Skip to content

Releases: iMark21/sdd-harness

Release list

v1.0.0-rc1

v1.0.0-rc1 Latest
Latest

Choose a tag to compare

View all tags
@iMark21 iMark21 released this 16 May 20:58
v1.0.0-rc1
c182ac7

Release candidate 1: public-readiness audit fixup + beta hardening. Includes SH-F4-113 (CI badge fix for LinkedIn launch).

Assets 2
Loading

v1.0.0-alpha

v1.0.0-alpha

Choose a tag to compare

View all tags
@iMark21 iMark21 released this 15 May 18:41
v1.0.0-alpha
3d60e0c

sdd-harness — a runtime-agnostic Spec-Driven Development harness that any AI can operate.

Install

git clone https://github.com/iMark21/sdd-harness.git ~/.sdd-harness
cd ~/.sdd-harness && bash install.sh

# In any target repo:
sdd-harness init

What's in this release

  • A canonical .ai/ layer with vision, context, backlog, decisions, commands, hooks, agents, and notes.
  • 5-line root bootloaders (CLAUDE.md, AGENTS.md) — any AI runtime reads them and is pointed to .ai/.
  • A pre-commit hook that blocks feature commits drifting from their specs.
  • The phase-close discipline that keeps CONTEXT.md honest as the project advances.

Coming from agentlayer v0.5.0?

This is a documented rupture. The old agent-explore → plan → code → verify flow is gone; the new flow is spec → story → implement → verify → review → release. See CHANGELOG.md for the migration note.

Loading

v0.6.0

v0.6.0

Choose a tag to compare

View all tags
@iMark21 iMark21 released this 23 Apr 20:01
v0.6.0
7245933

Added

  • agentlayer init — recommended single-entrypoint command. Detects repository state (fresh vs. already has AI files), asks once which runtime(s) to use, prints a preflight summary (target repo, project type, existing AI files, chosen action, runtimes), confirms, and routes to install or standardize. Path argument is optional; defaults to the current directory. audit, install, and standardize remain available for advanced/scripted use.
  • README recut around the first-use path (agentlayer init). Internal structural detail moved to MANUAL.md.
  • README "Alternative — let your AI install it" section now states the prerequisites explicitly: the assistant must have local read/write access to the repository; cloud-only chat tools do not work.

Changed (UX, breaking in edge cases)

  • agentlayer install now refuses to run on a repository that already has any AI-related file (.ai/, AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, .github/instructions/, .cursor/rules/agentlayer.mdc, or AGENTLAYER.md). The CLI exits non-zero and points at agentlayer standardize. The previous behavior (warn + optional prompt to continue) could leave a repo in a mixed state.
  • agentlayer install --non-interactive without --runtimes now exits non-zero with an explicit error. Previously it silently fell back to a detected default (e.g. codex,claude,generic) and generated adapters the user had not asked for.
  • install and standardize post-run output replaced the prose guidance with visually delimited, copy-paste-ready prompt blocks — one per selected runtime, with wording aligned to MANUAL.md "What To Ask The AI After Install".

Fixed

  • agentlayer install . no longer renders Project Name | . in generated docs. The target path is normalized with cd && pwd -P before any path operation.
  • install.sh now emits a non-fatal warning when run from a volatile path (/tmp, /var/folders, /var/tmp). Clones into those locations produced a symlink that broke on next OS cleanup.
  • README CLI-install example now clones into ~/.agentlayer instead of /tmp/agentlayer to avoid the same footgun.
Loading