Get This Tool
Hanesu
Pricing
- Model
- Free
Summary
Long prompt, single shot, hope for the best — that's the default mode for most AI coding agents, and it falls apart the moment a task requires search, then planning, then verification before touching production code. Hanesu is an experimental workflow layer that sits inside your repo and gives agents a visible, structured process instead of a blank canvas.
The project borrows from Harness Engineering principles: work is broken into phases with task files, role handoffs, quality gates, and progress artifacts written to disk. Agents using runtimes like OpenCode, Codex, or Claude Code run through that structure rather than a monolithic prompt. The vendor explicitly flags this is not for small, obvious edits — a direct prompt is faster there. Where it earns its place is multi-step refactors, security-sensitive changes, or bugfix workflows where you need the agent to stop, surface what it found, and wait for your sign-off before proceeding.
Bottom line: Reach for Hanesu when an ambiguous, risky change needs documented decision artifacts and human gates baked into the agent's path — skip it when the edit is two lines and a test, because the overhead will cost more than the safety buys.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Phase-gated workflow structure means the agent stops and surfaces findings before writing code, so risky refactors don't reach your codebase without a checkpoint you signed off on.
- Artifact writing is built into each phase, so decision records and discovery outputs are committed alongside the code change — teams doing security audits or post-incident reviews have a documented trail rather than a reconstructed chat log.
- MIT license and local repo installation means no external service dependency and no data leaving your environment, which removes the approval friction that blocks adoption in regulated or air-gapped codebases.
- Works alongside existing agent runtimes rather than replacing them, so teams already invested in OpenCode, Codex, or Claude Code don't have to abandon their toolchain to add structured workflow control.
Cons
Sign in to edit- For tasks that are small or well-defined, the phase and artifact overhead slows the agent down relative to a single direct prompt — the tool's own docs acknowledge this, but teams will still burn time learning where that line sits in their specific codebase.
- The project carries 2 stars and 4 commits at the time of curation; there is no issue tracker activity and no documented community — teams hitting an undocumented edge case in the gate logic have no support channel beyond reading the source code themselves.
- Hanesu has no API and no integration surface beyond local repo files, so any team that needs to tie agent workflow state into CI pipelines, ticketing systems, or deployment gates will have to build that plumbing from scratch — at which point they are maintaining the workflow layer Hanesu provides plus the integration layer it doesn't, and a more mature agent orchestration platform becomes the faster path.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- npm, GitHub
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-07-26T04:31:53.260Z
Best For
Who it's for
- Ambiguous or multi-phase coding tasks
- Teams wanting predictable agent behavior
- Repositories needing documented decision artifacts
What it does well
- Multi-step feature development with human gates
- Risky refactors requiring verification
- Audit or security-related code changes
- Bugfix workflows with scenario definition
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Hanesu
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Hanesu free?
- Yes — Hanesu is fully free to use. There is no paid tier.
- Is Hanesu open source?
- Yes. Hanesu is open source.
- Can I self-host Hanesu?
- Yes. Hanesu supports self-hosting on your own infrastructure.
- What platforms does Hanesu support?
- Hanesu is available on: npm, GitHub.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Hanesu installs into a repository via `npx create-hanesu` and adds a control layer that AI coding agents execute against. Rather than receiving one long prompt and running to completion, an agent working through Hanesu follows a sequence of task files organized into phases: search and discovery, artifact writing, phased coding, quality gate checkpoints, and a final verification step. The agent doesn’t decide when to move forward — the gate structure does, with human review required at configured checkpoints before the next phase unlocks.
The differentiating idea is the artifact trail. Each phase produces written outputs — decision records, findings, plans — that persist in the repo. For audit-sensitive or security-related changes, this means the reasoning behind a refactor isn’t buried in a chat window; it’s a committed file. Teams doing compliance work or post-incident reviews can read exactly what the agent considered before it touched anything.
Hanesu is explicitly scoped to ambiguous, multi-step, or risky work. The docs describe it as sitting inside your repo alongside agent runtimes rather than replacing them, which means it adds surface area to maintain. For teams already running Claude Code or Codex with their own prompt conventions, adopting Hanesu means learning a second layer of abstractions and keeping both in sync. Early-stage repositories with evolving structures will feel that friction most sharply.
The project is MIT-licensed with public source on GitHub, self-hosted by definition since it runs locally inside your repo, and carries no API dependency of its own — behavior is determined by whichever agent runtime you point at it.