From 1a85798d3938f6aecc0c6a73da43ffad1687fdec Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Sat, 2 May 2026 10:50:33 +0000
Subject: [PATCH] docs: fix label list in uninstall steps and update
 contributing test section

- README.md: replace nonexistent `state:in-progress` with the actual
  `agent-team:reviewed` label in the agent-team uninstall instructions
  (the skill creates 7 labels: agent-team, agent-team:reviewed, and
  state:plan-needed/impl-needed/review-needed/done/blocked)
- CONTRIBUTING.md: replace "There is no automated test harness" with an
  accurate summary of the three-tier test suite in tests/, linking to
  tests/README.md for full details; tier-1+tier-2 already run in CI

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 CONTRIBUTING.md | 17 ++++++++++++++++-
 README.md       |  2 +-
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 1c2721e..3d76521 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -74,7 +74,22 @@ Edit the relevant `SKILL.md` or data file. Test by running the skill locally wit
 
 ## Testing
 
-There is no automated test harness for skills — they are instruction sets interpreted by Claude Code, not code with unit tests. The validation steps are:
+The repo ships a three-tier test suite under `tests/`. Full details are in [tests/README.md](tests/README.md). The short version:
+
+```bash
+./tests/run-tests.sh           # tier-1 skill tests + tier-2 invariants (~5 min)
+./tests/run-tests.sh --verbose # show per-assertion output
+```
+
+| Tier | What it tests | Speed |
+|---|---|---|
+| 2 | Grep/filesystem invariants (no Claude invocation) | <1s |
+| 1 | Each skill loads and describes itself correctly | ~1–2min per skill |
+| 3 | Full pipeline run on `verkyyi/agent-team-playground` | ~20–35min, opt-in |
+
+Tier-1 and tier-2 also run in CI on every PR (`ci-tests.yml`).
+
+Additional validation steps for specific changes:
 
 1. **Load the plugin**: `claude --plugin-dir .` — confirm no startup errors.
 2. **Run the skill manually**: invoke `/discover-workflows` or `/install-workflow` and walk through the flow.
diff --git a/README.md b/README.md
index e18e51a..f3206aa 100644
--- a/README.md
+++ b/README.md
@@ -80,7 +80,7 @@ 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: `gh label delete agent-team` and `gh label delete agent-team:reviewed`, plus `gh label delete state:<name>` for each of `plan-needed`, `impl-needed`, `review-needed`, `done`, and `blocked`.
 
 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.