Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

74 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

level-five (l5)

tests License: MIT

A level 3 agentic harness built by following Agentic Programming by Jerod W. Wilkerson. The harness is a story execution system: stories enter with an approved plan, move through implementation, testing, and verification, retry when verification fails, and end completed or escalated.

About the name. The name is aspirational. What you'll find here is a level 3 harness, but level five is where the ladder leads, and the repository is built to grow in that direction.

Companion to the book

This repository tracks Agentic Programming through level 3. Part 3 (Chapters 12–19) explains how an agentic harness works, and Appendix A, "Building a Sample Level 3 Harness," builds this one from an empty directory to a working system, including the real escalations that happened along the way.

The book is at agenticprogrammingbook.com.

The appendix is the starting point, not the finish line. It stops at a deliberately small harness so the essential structure stays readable, and then hands you a roadmap: harden first, following Chapter 18, then scale, following Chapter 19. This repository is walking that roadmap. Every improvement arrives the way the book says it should — as a story the harness plans, executes, verifies, and documents itself.

The appendix state

The exact harness Appendix A describes is tagged appendix-a. If you are reading the appendix and want to check your own build against it, or want to start where the appendix stops, use that tag:

git clone https://github.com/jerodw/level-five.git
cd level-five
git checkout appendix-a

main has moved past it. The appendix's code excerpts — the workflow definition, the implementer prompt, the coordinator's routing loop — match the tag, and the differences on main are the point rather than drift.

What has changed since

Each story below is a step the book's roadmap calls for, or a failure the build hit that the roadmap did not anticipate. The story artifacts are committed in .harness/stories/. Run directories are execution state rather than source, so .harness/runs/ is gitignored and does not travel with a clone; the runs worth keeping — two escalations and a reset — are copied into .harness/runs-archive/.

Story Change Where the book argues for it
001–002 l5-status; per-stage changed-files records Appendix A (appendix-a)
003–004 One shared harness layer; machine-readable artifact schemas Ch. 16, prompt layering; Ch. 14, artifact contracts
005–007 Schema-directed story parser and pre-flight validation; one reader of a story artifact; coordinator-enforced stage output ownership Ch. 15, governance boundaries; Ch. 18, hardening
008–009 The story schema and the workflow's stage rules injected into the planner prompt Ch. 16, injection over restatement
010–012 attempts/attempt-N/ archives, execution-history.json, retry-history.json Ch. 17–18, retry evidence
013–017 Verification hardening: the suite re-run in a clean clone, assertions that can be shown to fail, the schema inventory moved out of tests/, the coordinator's output contract asserted directly, an implementer's test edits decided by reverting them Failures this build hit; Ch. 18 in spirit

Still ahead, in the order Chapters 18 and 19 recommend: per-agent logs and a watcher, hooks in place of a static allowed_tools allowlist, an adjudicator, an inspector, resumable escalated runs, pause-and-resume on capacity exhaustion, git worktrees and parallel story execution, a real initialization library, and a .harness/history/ record across runs.

The harness stays at level 3. Epics and products (Chapters 20–22) are a different unit of coordination, and the book is explicit that the story workflow earns that step through a track record rather than a feature list.

Prerequisites

  • Claude Code CLI (claude) with an active subscription
  • Python 3 (3.10+)
  • Git

No third-party dependencies — the harness uses only the Python standard library.

Scripts

All harness capabilities are invoked through l5- scripts in scripts/:

Script Purpose
l5-init Initialize a .harness/ structure in a target repository
l5-plan Plan a story interactively with the planner agent; produces a story artifact
l5-run Execute an approved story through the story workflow
l5-status Show a snapshot of story runs (status, current stage, retries), or one run's detail
l5-assist Launch the interactive assist agent with harness context

Example:

scripts/l5-plan "Add a --dry-run flag to l5-run"
scripts/l5-run story-001
scripts/l5-status

Layout

workflows/       workflow definitions (stages, artifact routes, retry rules)
schemas/         JSON Schemas for the structured artifacts, plus their manifest
prompts/         reusable agent prompt templates ({{placeholder}} injection)
orchestration/   the Story Coordinator and its supporting modules
rules/           execution rules enforced by the coordinator
scripts/         thin l5- entry points
templates/       starter files l5-init copies into a new target repository
.harness/        target-repository state: config, standards, docs, stories; plus
                 runs and logs, which are gitignored execution state

The harness pieces (workflows/, schemas/, prompts/, orchestration/, rules/, scripts/, templates/) are reusable across target repositories. The .harness/ directory is target-repository state; run l5-init to create it in any other repository you want the harness to work on.

This repository is both the harness repository and its own first target repository. Every demo story is a real harness feature, so the harness participates in building itself from the start.

How a story runs

  1. l5-plan runs an interactive planning session and writes an approved story artifact to .harness/stories/.
  2. l5-run hands the story to the Story Coordinator, which creates a story branch and a run directory under .harness/runs/<story-id>/.
  3. The coordinator advances the workflow stage by stage (implement → test → verify → document), assembling each stage's context, injecting it into the stage prompt, and invoking the agent headlessly (claude -p).
  4. The verifier writes verification-result.json. The coordinator routes from that artifact: advance, retry the implementer with structured retry guidance, or escalate. On a passing verdict it re-runs the suite in a fresh clone with the story committed, because the working tree is the one place that commit does not yet exist.
  5. Every run leaves its state (state.json), the same events in two renderings (events.log and execution-history.json), a record of any retry (retry-history.json), and the artifacts each stage produced.

See .harness/docs/ARCHITECTURE.md for the full architecture.

Tests

The Story Coordinator is deterministic and fully unit-tested without any model calls (a fake runner plays back scripted stage artifacts). Run the suite with:

.venv/bin/python -m pytest tests/ -q

Contributing and feedback

This repository tracks the book through level 3, so its scope is what Part 3 and Appendix A describe. Small fixes — genuine bugs, or errors in the code and its docs — are welcome via pull request. Improvements the book's roadmap calls for are welcome as issues; they are best planned and executed through the harness itself, which is the whole point of it. Changes that would take the harness past level 3, or in a direction the book does not argue for, are out of scope here.

Found a bug in the harness code? Open a GitHub issue. For anything about the book's content — typos, unclear passages, errata — please use the feedback form at agenticprogrammingbook.com/feedback rather than GitHub Issues.

License

MIT — see LICENSE. Copyright © 2026 Jerod W. Wilkerson.

About

A level-3 agentic harness — the companion code to Appendix A of the book Agentic Programming.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages