docs: fix agent-team docs after dispatch-input hardening (#69)

CONTRIBUTING.md

@@ -85,7 +85,7 @@ Never test by committing untested changes to `main`. The installed workflows run
 
 ## Workflow files
 
-The `.github/workflows/` directory contains seven dogfooded workflows. These are managed by `gh aw` — do not edit `.lock.yml` files by hand except to apply the OAuth tweak described in [skills/install-workflow/auth.md](skills/install-workflow/auth.md).
+The `.github/workflows/` directory contains six workflows: three dogfooded agentic workflows (`daily-repo-status`, `update-docs`, `weekly-research`) and three standard CI workflows (`agentics-maintenance`, `ci-tests`, `copilot-setup-steps`). Only the agentic workflows are managed by `gh aw` — do not edit their `.lock.yml` files by hand except to apply the OAuth tweak described in [skills/install-workflow/auth.md](skills/install-workflow/auth.md).
 
 If a workflow `.md` source needs changing:
 

README.md

@@ -80,7 +80,16 @@ To remove workflows this plugin installed into your target repo:
 
 - `gh aw remove <workflow>` for each installed workflow (deletes both the `.md` source and the compiled `.lock.yml`), then commit the deletion.
 - `gh secret delete CLAUDE_CODE_OAUTH_TOKEN` — or `ANTHROPIC_API_KEY`, whichever path you used — to unset the auth secret.
-- For `agent-team` specifically, also delete the seven labels: `gh label delete agent-team` plus `gh label delete state:<name>` for each of `plan-needed`, `impl-needed`, `review-needed`, `done`, `blocked`, and `in-progress`.
+- For `agent-team` specifically, also delete the seven labels:
+  ```bash
+  gh label delete agent-team
+  gh label delete state:plan-needed
+  gh label delete state:impl-needed
+  gh label delete state:review-needed
+  gh label delete state:done
+  gh label delete state:blocked
+  gh label delete agent-team:reviewed
+  ```
 
 Nothing else is persisted — the plugin writes only to your target repo (under user approval) and holds no local state outside Claude Code's own plugin directory.
 

catalog/agent-team/README.md

@@ -111,7 +111,10 @@ Then apply the OAuth token tweak to each `.lock.yml` per [`skills/install-workfl
 
 - **Concurrency**: each workflow uses `concurrency: group: agent-team-issue-${issue_number}` so only one role runs at a time per issue.
 - **Max iterations**: default 3 (reviewer kickback → implementer). The counter lives on the `iteration` input passed through the dispatch chain, bumped exclusively by the reviewer on kickback.
-- **Input propagation**: planner / implementer / reviewer must fail loudly if required `workflow_dispatch` inputs are missing. Do not rely on label search or recent-activity inference as a fallback.
+- **Input propagation**: planner / implementer / reviewer fail loudly if required `workflow_dispatch` inputs are missing **or** still appear as unresolved template literals (e.g. the raw string `${{ github.event.inputs.issue_number }}`). Never infer a missing value from labels, recent activity, or search results. Exact behavior:
+  - `issue_number` present but empty/unresolved → add `state:blocked`, post `🛑 agent-team: workflow_dispatch inputs were not propagated. Re-dispatch with valid inputs.`
+  - `issue_number` itself missing → call `missing_data` / `report_incomplete` to fail loudly.
+  - `pr_number` (implementer only) blank or still a literal → treated as "no existing PR"; a new branch + PR is created. Both are valid first-dispatch states.
 - **Non-UI only**: no screenshot capture. Reviewer validates via tests/CI status + reading the diff.
 - **Cost**: a single task can easily spend 4× the tokens of a monolithic workflow. Set `timeout-minutes` conservatively and monitor the first few runs.
 - **No auto-merge**: the reviewer approves but never merges. Humans merge.