Report · marked 10 Oct 2026

Fission-AI/OpenSpec

Solid foundations, held back in a few specific places.

TypeScript · 71,485 stars · 1,287 files · branch main

82 /100 A-

Instructions 15/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on instruction quality.Setup 16/16Whether an agent can install the project and get it running without a human. Full marks.Verification loop 25/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Full marks.Context economy 14/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context.Navigability 10/10How quickly anything new can orient itself. Full marks.

Higher is better. Accent marks what is costing you most.

Fix these first

Instruction quality

Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.

File sizes fit in context

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

The full marking

Every deduction below names the file or setting it came from.

Instructions 15/27 B-

Whether the repo tells an agent how to behave before it starts guessing.

✓Agent instruction file 12/12

AGENTS.md is present, which is the format the most tools read.

✗Instruction quality 0/12

The file exists but couldn't be read for scoring.

Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.

✓README as an entry point 3/3

README has a clear getting-started section.

Setup 16/16 A+

Whether an agent can install the project and get it running without a human.

✓Deterministic install 6/6

pnpm-lock.yaml pins the dependency tree.

Found pnpm-lock.yaml

✓Discoverable commands 6/6

Commands are declared where an agent will look for them.

package.json scripts (lint, build, generate:skills, regen:parity-hashes, dev, dev:cli…)

scripts/ directory

–Environment config n/a

Not applicable — this reads as a library, with no environment to configure.

✓Pinned runtime version 2/2

The language runtime version is pinned.

package.json engines.node >=20.19.0

✓Reproducible environment 2/2

.devcontainer/devcontainer.json gives a known-good environment.

Verification loop 25/25 A+

Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.

✓Tests exist 8/8

452 test files against 473 source files.

e.g. openspec/changes/add-amp-support/specs/ai-tool-paths/spec.md, openspec/changes/add-change-stacking-awareness/specs/change-creation/spec.md, openspec/changes/add-change-stacking-awareness/specs/change-stacking-workflow/spec.md

✓Test command is discoverable 7/7

An agent can find and run `npm run test`.

✓Continuous integration 4/4

3 GitHub Actions workflows define what "passing" means.

✓Lint and format rules 3/3

eslint.config.js encodes the house style.

✓Static type checking 3/3

Strict type checking is on, which catches a whole class of agent mistakes before they run.

Context economy 14/20 B+

Whether the repo fits in a context window, or fights it.

✓No committed build output 6/6

No generated directories committed.

✓.gitignore hygiene 3/3

.gitignore covers 73 patterns.

✗File sizes fit in context 0/6

3 source files are over 100KB.

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

test/core/archive.test.ts — 368KB

test/core/update.test.ts — 180KB

test/core/init.test.ts — 125KB

✓Repository weight 5/5

About 10.6MB checked out, which is comfortable.

Here is your AGENTS.md

Drafted from what is actually in this repository: the install command from your lockfile, the commands you already declare, your real directory layout. Anything marked TODO needs a person. Save it at the root as AGENTS.md.

AGENTS.md — drafted for Fission-AI/OpenSpec

# AGENTS.md

Spec-driven development (SDD) for AI coding assistants.

## Setup

```
pnpm install
```

## Commands

```
pnpm dev                   # run locally
pnpm build                 # produce a build
pnpm test                  # run the test suite, must pass before any commit
pnpm lint                  # lint
pnpm generate:skills
pnpm regen:parity-hashes
pnpm dev:cli
pnpm test:watch
```

## Layout

- `test/`    224 source files
- `src/`     210 source files
- `website/` 28 source files
- `scripts/` 6 source files
- `bin/`     1 source file

## Conventions

- Tests live alongside the code they cover, following `openspec/changes/add-amp-support/specs/ai-tool-paths/spec.md`.
- TypeScript runs in strict mode. Type errors are the fastest feedback available, so do not weaken it.
- CI defines what passing means. See `.github/workflows/ci.yml`, and keep it green.
- TODO: add the two or three conventions a newcomer always gets wrong here.

## Gotchas

- `test/core/archive.test.ts` is 368KB. It will not fit comfortably in context, so read it in parts.

---

Drafted by agentreadme.com from what is in this repository. Everything marked TODO
needs a human. Check it in as AGENTS.md at the root.

Open the raw markdown or curl -o AGENTS.md agentreadme.com/draft/Fission-AI/OpenSpec.md

A draft gets the commands right and stops at the things only a maintainer knows. What a good TypeScript AGENTS.md looks like covers what to add by hand, and what AGENTS.md is explains the format itself.

Show the mark

The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.

[![agent ready](https://agentreadme.com/badge/Fission-AI/OpenSpec.svg)](https://agentreadme.com/Fission-AI/OpenSpec)

Other TypeScript repositories, marked

freeCodeCamp/freeCodeCamp 69 B openclaw/openclaw 73 B+ nilbuild/developer-roadmap 45 C deepseek-ai/deepseek-harness 82 A- vuejs/vue 67 B anomalyco/opencode 78 A-

All TypeScript repositories

Think this mark is wrong?

Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.

Open an issue, already filled in