fix: add honest status reporting protocol to prevent false validation claims

AI agents were marking services as "validated" or "working" after only
running structural tests (build + --help) without any live interaction
against the real external system. This adds a mandatory section to
AGENTS.md that:

- Distinguishes "built", "structural test", and "validated" as distinct
  states with concrete examples
- Prohibits using "validated"/"working"/"done"/"complete" for credential-
  dependent services until a live operation succeeds
- Requires obtaining credentials and running real read/write operations
  before claiming completion
- Enforces todo-list honesty: items can only be marked completed when
  their acceptance criterion is actually met

💘 Generated with Crush

Assisted-by: Crush:glm-5.2

AGENTS.md

@@ -100,6 +100,31 @@ For each agent, verify in order:
 
 **CRITICAL**: Items 1-3 are NON-NEGOTIABLE. Do not mark a server as "working" without protocol validation.
 
+## Honest Status Reporting (MANDATORY)
+
+AI agents MUST distinguish between these distinct states and never blur them:
+
+| State | Meaning | Example |
+|-------|---------|---------|
+| **Built** | Image/container compiles or assembles without errors | `docker build` exits 0 |
+| **Structural test passed** | Binary runs, `--help` works, error paths return correct codes | CLI prints usage, missing-env exits 2 |
+| **Validated / Working** | A **live** interaction against a real external system succeeded | `whoami` returns real user data from the live API |
+
+**A structural test is NOT validation.** Building + `--help` does not make a tool "validated" or "working".
+
+### Rules
+
+1. **Never use the words "validated", "working", "done", or "complete"** for any service that depends on external credentials or a live endpoint until you have:
+   - **Obtained** the real credentials / endpoint (not placeholder/dummy values).
+   - **Executed** at least one live read or write operation against the real system.
+   - **Observed** a successful response with real data.
+
+2. **Never claim validation is impossible then state the tool is done.** If you lack credentials, say *"blocked — needs credentials to validate"* and obtain them. Do not imply completion by omission.
+
+3. **Todo list honesty:** A todo item may only be marked `completed` when its acceptance criterion has actually been met. "Build and test" requires a passing test, not a successful build alone.
+
+4. **When blocked on validation:** Stop, state the exact blocker (e.g. "need DISCOURSE_API_KEY to run live whoami test"), and obtain it before proceeding or declaring the task done.
+
 ## MCP Handshake Command
 
 ```bash