAUDE.md, a Claude slash command, a Codex skill, or a subagent prompt.
The rendered `--limit` is only a display limit. Owner inference must come from
the full prebuilt map, including code structure, package READMEs, and wiki pages
whose provenance is maintained by `wiki pages update`, `wiki pages ingest`, and
`plan reconcile`.
Owner profiles use package documentation and owner-specific wiki pages. Broad
wiki pages with multiple source roots are useful background, but they should not
be treated as proof that every referenced package owns the task.
## Pipeline
0. Verify the installed CLI has this workflow:
```bash
indexion agent orient --help
```
If this command is missing, update or rebuild indexion before continuing.
Having an older `indexion` binary in PATH is not enough for this skill.
1. Generate the brief:
```bash
indexion agent orient --task-file task.md --output=.indexion/cache/agent/orient.md .
```
The first run writes `.indexion/cache/agent/orient-map.json`. Later runs
refresh changed files and affected owner profiles only. Use `--no-update`
when you intentionally want to query the saved map without refreshing it.
This is the mode to use when a zero-knowledge agent needs an immediate
owner guess from the latest prebuilt map.
For short tasks:
```bash
indexion agent orient --task "add a name/content drift audit" .
```
If the user task is in a language or wording that does not appear in the
repository's identifiers and README prose, keep the original task in your
notes and pass a short codebase-vocabulary gloss to `--task`. The gloss
should describe the objective, not the suspected owner. For example, say
"detect drift between names and implementation contents" instead of naming a
package you have not confirmed.
Do not put supporting infrastructure constraints into the owner-inference
`--task` gloss. Keep the original request, required tools, and implementation
constraints in your notes or subagent prompt. The gloss is only the objective
vocabulary used to query the prebuilt map, for example:
```bash
indexion agent orient --no-update --task "name/content drift scoring and remediation planning" .
```
2. Read these sections before editing:
- `Likely Implementation Owners`: core packages that should own domain
behavior.
Treat the first entry as the initial owner hypothesis unless follow-up
evidence contradicts it.
- `Knowledge Sources`: release notes, wiki pages, READMEs, or other
documentation that matched the task. Use these as context; do not treat a
documentation-only path as the place to implement domain behavior.
- `Consumer Surfaces`: CLI, skills, docs, or adapters likely to call the core.
- `Do Not Implement Here`: files to avoid as domain implementation targets.
- `Required Preflight`: files the agent should read before patching.
- `Orientation Map`: confirms the total file/owner/documentation corpus used
before display truncation.
3. Confirm the owner with focused tools:
```bash
indexion doc graph --format=text <likely-owner>
indexion grep --semantic=name:<term> .
indexion search "<task concept>" .
```
Use the distinguishing terms from the brief and the user task, not only the
broad infrastructure words. If search results drift toward supporting
systems instead of the likely owner, refine the query with the name/content,
drift, divergence, or domain-specific terms that actually define the task
before changing the owner.
4. Gate implementation:
- If the intended edit path appears in `Do Not Implement Here`, stop and
explain the conflict.
- If the intended owner is absent from `Likely Implementation Owners`, gather
more evidence with `doc graph`, `grep`, `search`, or `explore`.
- Keep CLI code thin unless the brief and follow-up evidence show it owns the
behavior.
5. Use for zero-knowledge delegation:
Give a subagent only the task and the generated orientation brief, then quiz
it before assigning implementation work. It should immediately name the core
implementation owner, one knowledge source, one unsafe edit location, and one
preflight evidence path. Passing that quiz is the signal that the prebuilt map
has transferred the right ownership assumptions.
## External Agent Mapping
- Claude Code: store stable guidance in `CLAUDE.md`, project commands in
`.claude/commands/`, and project subagents in `.claude/agents/`.
- Codex: store stable guidance in AGENTS.md or skills, and paste the orientation
brief into delegated task context.
- Multi-agent workflows: use the brief as the structured handoff payload so each
isolated agent starts with the same repository-specific assumptions.
© trkbt10 · Apache-2.0 · trkbt10/indexion-skills