Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 55 additions & 0 deletions AGENTS.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
<!-- AUTO-GENERATED by agent-core sync. Do not edit directly. -->

Check warning on line 1 in AGENTS.md

View workflow job for this annotation

GitHub Actions / agnix / agnix

Multiple instruction layers detected without documented precedence%3A AGENTS.md (/home/runner/work/sync-docs/sync-docs/AGENTS.md)%2C CLAUDE.md (/home/runner/work/sync-docs/sync-docs/CLAUDE.md) [XP-006]

Check warning on line 1 in AGENTS.md

View workflow job for this annotation

GitHub Actions / agnix / agnix

Missing project context section in AGENTS instruction file [AGM-004]
# sync-docs

> Sync documentation with code changes. Find outdated refs, update CHANGELOG, flag stale examples.

## Agents

- sync-docs-agent

## Skills

- sync-docs

## Commands

- sync-docs

## Critical Rules

1. **Plain text output** - No emojis, no ASCII art. Use `[OK]`, `[ERROR]`, `[WARN]`, `[CRITICAL]` for status markers.
2. **No unnecessary files** - Don't create summary files, plan files, audit files, or temp docs.
3. **Task is not done until tests pass** - Every feature/fix must have quality tests.
4. **Create PRs for non-trivial changes** - No direct pushes to main.
5. **Always run git hooks** - Never bypass pre-commit or pre-push hooks.
6. **Use single dash for em-dashes** - In prose, use ` - ` (single dash with spaces), never ` -- `.
7. **Report script failures before manual fallback** - Never silently bypass broken tooling.
8. **Token efficiency** - Be concise. Save tokens over decorations.

Check failure on line 27 in AGENTS.md

View workflow job for this annotation

GitHub Actions / agnix / agnix

Potential secret detected in AGENTS.md [CDX-AG-002]

## Model Selection

| Model | When to Use |
|-------|-------------|
| **Opus** | Complex reasoning, analysis, planning |
| **Sonnet** | Validation, pattern matching, most agents |
| **Haiku** | Mechanical execution, no judgment needed |

## Core Priorities

1. User DX (plugin users first)
2. Worry-free automation
3. Token efficiency
4. Quality output
5. Simplicity

## Dev Commands

```bash
npm test # Run tests
npm run validate # All validators
```

## References

- Part of the [agentsys](https://github.com/agent-sh/agentsys) ecosystem
- https://agentskills.io

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For consistency with the link on the previous line, it's better to provide descriptive text for this URL. This improves readability.

Suggested change
- https://agentskills.io
- [Agent Skills](https://agentskills.io)

8 changes: 8 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,13 @@
# Changelog

## [Unreleased]

### Added

- Doc-drift signals from `agent-analyzer` binary: docs with low code-coupling are surfaced as likely stale
- Prompt in `sync-docs` skill to generate `repo-intel` map when not found, enabling doc-drift detection
- Pre-fetch of doc-drift data in `sync-docs` command before spawning the agent, reducing redundant binary calls

## [1.0.0] - 2026-02-21

Initial release. Extracted from [agentsys](https://github.com/agent-sh/agentsys) monorepo.
Loading