Trackline — AI skill for Claude Code
An alignment layer for AI agents.
How to install Trackline
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open yerinsabraham/trackline and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Trackline does
An alignment layer for AI agents. Watches whether an agent's actions still match the task, rules and evidence it was given: beside local coding agents like Claude Code, and across production agent traces. One engine, two surfaces. The CI eval gate is the first working component.
Alternatives in AI
- Generate Clip — Generate AI video clips for your Remotion project 113 ★
- Fable Soul — A judgment layer for AI coding agents - make your AI think, verify, and communicate like a senior engineer 106 ★
- Claude Council Skill — A Claude skill that convenes 7 expert AI personas to debate any decision, idea, or problem — then synthesizes 87 ★
README
trackline
**An alignment layer for AI agents.**
Trackline watches whether an AI agent's actions still match the task, the rules and the evidence it was given. It works across two surfaces:
- Locally, it runs beside coding agents like Claude Code, Codex and Cursor, catching drift while the work is still happening.
- In production, it ingests agent traces, scores alignment, and flags runs where the agent appears to have gone off task.
The same core engine powers both: **normalise what the agent did, compare it against intent, produce an evidence-backed verdict.**
An agent that goes off task does not crash. It edits files nobody mentioned, ignores the rules file it read an hour ago, and the build stays green. Tests check that code does what it was written to do; they have no opinion on whether it is the code you asked for. Trackline is the layer that notices.
Build status
Trackline is being built in phases. This section is the only part of this README that changes as they land.
| Component | Status |
|---|---|
| Eval gate (CI regression gate) | ✅ Working. Documented below. |
| Core alignment engine | Foundation phase |
| Local surface (coding agents) | Not started |
| Production surface (trace ingest) | Not started |
The eval gate is the first working component and will fold into the broader alignment engine as its CI-side entry point. It is real, tested and gating merges today; everything else is honest roadmap.
Design notes and the reasoning behind the phases: [yerinsabraham.com/engineering/nothing-notices-when-an-agent-drifts](https://yerinsabraham.com/engineering/nothing-notices-when-an-agent-drifts).
**The measurements behind the design are in [`docs/experiments/`](docs/experiments/),** with the code and raw data that produced them:
| Question | Answer | |
|---|---|---|
| 1 | When a hook blocks an agent and explains why, does the agent correct itself? | **Yes, 11 |
Related Skills
Intent Drift Skill
Detects intent drift in AI-assisted development by comparing original goals against current execution plans us
Franken Alignment
Evidence-carrying control system for powerful AI agents, featuring epistemic MVCC, authority graphs, progressi
Stakeholder Analysis Skill For Developing Partnership Strategy
Free AI skill that turns stakeholder analysis into a partnership strategy: stakeholder mapping matrix (impact
AI Operator Kit
Battle-tested patterns from running AI agents in production daily: the CLAUDE.md that finishes work, a 5-layer
Svdo Meter
SVDO Meter is an open-source telemetry and evaluation layer for AI coding agents. Measure execution, token usa
Dresscode
Scores the design system across 20 areas with evidence, tests whether AI applies it without guessing, and turn
Related Agents
Pi Implementer
Implementation lane driven by the pi CLI (a local multi-provider coding agent, distinct from omp). Model-agnos
Citation Judge
Stage 3 worker — reads one listing of middle-band citation matches, each an entry a corpus file prints beside
Test Scout
Doctrine: spawned by /doctrine:prepare beside doctrine:scout to map each Criterion of a task to its check, lay
