openspeccer

Files (61)

• .gitignore
• CHANGELOG.md
• CLAUDE.md
• Makefile
• SKILL.md
• app.js · assets/web/
• export.js · assets/web/
• index.html · assets/web/
• lib.js · assets/web/
• md.js · assets/web/
• site-export.js · assets/web/
• style.css · assets/web/
• ui.js · assets/web/
• LICENSES.txt · assets/web/vendor/
• SOURCES.md · assets/web/vendor/
• hooks.mjs · assets/web/vendor/
• htm.mjs · assets/web/vendor/
• marked.esm.js · assets/web/vendor/
• mermaid.min.js · assets/web/vendor/
• preact.mjs · assets/web/vendor/
• agents.js · assets/web/views/
• burndown.js · assets/web/views/
• changes.js · assets/web/views/
• commands.js · assets/web/views/
• config.js · assets/web/views/
• dashboard.js · assets/web/views/
• guide.js · assets/web/views/
• schemas.js · assets/web/views/
• search.js · assets/web/views/
• specs.js · assets/web/views/
• timeline.js · assets/web/views/
• pyproject.toml
• __init__.py · scripts/openspeccer/
• agents.py · scripts/openspeccer/
• cli.py · scripts/openspeccer/
• commands.py · scripts/openspeccer/
• config.py · scripts/openspeccer/
• docs.py · scripts/openspeccer/
• repo.py · scripts/openspeccer/
• reqdiff.py · scripts/openspeccer/
• scan.py · scripts/openspeccer/
• schemas.py · scripts/openspeccer/
• search.py · scripts/openspeccer/
• server.py · scripts/openspeccer/
• vcs.py · scripts/openspeccer/
• yamlish.py · scripts/openspeccer/
• serve.py · scripts/
• helpers.py · tests/
• test_cli.py · tests/
• test_cli_parity.py · tests/
• test_commands.py · tests/
• test_config.py · tests/
• test_docs.py · tests/
• test_export_md.py · tests/
• test_md.py · tests/
• test_repo.py · tests/
• test_reqdiff.py · tests/
• test_review_cases.py · tests/
• test_schemas.py · tests/
• test_server.py · tests/
• …and 1 more

SKILL.md (first lines)

openspeccer is a read-only local web dashboard for any repository holding an `openspec/` directory. It is stdlib Python and needs no install. Run `<this-skill-dir>/scripts/serve.py --help` for every option.

## Workflow

1. Create a task per step below, each with its completion criterion, then work through them.
2. Find the repo: pass the user's repo path, or omit it and the script searches upward from the current directory for `openspec/`.
3. For a status question ("what's in flight?"), run `serve.py <repo> --summary` and answer from its output. For one change's artifacts and tasks, use `--change <slug>`. `--json` prints the whole snapshot; send it to a file and read only what you need. Done once you have answered, with no server started.
4. If the user wants the dashboard, start `serve.py <repo>` as a background process. Done when a line containing `serving <name> at <url>` appears, or the process exits; on exit, report its stderr to the user.
5. Always give the user the URL. Pass `--no-open` in headless or remote sessions, and when re-running against a server that is already up.
6. To stop it, end the background process you started, using the PID or task handle you captured at launch.

## Gotchas

- Re-running for the same repo reuses the running server and prints `already serving`, so step 4 is safe to repeat.
- A server you did not start (no handle from this session) belongs to the user. Leave it running.
- The OpenSpec CLI is optional and only feeds the Schemas and Commands pages. Without it, only project schemas show and Commands is empty. For a CLI outside `PATH`, set `OPENSPECCER_OPENSPEC_BIN`.
- Active changes from every git worktree are aggregated by default.
- The page updates as files change, so there is nothing to refresh after editing artifacts.

From sammcj/agentic-coding, Apache-2.0.

More from sammcj/agentic-coding