Skip to content
sabindPublic

About

This plugin helps you write code like a seasoned engineer, even if you don't know all the best practices.

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

ponderly

This plugin helps you write code like a seasoned engineer, even if you don't know all the best practices. It leans on our own thinking for reasoning, since even the best AIs cannot reason: they predict the next token in a sequence, and we have to decide which direction to point them in. It aims to slow the AI down when the scope is unclear and let it run fast when it knows what to do. At the same time, it catches the AI before it lets itself make mistakes or assumptions, so the pace always fits the level of understanding.

How it was built, and what it caught on the site it was tuned on, is told at dansabin.com/projects/ponderly.

Docs: guides to plan a year, build a feature, fix a bug, make a small change and tune a template; the Reference; the evidence; contributing.

Install

ponderly is a plugin for Claude Code. It adds skills, agents and team rules that every session loads. This repository is its marketplace, sabind, and the marketplace holds one plugin, ponderly. From any terminal:

claude plugin marketplace add sabind/ponderly
claude plugin install ponderly@sabind

The plugin loads the next time you start Claude Code. In a session that is already open, run /reload-plugins.

An implement-spec wave 1 report: Problems first, a wrong statement about data-driven tones with two options, a CLI error position and one failed gallery build; then Done task by task with the requirements each meets, the checks, the files changed, and Next, which says wave 2 starts now.

What it does

You ask Claude for a job, and the plugin runs the skill that fits it. A small, contained change goes to one agent that builds it and proves it. A bug goes to bugfix, which reproduces it before any code changes. Anything bigger becomes a spec of requirements, design and tasks, each of which you approve before the next, and implement-spec builds it wave by wave. Before the pull request, readable-code makes the branch's code read plainly without changing what it does, and tighten-tests slims its tests without losing a covered line.

flowchart LR
    strategy --> hld --> lld --> start-task
    start-task -->|"one contained change"| task-executor
    start-task -->|"a defect"| bugfix
    start-task -->|"anything bigger"| spec["spec: requirements, design, tasks"]
    spec --> implement-spec
    implement-spec -->|"each task"| task-executor
    implement-spec -->|"each wave"| wave-reviewer
    start-task -->|"after a done change"| pr
    implement-spec -->|"every task ticked"| pr
    bugfix --> pr
    readable-code -->|"then the tests"| tighten-tests
    readable-code --> pr
    tighten-tests -->|"code not yet readable"| readable-code
    tighten-tests -->|"each gap found"| start-task
    tighten-tests --> pr
    review -->|"each lens"| review-arm
    review -->|"the merged findings"| wave-reviewer
Loading

The Reference describes each skill and agent, including report, which writes hand-backs like the one above.

When to use it

  • Claude Code without the plugin. Claude Code is an agentic coding tool that reads your codebase, edits files and runs commands, in the terminal, an IDE, a desktop app or the browser. Use the plugin on top of it when you want each request routed to a skill, specs you approve before code, and the same team rules in every session.
  • Kiro. Kiro is an agentic IDE built around spec-driven development: it breaks complex features into detailed implementation plans with tracking, and its steering files hold a project's rules. In ten months of my own use it was good for thinking a feature through, but it often reported a fix or a task as done before checking it, and I had to restate rules in each workspace. The plugin brings the same spec way of working into Claude Code, ticks a task only after its checks have run, and loads the same rules in every repository.

How it is tested

make validate runs the free checks under checks/ and claude plugin validate, with no model call, and CI runs it on every pull request. The make eval-* targets run claude plugin eval cases for the skills, agents, hooks and most rules; each case is a real model call, so they run by hand and never in CI, and the evidence shows what they found.

What this does not do

  • It does not commit, push or open a pull request unless you ask, and pr opens one only after you approve its draft. readable-code and tighten-tests leave their changes uncommitted.
  • It does not commit on the default branch. When you are on it, pr and implement-spec offer to create a branch first.
  • It does not decide what to build. You own each spec document and approve it before the next, and implement-spec never edits the spec beyond its checkboxes without your approval.
  • The plugin itself does not read a credential or send anything anywhere except through git and gh to your repository's own remote, and the review-arm agent's web searches, which name only a tool outside the repository and the behaviour in question, never your code. The task-executor agent and the readable-code and tighten-tests skills also run the project's own tests, and the two skills its other tools, which do whatever they do in that project. tighten-tests adds a coverage tool only when you say yes. What each part runs is in the Reference's What the plugin runs and sends.

Develop the plugin

To set up, test and submit a change, read the contributing guide.

License

MIT. See LICENSE.

About

This plugin helps you write code like a seasoned engineer, even if you don't know all the best practices.

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages