ros/spec-kit
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update config

Browse Source
This commit is contained in:
Den Delimarsky 🌺
2025-09-20 10:10:23 -07:00
parent caee341af9
commit d7d2c145c7
4 changed files with 4 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -262,14 +262,6 @@ The CLI will check if you have Claude Code, Gemini CLI, Cursor CLI, Qwen CLI, op
specify init <project_name> --ai claude --ignore-agent-tools specify init <project_name> --ai claude --ignore-agent-tools
``` ```
> [!NOTE]
> Codex CLI specifics
> - `specify init --ai codex` seeds `commands/*.md` in your repo and automatically mirrors them into `${CODEX_HOME:-~/.codex}/prompts` so Codex picks up `/specify`, `/plan`, and `/tasks` immediately.
> - If Codex was running during installation, restart the CLI once so it reloads the refreshed slash commands.
> - Codex persists its working memory in `AGENTS.md`; if you do not see that file yet, run `codex /init` once inside the project to generate it.
> - When Codex is configured to run helper scripts, open `codex /approvals` and enable “Run shell commands”.
> - If you point `CODEX_HOME` at the project (for per-repo isolation) the installer adds ignore rules for Codex session artifacts to `.gitignore`; adjust them as needed for your workflow.
### **STEP 1:** Establish project principles ### **STEP 1:** Establish project principles
Go to the project folder and run your AI agent. In our example, we're using `claude`. Go to the project folder and run your AI agent. In our example, we're using `claude`.

4
templates/commands/plan.md
View File

@@ -14,10 +14,10 @@ Given the implementation details provided as an argument, do this:
- Success criteria and acceptance criteria - Success criteria and acceptance criteria
- Any technical constraints or dependencies mentioned - Any technical constraints or dependencies mentioned
3. Read the constitution at `memory/constitution.md` to understand constitutional requirements. 3. Read the constitution at `/memory/constitution.md` to understand constitutional requirements.
4. Execute the implementation plan template: 4. Execute the implementation plan template:
- Load `templates/plan-template.md` (already copied to IMPL_PLAN path) - Load `/templates/plan-template.md` (already copied to IMPL_PLAN path)
- Set Input path to FEATURE_SPEC - Set Input path to FEATURE_SPEC
- Run the Execution Flow (main) function steps 1-9 - Run the Execution Flow (main) function steps 1-9
- The template is self-contained and executable - The template is self-contained and executable

2
templates/commands/specify.md
View File

@@ -5,7 +5,7 @@ scripts:
ps: scripts/powershell/create-new-feature.ps1 -Json "{ARGS}" ps: scripts/powershell/create-new-feature.ps1 -Json "{ARGS}"
--- ---
The text the user typed after `/specify` in the triggering message **is** the feature description. Assume you always have it available in this conversation even if `{ARGS}` appears literally below. Do not ask the user to repeat it unless they provided a truly empty command. The text the user typed after `/specify` in the triggering message **is** the feature description. Assume you always have it available in this conversation even if `{ARGS}` appears literally below. Do not ask the user to repeat it unless they provided an empty command.
Given that feature description, do this: Given that feature description, do this:

2
templates/commands/tasks.md
View File

@@ -21,7 +21,7 @@ Given the context provided as an argument, do this:
- Generate tasks based on what's available - Generate tasks based on what's available
3. Generate tasks following the template: 3. Generate tasks following the template:
- Use `templates/tasks-template.md` as the base - Use `/templates/tasks-template.md` as the base
- Replace example tasks with actual tasks based on: - Replace example tasks with actual tasks based on:
* **Setup tasks**: Project init, dependencies, linting * **Setup tasks**: Project init, dependencies, linting
* **Test tasks [P]**: One per contract, one per integration scenario * **Test tasks [P]**: One per contract, one per integration scenario