dynos-audit
Description: Spec-driven audit enforcement for AI coding agents. Intercepts every phase transition with a mandatory audit loop. It builds a
Open source Repository Open in the app JSON README (API)
About
Description: Spec-driven audit enforcement for AI coding agents. Intercepts every phase transition with a mandatory audit loop. It builds a requirement ledger from your spec, audits the artifact, identifies gaps, delegates fixes, and re-audits until every requirement is provably done with evidence. Never accepts "mostly complete." Requires Superpowers.
Details
- Kind
- Plugins
- Topic
- No topic detected
- Publisher
- hassamsheikh
- Origin
- marketplace
- Category
- ferramentas
- Stars
- 2
- Forks
- 2
- Open pull requests
- 2
- Last push
- 2026-09-06T16:36:37Z
- Repository state
- ativo
- Language
- Python
- License
- MIT
- Added
- 2026-08-30 01:48:58
- Updated
- 2026-08-30 01:48:58
- Origin id
hassamsheikh/dynos-audit/dynos-audit
README
<p align="center">
<a href="https://dynos.fit">
<img src="dynos-logo-dark.svg" alt="dynos.fit" />
</a>
</p>
# dynos-work
A Claude Code and Codex plugin that builds features, catches its own bugs, and gets better at your codebase over time.
## Install
### Claude Code
```
claude plugin marketplace add dynos-fit/dynos-work
claude plugin install dynos-work
```
### Codex
This repo also includes a Codex plugin manifest at `.codex-plugin/plugin.json`. Install it through your Codex plugin workflow from this repository root.
## Use
### Claude Code
```
/dynos-work:start build a user settings page
```
### Codex
Invoke the `start` skill with your task, for example: "Use dynos-work start to build a user settings page."
That's it. You'll answer a few questions about what you want, approve a spec, approve a plan — then it builds.
## What happens
When you start a task, the plugin:
1. **Asks what you need** — a few targeted questions to nail down scope
2. **Writes a spec** — exact behavior, edge cases, what's out of scope. You approve it.
3. **Writes a plan** — which files change, in what order, how it'll be tested. You approve it.
4. **Builds in parallel** — multiple agents work on independent pieces simultaneously
5. **Audits its own work** — independent agents check for bugs, security issues, and spec gaps
6. **Repairs what it finds** — automatically, up to 3 attempts before it asks you
After the task, it learns from what went wrong and builds prevention rules for next time. Your 10th task is better than your 1st.
## Commands
```
/dynos-work:start [task] start a new task
/dynos-work:execute run the approved plan
/dynos-work:audit audit, repair, and close
/dynos-work:status check where your task is
/dynos-work:resume continue after interruption
/dynos-work:investigate [bug] deep bug investigation
/dynos-work:residual inspect or drain non-blocking findings
```
## Requirements
Claude Code or Codex, plus Python 3 for the local dynos-work control plane.
## Running with permissions ON
The pipeline works without `--dangerously-skip-permissions`. Every deterministic step funnels through one binary — `<plugin-root>/bin/dynos` — so you can allow that single command prefix once (via the permission prompt's "don't ask again" or a `Bash(<plugin-root>/bin/dynos ...)` allow rule in your settings) and then you only interact with the decisions that are actually yours: discovery questions, spec approval, plan approval, and TDD review. Plugin guardrail denials are not Claude Code permission errors — they say so explicitly and name the sanctioned alternative. Details: `docs/write-boundary-spec.md`.
## Links
- [Changelog](CHANGELOG.md)
- [Internals & CLI reference](INTERNALS.md)
- [Architecture](ARCHITECTURE.md)
- [Pipelines](PIPELINES.md)
---
> Completion is a control decision, not a model opinion.