Add v0.1 spec, execution plan, and project scaffold - #1
Merged
Conversation
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Help text and errors target coding agents: when-to-use guidance and a what/why/fix error format with stable exit codes. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
All future writes route through an explicit allowlist of user-level roots plus operator-designated project directories. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Establishes the tod v0.1 project: a settled spec and execution plan, plus the repository foundation the plan's first milestone calls for. tod is an operator harness that guides AGENTS.md-compatible coding agents for non-technical builders; it never scaffolds application code and never deploys.
Changes
project/tod-v0.1/): the outline is replaced with a full spec (requirements, non-goals, acceptance criteria) and a five-milestone execution plan with test cases mapped to every acceptance criterion. Key design points: config/state harness (no launcher), marker-block ownership inside possibly pre-existing shared files, agent-led onboarding, and deterministic CLI mutations.better-resultandzodas the only runtime dependencies. CI runs typecheck, lint, and tests on PRs. Package istod-ai, exposing atodbinary.src/run.ts,src/commands/): routing plus stubs forinit,new,sync,status. Help text and errors target coding agents: when-to-use guidance and a what/why/fix error format with stable exit codes (src/output.ts).src/boundary.ts): symlink-resolved containment check against an allowlist of user-level roots plus operator-designated project directories. All future filesystem writes route through it.AGENTS.md,CLAUDE.mdsymlink): engineering rules for agents working on tod: operator-system safety, non-destructive marker-block edits, determinism-first tooling, dependency policy.Why
tod runs on the machines of non-technical operators, so safety primitives come first: the boundary module and the non-destructive editing rules exist before any command can write to disk. The CLI is agent-facing rather than human-facing, which shapes help text and error output as machine-actionable guidance. Marker blocks (rather than whole-file ownership) let tod coexist with an operator's existing AGENTS.md instead of overwriting it.
🤖 Generated with Claude Code