agent-guild 1.3.0__tar.gz → 1.3.2__tar.gz

{agent_guild-1.3.0 → agent_guild-1.3.2}/CHANGELOG.md

@@ -2,6 +2,21 @@
 
 ## [Unreleased]
 
+## [1.3.2] - 2026-10-22
+
+- Cursor and Codex agent copies now refer only to `AGENTS.md` instead of "`CLAUDE.md` / `AGENTS.md`"; Claude Code copies are unchanged.
+- Keep CRLF line endings when appending the rules sections to an existing `AGENTS.md`/`CLAUDE.md`, instead of rewriting the file with LF.
+
+## [1.3.1] - 2026-10-22
+
+- Install Codex skills into the supported `.agents/skills/` discovery path. Reuse existing project skill copies,
+  including supporting files, when adding Codex; legacy `.codex/skills/` installs are preserved as a migration source.
+- Migrate shared rules from `CLAUDE.md` into `AGENTS.md` when adding Cursor or Codex, preserving project customizations,
+  Claude-only sections and the Claude import shim. Warn on conflicting duplicate sections. Dry runs remain read-only.
+- Reuse existing project MCP arguments and environment settings when adding a Codex server, while preserving existing
+  Codex entries. Generated shared rules explicitly tell every tool to read the workflow file.
+- Quote language-coder descriptions as valid YAML, and decode quoted values before converting to Cursor or Codex.
+
 ## [1.3.0] - 2026-10-22
 
 - Cursor and Codex support. The installer detects the tools a project uses (`.claude/` or `CLAUDE.md`, `.cursor/`,

{agent_guild-1.3.0 → agent_guild-1.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: agent-guild
-Version: 1.3.0
+Version: 1.3.2
 Summary: A multi-agent setup for Claude Code, Cursor and Codex (orchestrator + architect, coder, grader, utility subagents) with memory-bank, jevmem and Spec-Driven Development wired in, installed into a project with one command.
 Project-URL: Homepage, https://github.com/illescasDaniel/agent-guild
 Project-URL: Issues, https://github.com/illescasDaniel/agent-guild/issues
@@ -15,6 +15,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Software Development
 Requires-Python: >=3.11
+Requires-Dist: pyyaml<7,>=6.0.3
 Description-Content-Type: text/markdown
 
 # agent-guild
@@ -34,7 +35,8 @@ utility), and three features come wired in:
   - [jev-mem](https://github.com/illescasDaniel/jev-mem): *long-term facts*, recalled by relevance through an MCP
     server and session hooks.
 - **Spec-Driven Development (SDD)**, via [sdd-feature](https://github.com/illescasDaniel/sdd-feature-skill): specs,
-  design, interfaces, implementation and grading, with approval gates between phases. Opt-in per project.
+  design, interfaces, implementation and grading, with approval gates between phases. Included by default; omit it
+  with `--without sdd`.
 
 ```bash
 uvx agent-guild /path/to/project
@@ -60,7 +62,7 @@ uvx agent-guild /path/to/project
 
 | File | Install to (Claude Code) | Role |
 |---|---|---|
-| [development-workflow.md](development-workflow.md) | imported from `~/.claude/CLAUDE.md` | Orchestrator rules: knowledge layers, routing, SDD phase → agent map, briefs, memory protocol |
+| [development-workflow.md](development-workflow.md) | `.agents/development-workflow.md` | Orchestrator rules: knowledge layers, routing, SDD phase → agent map, briefs, memory protocol |
 | [agents/architect.md](agents/architect.md) | `~/.claude/agents/` | Opus, read-only. Plans, SDD Phase 1 design decisions, Phase 2 interfaces, root causes |
 | [agents/coder.md](agents/coder.md) | `~/.claude/agents/` | Sonnet. Scoped implementation; parallel-safe |
 | [agents/code-grader.md](agents/code-grader.md) | `~/.claude/agents/` | Opus, read-only. SDD Phase 5. Body identical to the sdd-feature skill's grader; only the frontmatter differs |
@@ -73,7 +75,10 @@ These are the Claude Code sources; the installer converts them for Cursor and Co
 ### Quick: the installer (per project)
 
 `agent-guild` copies everything into a project (plain copies, not links, so the project can edit them) and is
-safe to re-run: files that differ from the shipped version are skipped unless you pass `--force`.
+safe to re-run: existing files that differ from the selected source are skipped unless you pass `--force`.
+It resolves and validates all sources and configuration in an in-memory plan before writing project files.
+`--dry-run` builds the same plan (including downloads into a temporary directory), without writing to the project.
+Preflight failures leave the project unchanged; filesystem errors during the final writes can still leave a partial install.
 
 ```bash
 uvx agent-guild /path/to/project --dry-run
@@ -86,21 +91,27 @@ uvx agent-guild /path/to/project
 It does, in the project, for each coding tool it finds (see **Tools** below):
 
 - copies the agents in that tool's format and folder (`.claude/agents/*.md`; `.cursor/agents/*.md` with `readonly`
-  instead of `disallowedTools`; `.codex/agents/*.toml`), and one shared `development-workflow.md` next to the first
-  tool's agents;
+  instead of `disallowedTools`; `.codex/agents/*.toml`), and one shared
+  `.agents/development-workflow.md`, explicitly read by Claude Code, Cursor and Codex;
 - copies the `memory-bank`, `jev-memory` and `sdd-feature` skills into that tool's skills folder (`.claude/skills/`,
-  `.cursor/skills/`, `.codex/skills/` for Codex), cloned from GitHub, or from local clones with `--sources-dir DIR`;
-- adds three removable sections to `AGENTS.md`: *Agents and delegation*, *Memory bank* and *Phase Gate Protocol*. If the
-  project has only a `CLAUDE.md`, they go there instead; with neither, `AGENTS.md` is created. When Claude Code is one
-  of the tools, `CLAUDE.md` gets an `@AGENTS.md` import (Claude Code doesn't read `AGENTS.md`). A section that either
-  file already has is not added again;
+  `.cursor/skills/`, `.agents/skills/` for Codex), cloned from GitHub, or from local clones with `--sources-dir DIR`;
+- adds three removable sections: *Agents and delegation*, *Memory bank* and *Phase Gate Protocol*. If `AGENTS.md`
+  exists, that is the target. If only `CLAUDE.md` exists and only Claude Code is selected, it is the target instead.
+  Otherwise, creates `AGENTS.md`. Existing sections in the target are preserved; conflicts with sections in the
+  other instruction file produce warnings. **No developer rules are moved, deleted or migrated between files.**
+  Modern Claude Code (v2.1.277+, with built-in AGENTS support enabled) can read `AGENTS.md` directly when no
+  project/local `CLAUDE.md` takes precedence. Use `--claude-compat` to add an `@AGENTS.md` import for older versions
+  or sessions that prefer `CLAUDE.md`; meaningful existing Claude content is retained. With both files present,
+  the installer warns if Claude may not load the new shared instructions. See [Claude's instruction loading docs](https://code.claude.com/docs/en/memory#agentsmd);
 - adds the pinned jevmem server to the tool's MCP config (`.mcp.json`, `.cursor/mcp.json`, `.codex/config.toml`),
-  merging into existing files;
-- for Claude Code only: adds the jevmem hooks to `.claude/settings.json`, sets `autoMemoryEnabled: false` and the
-  project's model to `sonnet`.
+  merging into existing files. New Codex servers reuse matching project entries from `.mcp.json`, then
+  `.cursor/mcp.json`, before falling back to defaults; existing Codex entries always win;
+- for Claude Code only: adds the jevmem hooks to `.claude/settings.json`. It preserves existing project/local model
+  and auto-memory preferences; only absent preferences default to `sonnet` and `autoMemoryEnabled: false`.
+  `--model` and `--disable-auto-memory` explicitly override the corresponding destination settings.
 
 **Tools.** The installer detects what the project uses: `.claude/` or `CLAUDE.md` → Claude Code, `.cursor/` → Cursor,
-`.codex/` or `.agents/` → Codex; with several, it installs for all of them, and with none, for Claude Code. Override
+`.codex/` or `.agents/skills/` → Codex; with several, it installs for all of them, and with none, for Claude Code. Override
 with `--tools claude,cursor,codex`. Cursor and Codex agents don't carry the Claude model tiering (Cursor gets
 `model: inherit`, Codex inherits the session model) and Codex has no read-only switch for an agent, so the read-only
 agents say it in their instructions. Cursor also reads `.claude/` and `.agents/` folders, so with several tools
@@ -112,12 +123,14 @@ installed it may list a skill twice.
 | `--with coder-python` / `coder-swift` / `coder-typescript` | Add a language coder (repeatable): the generic coder, required to use that language's code-navigation MCP ([codenav-mcp](https://github.com/illescasDaniel/codenav-mcp), [codenav-swift-mcp](https://github.com/illescasDaniel/codenav-swift-mcp), [webnav-ts-mcp](https://github.com/illescasDaniel/webnav-ts-mcp)). Also adds the MCP server to `.mcp.json` (an existing entry is kept) and an `AGENTS.md` rule that routes that language's work to it. The MCP's own prerequisites (uv, a Swift toolchain, Node) are printed after the install |
 | `--coders-only` | With `--with`: install only the language coders (agent, MCP server, `AGENTS.md` rule) and nothing else. After a normal install, the tool detects Python, Swift and TypeScript/JS projects and prints this command for the coders you don't have yet |
 | `--without sdd` / `memory-bank` / `jevmem` | Leave a component out. `sdd` also drops `code-grader` and the gate section; `jevmem` drops its skill, server, hooks and the auto-memory switch |
-| `--model ALIAS` | Project main-session model; default `sonnet` (the per-project alternative to the global setting below), `none` leaves it unset |
+| `--model ALIAS` | Explicitly set the Claude project model. When omitted, preserve project/local preferences and default to `sonnet` only if absent; `none` does not set a model |
+| `--claude-compat` | Add a `CLAUDE.md` import of `AGENTS.md` for older Claude Code or sessions that prefer Claude instruction files. Off by default |
+| `--disable-auto-memory` | Explicitly set `autoMemoryEnabled: false`; otherwise preserve an existing project/local preference |
 | `--import-cursor-skills` | Also copy the project's `.cursor/skills/*` into `.claude/skills/` (needs `claude` among the tools); skills that already exist are kept |
 | `--personal-settings` | Put `--model` and `autoMemoryEnabled` in the git-ignored `.claude/settings.local.json` |
 | `--import-auto-memory` | First import the project's existing auto-memory notes into jevmem |
 | `--keep-auto-memory` | Don't switch auto-memory off |
-| `--sources-dir DIR` | Use local clones named `memory-bank/`, `jev-mem/`, `sdd-feature-skill/` instead of GitHub |
+| `--sources-dir DIR` | Use local clones named `memory-bank/`, `jev-mem/`, `sdd-feature-skill/` instead of the pinned upstream revisions; this is an explicit reproducibility override |
 | `--git-exclude` | List the files this run *creates* in `.git/info/exclude` (local to your clone, never committed), so you can try the setup without it showing in `git status`. Off by default: files are added normally and your git settings apply. Edits to files git already tracks (e.g. an existing `.mcp.json`) can't be hidden; the tool warns about them |
 | `--force`, `--dry-run` | Overwrite edited copies; show the plan without writing |
 
@@ -145,6 +158,15 @@ or `CLAUDE.md` already has), so it is safe to run on a project with its own agen
 - **Skipped files are yours.** Anything the log marks `skipped ... differs` keeps your version. If it is an older or
   customised copy of a shipped one (the `sdd-feature` skill, `code-grader`, `jev-memory`), diff it against the shipped
   file and merge what you want by hand. `--force` replaces it instead.
+- **All tools reuse project sources.** For agents, choose the first existing copy in Claude, Cursor, Codex order;
+  convert it for missing tool copies. Language coders inherit the project's generic coder body. For skills, choose
+  `.claude/skills`, `.cursor/skills`, `.agents/skills`, then legacy `.codex/skills`, and use that source for every
+  tool. Full supporting trees are copied. Existing divergent copies stay protected and produce drift warnings.
+  The selected source is printed, including in dry-runs. These are plain copies; later edits are not synchronized.
+  `--force` deliberately uses shipped sources instead. Codex discovers project skills under `.agents/skills`.
+- **Upstream skills are pinned.** Each release selects exact Git commits in `SKILL_REVISIONS`; fetching verifies
+  the resolved commit. `.agents/skill-sources.json` records the upstream URLs, revisions and content hashes.
+  `--sources-dir` records `local` plus content hashes instead, so local edits are visible in provenance.
 - **New files can land next to yours.** A skill folder you already have keeps its `SKILL.md`, but the shipped files
   that are missing (templates, scripts) are added beside it. If `.claude/skills` is a symlink to `.cursor/skills`, the
   log says so, and the skills are written there.
@@ -175,9 +197,9 @@ or `CLAUDE.md` already has), so it is safe to run on a project with its own agen
   changes.
 - **The grader runs on Opus.** The code it grades was written by Sonnet coders, so a different, stronger model gives
   a more independent review.
-- **SDD is opt-in.** The global workflow uses SDD only when a project's `AGENTS.md` / `CLAUDE.md` adopts the Phase Gate
-  Protocol, or when you ask for the `sdd-feature` skill directly. Projects that don't want gates just leave the rule
-  out.
+- **SDD is included by default.** A standard installation adds its skill, grader and Phase Gate Protocol.
+  Pass `--without sdd` to omit those additions. Existing developer-owned files and rules are not removed by this
+  flag. The workflow activates SDD when the project adopts the protocol or explicitly invokes the skill.
 - **Gates and gate status.** SDD gates stay between the orchestrator and the user. The gate status is recorded in
   `memory/activeContext.md`, so a new session resumes at the right gate.
 

{agent_guild-1.3.0 → agent_guild-1.3.2}/README.md

@@ -15,7 +15,8 @@ utility), and three features come wired in:
   - [jev-mem](https://github.com/illescasDaniel/jev-mem): *long-term facts*, recalled by relevance through an MCP
     server and session hooks.
 - **Spec-Driven Development (SDD)**, via [sdd-feature](https://github.com/illescasDaniel/sdd-feature-skill): specs,
-  design, interfaces, implementation and grading, with approval gates between phases. Opt-in per project.
+  design, interfaces, implementation and grading, with approval gates between phases. Included by default; omit it
+  with `--without sdd`.
 
 ```bash
 uvx agent-guild /path/to/project
@@ -41,7 +42,7 @@ uvx agent-guild /path/to/project
 
 | File | Install to (Claude Code) | Role |
 |---|---|---|
-| [development-workflow.md](development-workflow.md) | imported from `~/.claude/CLAUDE.md` | Orchestrator rules: knowledge layers, routing, SDD phase → agent map, briefs, memory protocol |
+| [development-workflow.md](development-workflow.md) | `.agents/development-workflow.md` | Orchestrator rules: knowledge layers, routing, SDD phase → agent map, briefs, memory protocol |
 | [agents/architect.md](agents/architect.md) | `~/.claude/agents/` | Opus, read-only. Plans, SDD Phase 1 design decisions, Phase 2 interfaces, root causes |
 | [agents/coder.md](agents/coder.md) | `~/.claude/agents/` | Sonnet. Scoped implementation; parallel-safe |
 | [agents/code-grader.md](agents/code-grader.md) | `~/.claude/agents/` | Opus, read-only. SDD Phase 5. Body identical to the sdd-feature skill's grader; only the frontmatter differs |
@@ -54,7 +55,10 @@ These are the Claude Code sources; the installer converts them for Cursor and Co
 ### Quick: the installer (per project)
 
 `agent-guild` copies everything into a project (plain copies, not links, so the project can edit them) and is
-safe to re-run: files that differ from the shipped version are skipped unless you pass `--force`.
+safe to re-run: existing files that differ from the selected source are skipped unless you pass `--force`.
+It resolves and validates all sources and configuration in an in-memory plan before writing project files.
+`--dry-run` builds the same plan (including downloads into a temporary directory), without writing to the project.
+Preflight failures leave the project unchanged; filesystem errors during the final writes can still leave a partial install.
 
 ```bash
 uvx agent-guild /path/to/project --dry-run
@@ -67,21 +71,27 @@ uvx agent-guild /path/to/project
 It does, in the project, for each coding tool it finds (see **Tools** below):
 
 - copies the agents in that tool's format and folder (`.claude/agents/*.md`; `.cursor/agents/*.md` with `readonly`
-  instead of `disallowedTools`; `.codex/agents/*.toml`), and one shared `development-workflow.md` next to the first
-  tool's agents;
+  instead of `disallowedTools`; `.codex/agents/*.toml`), and one shared
+  `.agents/development-workflow.md`, explicitly read by Claude Code, Cursor and Codex;
 - copies the `memory-bank`, `jev-memory` and `sdd-feature` skills into that tool's skills folder (`.claude/skills/`,
-  `.cursor/skills/`, `.codex/skills/` for Codex), cloned from GitHub, or from local clones with `--sources-dir DIR`;
-- adds three removable sections to `AGENTS.md`: *Agents and delegation*, *Memory bank* and *Phase Gate Protocol*. If the
-  project has only a `CLAUDE.md`, they go there instead; with neither, `AGENTS.md` is created. When Claude Code is one
-  of the tools, `CLAUDE.md` gets an `@AGENTS.md` import (Claude Code doesn't read `AGENTS.md`). A section that either
-  file already has is not added again;
+  `.cursor/skills/`, `.agents/skills/` for Codex), cloned from GitHub, or from local clones with `--sources-dir DIR`;
+- adds three removable sections: *Agents and delegation*, *Memory bank* and *Phase Gate Protocol*. If `AGENTS.md`
+  exists, that is the target. If only `CLAUDE.md` exists and only Claude Code is selected, it is the target instead.
+  Otherwise, creates `AGENTS.md`. Existing sections in the target are preserved; conflicts with sections in the
+  other instruction file produce warnings. **No developer rules are moved, deleted or migrated between files.**
+  Modern Claude Code (v2.1.277+, with built-in AGENTS support enabled) can read `AGENTS.md` directly when no
+  project/local `CLAUDE.md` takes precedence. Use `--claude-compat` to add an `@AGENTS.md` import for older versions
+  or sessions that prefer `CLAUDE.md`; meaningful existing Claude content is retained. With both files present,
+  the installer warns if Claude may not load the new shared instructions. See [Claude's instruction loading docs](https://code.claude.com/docs/en/memory#agentsmd);
 - adds the pinned jevmem server to the tool's MCP config (`.mcp.json`, `.cursor/mcp.json`, `.codex/config.toml`),
-  merging into existing files;
-- for Claude Code only: adds the jevmem hooks to `.claude/settings.json`, sets `autoMemoryEnabled: false` and the
-  project's model to `sonnet`.
+  merging into existing files. New Codex servers reuse matching project entries from `.mcp.json`, then
+  `.cursor/mcp.json`, before falling back to defaults; existing Codex entries always win;
+- for Claude Code only: adds the jevmem hooks to `.claude/settings.json`. It preserves existing project/local model
+  and auto-memory preferences; only absent preferences default to `sonnet` and `autoMemoryEnabled: false`.
+  `--model` and `--disable-auto-memory` explicitly override the corresponding destination settings.
 
 **Tools.** The installer detects what the project uses: `.claude/` or `CLAUDE.md` → Claude Code, `.cursor/` → Cursor,
-`.codex/` or `.agents/` → Codex; with several, it installs for all of them, and with none, for Claude Code. Override
+`.codex/` or `.agents/skills/` → Codex; with several, it installs for all of them, and with none, for Claude Code. Override
 with `--tools claude,cursor,codex`. Cursor and Codex agents don't carry the Claude model tiering (Cursor gets
 `model: inherit`, Codex inherits the session model) and Codex has no read-only switch for an agent, so the read-only
 agents say it in their instructions. Cursor also reads `.claude/` and `.agents/` folders, so with several tools
@@ -93,12 +103,14 @@ installed it may list a skill twice.
 | `--with coder-python` / `coder-swift` / `coder-typescript` | Add a language coder (repeatable): the generic coder, required to use that language's code-navigation MCP ([codenav-mcp](https://github.com/illescasDaniel/codenav-mcp), [codenav-swift-mcp](https://github.com/illescasDaniel/codenav-swift-mcp), [webnav-ts-mcp](https://github.com/illescasDaniel/webnav-ts-mcp)). Also adds the MCP server to `.mcp.json` (an existing entry is kept) and an `AGENTS.md` rule that routes that language's work to it. The MCP's own prerequisites (uv, a Swift toolchain, Node) are printed after the install |
 | `--coders-only` | With `--with`: install only the language coders (agent, MCP server, `AGENTS.md` rule) and nothing else. After a normal install, the tool detects Python, Swift and TypeScript/JS projects and prints this command for the coders you don't have yet |
 | `--without sdd` / `memory-bank` / `jevmem` | Leave a component out. `sdd` also drops `code-grader` and the gate section; `jevmem` drops its skill, server, hooks and the auto-memory switch |
-| `--model ALIAS` | Project main-session model; default `sonnet` (the per-project alternative to the global setting below), `none` leaves it unset |
+| `--model ALIAS` | Explicitly set the Claude project model. When omitted, preserve project/local preferences and default to `sonnet` only if absent; `none` does not set a model |
+| `--claude-compat` | Add a `CLAUDE.md` import of `AGENTS.md` for older Claude Code or sessions that prefer Claude instruction files. Off by default |
+| `--disable-auto-memory` | Explicitly set `autoMemoryEnabled: false`; otherwise preserve an existing project/local preference |
 | `--import-cursor-skills` | Also copy the project's `.cursor/skills/*` into `.claude/skills/` (needs `claude` among the tools); skills that already exist are kept |
 | `--personal-settings` | Put `--model` and `autoMemoryEnabled` in the git-ignored `.claude/settings.local.json` |
 | `--import-auto-memory` | First import the project's existing auto-memory notes into jevmem |
 | `--keep-auto-memory` | Don't switch auto-memory off |
-| `--sources-dir DIR` | Use local clones named `memory-bank/`, `jev-mem/`, `sdd-feature-skill/` instead of GitHub |
+| `--sources-dir DIR` | Use local clones named `memory-bank/`, `jev-mem/`, `sdd-feature-skill/` instead of the pinned upstream revisions; this is an explicit reproducibility override |
 | `--git-exclude` | List the files this run *creates* in `.git/info/exclude` (local to your clone, never committed), so you can try the setup without it showing in `git status`. Off by default: files are added normally and your git settings apply. Edits to files git already tracks (e.g. an existing `.mcp.json`) can't be hidden; the tool warns about them |
 | `--force`, `--dry-run` | Overwrite edited copies; show the plan without writing |
 
@@ -126,6 +138,15 @@ or `CLAUDE.md` already has), so it is safe to run on a project with its own agen
 - **Skipped files are yours.** Anything the log marks `skipped ... differs` keeps your version. If it is an older or
   customised copy of a shipped one (the `sdd-feature` skill, `code-grader`, `jev-memory`), diff it against the shipped
   file and merge what you want by hand. `--force` replaces it instead.
+- **All tools reuse project sources.** For agents, choose the first existing copy in Claude, Cursor, Codex order;
+  convert it for missing tool copies. Language coders inherit the project's generic coder body. For skills, choose
+  `.claude/skills`, `.cursor/skills`, `.agents/skills`, then legacy `.codex/skills`, and use that source for every
+  tool. Full supporting trees are copied. Existing divergent copies stay protected and produce drift warnings.
+  The selected source is printed, including in dry-runs. These are plain copies; later edits are not synchronized.
+  `--force` deliberately uses shipped sources instead. Codex discovers project skills under `.agents/skills`.
+- **Upstream skills are pinned.** Each release selects exact Git commits in `SKILL_REVISIONS`; fetching verifies
+  the resolved commit. `.agents/skill-sources.json` records the upstream URLs, revisions and content hashes.
+  `--sources-dir` records `local` plus content hashes instead, so local edits are visible in provenance.
 - **New files can land next to yours.** A skill folder you already have keeps its `SKILL.md`, but the shipped files
   that are missing (templates, scripts) are added beside it. If `.claude/skills` is a symlink to `.cursor/skills`, the
   log says so, and the skills are written there.
@@ -156,9 +177,9 @@ or `CLAUDE.md` already has), so it is safe to run on a project with its own agen
   changes.
 - **The grader runs on Opus.** The code it grades was written by Sonnet coders, so a different, stronger model gives
   a more independent review.
-- **SDD is opt-in.** The global workflow uses SDD only when a project's `AGENTS.md` / `CLAUDE.md` adopts the Phase Gate
-  Protocol, or when you ask for the `sdd-feature` skill directly. Projects that don't want gates just leave the rule
-  out.
+- **SDD is included by default.** A standard installation adds its skill, grader and Phase Gate Protocol.
+  Pass `--without sdd` to omit those additions. Existing developer-owned files and rules are not removed by this
+  flag. The workflow activates SDD when the project adopts the protocol or explicitly invokes the skill.
 - **Gates and gate status.** SDD gates stay between the orchestrator and the user. The gate status is recorded in
   `memory/activeContext.md`, so a new session resumes at the right gate.
 

{agent_guild-1.3.0 → agent_guild-1.3.2}/docs/manual_installation.md

@@ -22,7 +22,7 @@ printf '\n@/path/to/agent-guild/development-workflow.md\n' >> ~/.claude/CLAUDE.m
 
 Orchestrator model: either globally, in `~/.claude/settings.json`, replace `"model": "opusplan"` with
 `"model": "sonnet"`; or only for a project, with `"model": "sonnet"` in its `.claude/settings.json` (or
-`.claude/settings.local.json` to keep it personal). The installer does the latter by default.
+`.claude/settings.local.json` to keep it personal). The installer defaults an absent project model to Sonnet and preserves existing project/local preferences.
 
 jevmem's own settings (API key or local model, `~/.jevmem/config.jsonc`) and its embedding model are per machine
 either way:

{agent_guild-1.3.0 → agent_guild-1.3.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "agent-guild"
-version = "1.3.0"
+version = "1.3.2"
 description = "A multi-agent setup for Claude Code, Cursor and Codex (orchestrator + architect, coder, grader, utility subagents) with memory-bank, jevmem and Spec-Driven Development wired in, installed into a project with one command."
 readme = "README.md"
 license = "MIT"
@@ -16,7 +16,7 @@ classifiers = [
   "Topic :: Software Development",
 ]
 requires-python = ">=3.11"
-dependencies = []
+dependencies = ["PyYAML>=6.0.3,<7"]
 
 [project.urls]
 Homepage = "https://github.com/illescasDaniel/agent-guild"

{agent_guild-1.3.0 → agent_guild-1.3.2}/src/agent_guild/cli.py

@@ -51,7 +51,7 @@ def build_parser() -> argparse.ArgumentParser:
     p.add_argument("project", type=Path, help="path to the project's root")
     p.add_argument("--tools", metavar="LIST",
                    help=f"comma-separated tools to install for: {', '.join(TOOLS)}. Default: the ones the project already "
-                        "uses (.claude/ or CLAUDE.md, .cursor/, .codex/ or .agents/), or claude when none is found. Each gets "
+                        "uses (.claude/ or CLAUDE.md, .cursor/, .codex/ or .agents/skills/), or claude when none is found. Each gets "
                         "agents and skills in its own format and folder, and an MCP config")
     p.add_argument("--without", action="append", default=[], choices=COMPONENTS, metavar="COMPONENT",
                    help=f"leave a component out (repeatable): {', '.join(COMPONENTS)}. "
@@ -64,11 +64,17 @@ def build_parser() -> argparse.ArgumentParser:
     p.add_argument("--coders-only", action="store_true",
                    help="with --with: install only the language coders (agent, MCP server, routing rule) and leave "
                         "everything else in the project untouched")
-    p.add_argument("--model", default="sonnet", metavar="ALIAS",
-                   help="the project's main-session model (default: sonnet; 'none' leaves it unset)")
+    p.add_argument("--model", metavar="ALIAS",
+                   help="explicitly set the Claude model; otherwise preserve existing settings, defaulting to sonnet "
+                        "only when absent; 'none' leaves it unset")
+    p.add_argument("--claude-compat", action="store_true",
+                   help="add a CLAUDE.md @AGENTS.md import for older Claude Code or sessions preferring CLAUDE.md")
     p.add_argument("--personal-settings", action="store_true",
                    help="write --model and autoMemoryEnabled to .claude/settings.local.json instead of the committed settings.json")
-    p.add_argument("--keep-auto-memory", action="store_true", help="don't set autoMemoryEnabled=false")
+    memory = p.add_mutually_exclusive_group()
+    memory.add_argument("--keep-auto-memory", action="store_true", help="don't set autoMemoryEnabled=false")
+    memory.add_argument("--disable-auto-memory", action="store_true",
+                        help="explicitly set autoMemoryEnabled=false; otherwise preserve an existing preference")
     p.add_argument("--import-auto-memory", action="store_true",
                    help="first import the project's existing Claude auto-memory notes into jevmem (needs jevmem configured)")
     p.add_argument("--import-cursor-skills", action="store_true",
@@ -102,7 +108,10 @@ def main(argv: list[str] | None = None) -> int:
         without=frozenset(args.without),
         with_coders=frozenset(args.with_coders),
         coders_only=args.coders_only,
-        model=None if args.model.lower() == "none" else args.model,
+        model=None if args.model is None or args.model.lower() == "none" else args.model,
+        set_default_model=args.model is None,
+        claude_compat=args.claude_compat,
+        disable_auto_memory=args.disable_auto_memory,
         keep_auto_memory=args.keep_auto_memory,
         personal_settings=args.personal_settings,
         import_auto_memory=args.import_auto_memory,

{agent_guild-1.3.0 → agent_guild-1.3.2}/src/agent_guild/files.py

@@ -17,6 +17,29 @@ class Ctx:
     warnings: list[str] = field(default_factory=list)
     new_paths: list[tuple[Path, bool]] = field(default_factory=list)  # (topmost new path, is a directory)
     edited_existing: list[Path] = field(default_factory=list)
+    pending: dict[Path, bytes] = field(default_factory=dict)
+
+    def exists(self, path: Path) -> bool:
+        return path in self.pending or path.exists()
+
+    def read(self, path: Path) -> bytes:
+        return self.pending[path] if path in self.pending else path.read_bytes()
+
+    def write(self, path: Path, data: bytes):
+        if path.exists() and not path.is_file():
+            raise SystemExit(f"error: {path} must be a file")
+        for parent in path.parents:
+            if parent.exists() and not parent.is_dir():
+                raise SystemExit(f"error: {parent} must be a directory")
+        self.pending[path] = data
+
+    def apply(self):
+        """Apply only after every source and generated configuration has been checked."""
+        if self.dry_run:
+            return
+        for path, data in self.pending.items():
+            path.parent.mkdir(parents=True, exist_ok=True)
+            path.write_bytes(data)
 
     def log(self, status: str, path: Path | str, note: str = "") -> None:
         shown = path
@@ -43,8 +66,8 @@ class Ctx:
 
 def write_bytes(ctx: Ctx, dest: Path, data: bytes) -> str:
     """Create `dest`, or replace it only with --force. Never overwrites a file that differs by default."""
-    if dest.exists():
-        if dest.read_bytes() == data:
+    if ctx.exists(dest):
+        if ctx.read(dest) == data:
             ctx.log("unchanged", dest)
             return "unchanged"
         if not ctx.force:
@@ -55,9 +78,7 @@ def write_bytes(ctx: Ctx, dest: Path, data: bytes) -> str:
     else:
         status = "created"
         ctx.track_new(dest)
-    if not ctx.dry_run:
-        dest.parent.mkdir(parents=True, exist_ok=True)
-        dest.write_bytes(data)
+    ctx.write(dest, data)
     ctx.log(status if not ctx.dry_run else f"would {status.removesuffix('d')}", dest)
     return status
 
@@ -69,11 +90,11 @@ def copy_tree(ctx: Ctx, src: Path, dest: Path) -> None:
             write_bytes(ctx, dest / item.relative_to(src), item.read_bytes())
 
 
-def read_json(path: Path) -> tuple[dict[str, Any], str]:
+def read_json(path: Path, ctx: Ctx | None = None) -> tuple[dict[str, Any], str]:
     """Return (data, indent). Missing file -> ({}, two spaces). Matches the file's existing indent style."""
-    if not path.exists():
+    if not (ctx.exists(path) if ctx else path.exists()):
         return {}, "  "
-    text = path.read_text(encoding="utf-8")
+    text = ctx.read(path).decode("utf-8") if ctx else path.read_text(encoding="utf-8")
     if not text.strip():
         return {}, "  "
     try:
@@ -90,12 +111,10 @@ def write_json(ctx: Ctx, path: Path, data: dict[str, Any], indent: str, changes:
     if not changes:
         ctx.log("unchanged", path)
         return
-    verb = "edit" if path.exists() else "create"
+    verb = "edit" if ctx.exists(path) else "create"
     if verb == "edit":
         ctx.edited_existing.append(path)
     else:
         ctx.track_new(path)
-    if not ctx.dry_run:
-        path.parent.mkdir(parents=True, exist_ok=True)
-        path.write_text(json.dumps(data, indent=indent, ensure_ascii=False) + "\n", encoding="utf-8")
+    ctx.write(path, (json.dumps(data, indent=indent, ensure_ascii=False) + "\n").encode("utf-8"))
     ctx.log(f"would {verb}" if ctx.dry_run else ("edited" if verb == "edit" else "created"), path, "+ " + ", ".join(changes))