@dalzoubi/dev-agents-sync 2.0.24 → 2.0.25
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +31 -21
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -51,9 +51,9 @@ npx --yes @dalzoubi/dev-agents-sync@1 init --targets codex
|
|
|
51
51
|
|
|
52
52
|
Codex is **opt-in only**. Unlike other targets there is no filesystem signal to detect (there is no `.codex/` directory), so `codex` is never auto-selected — you must pass `--targets codex` explicitly. You can combine it with other targets, e.g. `--targets claude,codex`.
|
|
53
53
|
|
|
54
|
-
**Output shape.** `init --targets codex` writes
|
|
54
|
+
**Output shape.** `init --targets codex` writes one directory-per-skill file per agent at `.agents/skills/<agent>/SKILL.md` — covering the full `define`/`deliver` topology listed under [Agents](#agents) — plus a thin root `AGENTS.md` index. Codex discovers these by scanning from the working directory up to the repo root, so each agent lives at its own `.agents/skills/<agent>/SKILL.md` path. Every file carries the managed-by marker, and `update` and `check` scope to these paths exactly like the other targets.
|
|
55
55
|
|
|
56
|
-
**Standalone.** Codex is a first-class standalone target. Each emitted `SKILL.md` bundles the workflow support docs it references, so a Codex-only install does **not** need `.claude/skills/*.md`, `.cursor/`, or any other target files to run the
|
|
56
|
+
**Standalone.** Codex is a first-class standalone target. Each emitted `SKILL.md` bundles the workflow support docs it references, so a Codex-only install does **not** need `.claude/skills/*.md`, `.cursor/`, or any other target files to run the agent workflows.
|
|
57
57
|
|
|
58
58
|
**Model-invoked, not slash commands.** Codex Agent Skills are model-invoked: a Codex user triggers an agent through `/skills`, a `$<name>` mention, or implicit selection by the model — *not* by typing a literal `/define`-style slash command the way Claude commands work. This is an accepted approximation of the slash-command UX the other targets provide; the agent content is the same, only the invocation differs.
|
|
59
59
|
|
|
@@ -140,35 +140,45 @@ With `--no-hooks-wiring`, the hook scripts are still installed under `.claude/ho
|
|
|
140
140
|
|
|
141
141
|
## Agents
|
|
142
142
|
|
|
143
|
-
Syncing installs
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
143
|
+
Syncing installs the `define`/`deliver` agent topology: two user-facing
|
|
144
|
+
orchestrators plus their namespaced workers (12 agents in total). Each agent has
|
|
145
|
+
a matching slash command (for example `/define`), and every agent reads the
|
|
146
|
+
project's `CLAUDE.md` / `AGENTS.md` at the start of a session.
|
|
147
|
+
|
|
148
|
+
**`define` namespace — spec authoring:**
|
|
148
149
|
|
|
149
150
|
| Agent | Command | Purpose |
|
|
150
151
|
|---|---|---|
|
|
151
|
-
| `define` | `/define` |
|
|
152
|
-
| `
|
|
153
|
-
| `
|
|
154
|
-
| `
|
|
155
|
-
| `
|
|
156
|
-
|
|
152
|
+
| `define` | `/define` | Q&A orchestrator. Runs a one-question-at-a-time Q&A to turn a vague ask into spec/plan/tasks artifacts, then auto-runs `define-analyze`. Read-only on source code. |
|
|
153
|
+
| `define-spec` | `/define-spec` | Writes `spec.md` (requirements). |
|
|
154
|
+
| `define-plan` | `/define-plan` | Writes `plan.md` (technical plan + authoritative working branch). |
|
|
155
|
+
| `define-tasks` | `/define-tasks` | Writes `tasks.md` (slices + estimates). |
|
|
156
|
+
| `define-analyze` | `/define-analyze` | Readiness gate. Scans for unresolved `[NEEDS CLARIFICATION]` markers, checks structure and estimates, and emits a `PASS` or `BLOCKED` verdict. Read-only; reports only. |
|
|
157
|
+
|
|
158
|
+
**`deliver` namespace — autonomous TDD delivery:**
|
|
157
159
|
|
|
158
|
-
|
|
159
|
-
|
|
160
|
+
| Agent | Command | Purpose |
|
|
161
|
+
|---|---|---|
|
|
162
|
+
| `deliver` | `/deliver <spec-path> [--auto] [--verbose] [--max-parallel=N]` | Autonomous TDD orchestrator. Drives the four-step cycle `deliver-test → deliver-solution → deliver-refactor → deliver-validate` across an approved spec's slices, with per-slice cycle budgets and recurrence detection; finalizes with `deliver-preflight`. Pauses on recurring failures, budget exhaustion, or interrupt. |
|
|
163
|
+
| `deliver-solution` | `/deliver-solution` | Implementation and debugging worker. Builds features from an approved spec, debugs, and runs fix-build-test loops. Pauses at checkpoints and won't commit unless asked. |
|
|
164
|
+
| `deliver-test` | `/deliver-test` | Test and quality worker. Writes failing-first unit/integration/regression tests and adds edge cases. Edits **test files only** — never production code. |
|
|
165
|
+
| `deliver-refactor` | `/deliver-refactor` | Behavior-preserving refactor worker. Improves production-source structure after tests are green; no new features, never test files. |
|
|
166
|
+
| `deliver-validate` | `/deliver-validate` | Review and risk worker. Audits the current branch before a PR for security, regressions, accessibility, performance, spec conformance, and coverage gaps. Read-only; outputs a severity-ranked report. |
|
|
167
|
+
| `deliver-preflight` | `/deliver-preflight` | Pre-review gate. Runs lint, unit tests, and build if relevant, then summarizes what changed. Does not push or open a PR. |
|
|
168
|
+
| `deliver-document` | `/deliver-document` | End-of-feature docs/CHANGELOG finalization; flips the spec's Status to Shipped. |
|
|
160
169
|
|
|
161
170
|
### When to use which
|
|
162
171
|
|
|
163
172
|
| You want to… | Use |
|
|
164
173
|
|---|---|
|
|
165
174
|
| Scope a new feature or change before writing code | `/define` |
|
|
166
|
-
| Confirm a spec is ready to build from | `/analyze` |
|
|
167
|
-
| Build from an approved spec
|
|
168
|
-
| Add test coverage or pin a bug with a failing test | `/test` |
|
|
169
|
-
|
|
|
170
|
-
|
|
|
171
|
-
|
|
|
175
|
+
| Confirm a spec is ready to build from | `/define-analyze` |
|
|
176
|
+
| Build from an approved spec or debug | `/deliver-solution` |
|
|
177
|
+
| Add test coverage or pin a bug with a failing test | `/deliver-test` |
|
|
178
|
+
| Clean up structure once the scoped tests are green | `/deliver-refactor` |
|
|
179
|
+
| Audit risk right before opening a PR | `/deliver-validate` |
|
|
180
|
+
| Build an approved spec largely hands-off, slice by slice | `/deliver` |
|
|
181
|
+
| Run lint/tests/build before review | `/deliver-preflight` |
|
|
172
182
|
|
|
173
183
|
## Common Flags
|
|
174
184
|
|
package/package.json
CHANGED