https://github.com/joshmock/the-agency
a coding agent harness
https://github.com/joshmock/the-agency
Last synced: 3 months ago
JSON representation
a coding agent harness
- Host: GitHub
- URL: https://github.com/joshmock/the-agency
- Owner: JoshMock
- Created: 2026-02-23T14:51:46.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2026-04-26T20:43:58.000Z (3 months ago)
- Last Synced: 2026-04-26T21:28:32.680Z (3 months ago)
- Language: TypeScript
- Size: 278 KB
- Stars: 6
- Watchers: 0
- Forks: 0
- Open Issues: 21
-
Metadata Files:
- Readme: README.md
- Agents: AGENTS.md
Awesome Lists containing this project
README
A collection of extensions, skills, tools and experiments with the [Pi coding agent](https://www.npmjs.com/package/@mariozechner/pi-coding-agent).
## Current offerings
- [**pi-tokenshrink**](./packages/tokenshrink/): reduce a prompt's token count deterministically, without using inference
- [**pi-hashline-edit**](./packages/hashline-edit/): alternate to Pi's built in `edit` tool that improves the accuracy and efficiency of file edits, with high potential to reduce token usage
- [**pi-spec-kit**](./packages/spec-kit/): use [Spec Kit](https://github.com/github/spec-kit) for spec-driven development
- [**vmpi**](./packages/vmpi/): run `pi` sandboxed in a QEMU microVM via [Gondolin](https://earendil-works.github.io/gondolin/) -- hardware-isolated, no root required
## Goals
### Local inference
**Privacy**, **self-sufficiency**, **ethics** and **energy conservation** are personal values of mine, so there will be an emphasis on local and low-energy inference sources (e.g. [vLLM](https://docs.vllm.ai/) using local GPUs or CPUs).
Local inference also enables experimentation with open models that have been trained on more carefully curated sets of data.
### Security
Tools and experiments will ideally build on the use of containers or other tools (e.g. [nono](https://nono.sh/)) that limit the blast radius of an agent. [pi-guardrails](https://www.npmjs.com/package/@aliou/pi-guardrails) is a great start, but there are many ways to work around it.
### Do less, better
Avoid maximalism and accelerationism vibes. All code output is authored by a human—assisted by an agent, but with thorough review and revision—who understands, dog-foods and ultimately vouches for all code before publishing it for others. These are tools to help developers craft a coding agent experience to help them, not replace them. It is **not** intended to enable [inactive gods](https://en.wikipedia.org/wiki/Deus_otiosus) wishing to set a course and walk away.
Doing less also means:
- optimizing prompts for token efficiency
- limiting what agents can see and do to avoid context bloat and incorrect choices
Doing better also means:
- navigating code lexically: why grep when you can query a syntax tree?
- optimizing prompts for accuracy, preventing agents from doing the wrong thing
- measure performance where possible to find bottlenecks