3925839f2a
Phase 2 of epic #4636, absorbing #4327 and #4354. Tests only; no fix. These MUST fail. Four CLI boundaries join externally-supplied input to a managed root with no containment validation. Each was driven through the real CLI and confirmed unconfined before the assertions were written: todo complete <name> src/commands.cts cmdTodoComplete check predicate --phase-dir <dir> check-command-router cmdCheckPredicate check decision-coverage-plan <dir> check-command-router resolvePath check gap-analysis.plan-post <dir> check-command-router Boundary 1 is worse than the issue describes. #4327 reports that a traversal name "resolves outside the todos root", which reads as an information leak. Measured, it is destructive: `todo complete ../../../../b1out/leak.md` exited 0, MOVED the outside file into completed/, and unlinked the original. The file was gone. cmdTodoComplete ends in fs.unlinkSync(sourcePath), so an unconfined name does not merely read across the boundary, it consumes across it. Boundary 2 reproduces #4354 exactly: a BLOCKING gate returned {"block":false,"details":{"match":true}} sourced entirely from a SECURITY.md in a directory the caller chose, outside the project. Boundaries 3 and 4 are not named in the epic. Both accepted an outside phase dir and exited 0. Rows that exist because they are the ones nobody enumerates: - ORDERING. A real file is created outside the todos root, then the traversal name targeting it is asserted rejected AND the outside file asserted still present and unmoved. #4327 notes the existence check and the move target BOTH follow the unvalidated join, so a rejection that lands after the read has already leaked — and, per the finding above, after the unlink has already destroyed. - `a/../../b.md` — looks balanced, resolves outside. - --dry-run must reject too; a preview must not leak a resolved outside path. - ${PHASE_DIR} interpolation into a command-exit-zero predicate is the SECOND predicate kind, which a fix inside gate-predicate-evaluator.cts would miss. - An absolute path INSIDE the project must still be accepted at every boundary — absolute is not a synonym for escaping. Cross-boundary rows loop over one shared list of escaping inputs and assert all four reject with the same shape, so four sites adopting one predicate cannot drift into four rejection contracts. Property tests cover BOTH directions — outside is always rejected, inside is always accepted. A property asserting only rejection is satisfied by a predicate that rejects everything, which is the degenerate-implementation trap found in Phase 1's review. Both are seeded. Regressions fold into the owning module suites rather than a new tests/fix-NNNN-*.test.cjs, per scripts/lint-regression-test-names.cjs. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
GSD Core
Git. Ship. Done.
English · Português · 简体中文 · 日本語 · 한국어
A light-weight meta-prompting, context engineering, and spec-driven development system for Claude Code, OpenCode, Antigravity CLI, Kimi CLI, Kilo, Codex, Copilot, Cursor, Windsurf, and more.
What is GSD Core
GSD Core is a context-engineering and spec-driven development framework that drives AI coding agents (Claude Code, Codex, Antigravity CLI, Kimi CLI, Copilot, Cursor, and more) through a disciplined phase loop. It solves context rot — the quality degradation that accumulates as an AI fills its context window — by running all heavy research, planning, and execution work in fresh-context subagents while keeping your main session lean.
How it works
Each milestone repeats the same five-step loop, one phase at a time:
- Discuss — capture implementation decisions before anything is planned
- Plan — research, decompose, and verify the plan fits a fresh context window
- Execute — run plans in parallel waves; each executor starts with a clean 200k-token context
- Verify — walk through what was built; diagnose and fix before declaring done
- Ship — create the PR, archive the phase, repeat for the next one
Quickstart
npx @opengsd/gsd-core@latest
The installer prompts for your runtime (Claude Code, OpenCode, Antigravity CLI, Kimi CLI, Kilo, Codex, Copilot, Cursor, Windsurf, and more) and whether to install globally or locally. The installer is required for cross-runtime compatibility — do not copy files from agents/ or commands/ directly.
On another runtime or without Node.js? See Install on your runtime.
Once installed, start a new project or onboard an existing repo:
/gsd-new-project # greenfield project
/gsd-onboard # existing codebase
New here? Follow Your first project for a guided walkthrough from install to first shipped phase, or Onboarding an existing codebase for brownfield setup.
Documentation
What's new in 1.7.0 → docs/whats-new-1.7.0.md
Tutorials — learning by doing:
How-to guides — task-focused recipes:
Reference — authoritative facts:
Explanation — concepts and design decisions:
Full index: docs/README.md. Other languages: 日本語 · 한국어 · Português · 简体中文.
Why it works
Most AI-coding setups fail at scale because context bloat silently degrades output quality, there is no shared memory between sessions, and nothing verifies that code actually works. GSD Core solves all three: heavy work runs in fresh subagents, structured artifacts like STATE.md and CONTEXT.md survive session boundaries, and the verify step walks through what was built and generates fix plans before a phase is declared done. See docs/explanation/context-engineering.md for the full reasoning.
Troubleshooting? See docs/how-to/recover-and-troubleshoot.md.
Community
| Project | Platform |
|---|---|
| gsd-opencode | Original OpenCode port |
| Discord | Community support |
Star History
License
MIT License. See LICENSE for details.
Claude Code is powerful. GSD Core makes it reliable.