docs(agents): scope documentation pointers by task and state completion criteria (#7593)

Restructures AGENTS.md so contributors read the references that match their
change instead of a blanket four-file reading list, and states explicit
completion/verification criteria in place of the compressed ten-rule summary.

Verified before merge: all 12 referenced paths exist on master (README,
CONTRIBUTING, docs/CONTRACTS.md, docs/GUIDELINES.md, CHANGELOG, ARCHITECTURE,
TESTING, docs/onboarding.md, docs/troubleshooting.md, docs/rfcs/README.md,
docs/UIUX-GUIDE.md, DESIGN.md), the referenced ./scripts/test.sh exists, and
the ten rules removed from AGENTS.md are all preserved in docs/GUIDELINES.md —
which the new version still points to. Net -2 lines, so no information is lost.

Co-authored-by: steveafrost <steveafrost@users.noreply.github.com>

AGENTS.md

@@ -5,25 +5,23 @@ repository. Keep it project-specific and safe to publish. Do not put personal
 machine setup, private network details, credentials, tokens, or local-only
 workflow notes here.
 
-## Read first
+## Documentation by task
 
-Before making changes, read:
+Use the references that match the change; there is no blanket reading list for
-
+unrelated work. Keep subsystem-specific safety and contract requirements below.
-1. `README.md`
-2. `CONTRIBUTING.md`
-3. `docs/CONTRACTS.md`
-4. `CHANGELOG.md`
-
-For architecture, testing, or setup work, also read the matching reference:
 
+- `README.md` for product behavior, setup, usage, and the docs index
+- `CONTRIBUTING.md` for contribution scope, PR format, and review requirements
+- `docs/CONTRACTS.md` to find the contract/RFC for the subsystem being changed
+- `docs/GUIDELINES.md` for bug-class coverage, state ownership, and evidence standards
+- `CHANGELOG.md` for release-history questions; ordinary PRs do not edit it
 - `ARCHITECTURE.md` for design constraints and current module layout
-- `TESTING.md` for local verification commands and manual test guidance
+- `TESTING.md` for local verification commands and relevant manual checks
 - `docs/onboarding.md` for first-run onboarding behavior
 - `docs/troubleshooting.md` for diagnostic flows
 - `docs/rfcs/README.md` for larger RFCs and state/durability contracts
-
+- `docs/UIUX-GUIDE.md` and `DESIGN.md` for layout, interaction flow, themes,
-For UI or UX work, read `docs/UIUX-GUIDE.md` and `DESIGN.md` before
+  chat rendering, and composer chrome
-changing layout, interaction flow, themes, chat rendering, or composer chrome.
 
 ## Onboarding and reinstall support
 
@@ -73,39 +71,34 @@ Follow that checklist's safety rules:
   in both the `rsync` and `cp -a` paths — `/opt/hermes` may contain subdirectories
   with restricted permissions (e.g. `.playwright/`).
 
-## Before you open a PR — the change guidelines
+## Completion and verification
 
-Read [`docs/GUIDELINES.md`](docs/GUIDELINES.md) in full before non-trivial work. It is the
+A change is ready for review when:
-distilled set of habits that get a change merged in one review round instead of several. The
-compressed form:
 
-1. **Fix the class, not the instance.** A bug usually has siblings — other call sites, backends,
+- The requested scope is implemented, with related call sites and lifecycle
-   companion endpoints, layouts, exit paths. Find them all and fix the shared chokepoint, or name
+  paths covered or explicitly identified as out of scope; unrelated cleanup is absent.
-   the ones you left out of scope.
+- Behavior changes have observable regression evidence where practical, including
-2. **Trace one authoritative value end-to-end** (`input → normalize → decision → action → persist →
+  proof that a bug-fix test fails before the fix and passes after it. Evidence covers
-   cleanup`); the code that *decides* and the code that *acts* must use the same resolved value.
+  affected and neighboring tests, not only new tests.
-3. **When you can't confirm something, fail closed and say so.** Never take the permissive branch on
+- State changes identify the authoritative value and its owner, use that value
-   uncertainty; never report a failure as success. "Unknown" is not "allowed."
+  through decision, action, and persistence, and account for cleanup on every exit.
-4. **Enumerate the state-space before editing** — entry point, backend, item count (0/1/many), every
+  Fallbacks and defaults extend the existing mechanism rather than duplicate it.
-   lifecycle exit (success/error/cancel/replace/teardown), auth on/off, concurrency, hostile input —
+- UI changes include before/after evidence at desktop and narrow widths and
-   and cover each or mark it out of scope. Most redo rounds are one un-considered dimension.
+  cover relevant mobile interactions; controls fit their frequency of use.
-5. **Assume inputs and check-then-use gaps are adversarial** — validate at the point of use (hold a
+- Relevant docs are current. The PR body follows `CONTRIBUTING.md`, includes
-   handle, don't re-resolve a path), scope caches by complete identity, handle crafted input.
+  `Contract Routing` (and `Contract Change` for intentional contract changes)
-6. **A test must fail before your fix and pass after it.** Assert observable behavior, not a source
+  where required by `docs/CONTRACTS.md`, and reports actual commands, outcomes,
-   string or a mock of the thing under test; use multiple items if selection is what's being tested.
+  assumptions, and anything not verified. Mocks are not proof of external behavior.
-7. **Name the owner of every piece of state and prove it's released on every exit** (success, error,
-   cancel, replace, shrink, teardown) — not just the happy path.
-8. **Fallbacks/defaults are contracts — extend the mechanism, don't copy it.** Editing N parallel
-   blocks identically means you missed a chokepoint (e.g. new copy goes in the `en` locale only).
-9. **The diff is the task and nothing else.** Extras go in the PR description, not the diff; run the
-   affected + neighboring tests before opening.
-10. **A visible control costs attention on every visit** — place it by frequency of use and by where
-    mainstream chat apps put the equivalent, not by where your diff already is; verify with
-    before/after images at desktop and narrow widths.
 
-Show the work in the PR body: the siblings you found, proof the test failed before the fix, the
+Within the requested scope, you may run local tests with disposable fixtures,
-verification run, before/after images for visible changes, and an explicit list of what you could
+fix failures caused by the change, and rerun affected tests without asking for
-not verify.
+approval at each step. Use `./scripts/test.sh` for pytest as specified above.
+This permission applies only with confirmed isolated state and no live
+credentials or services; the runner manages Python dependencies but is not a
+network sandbox. It does not authorize modifying real state, handling credentials,
+restarting existing services, or exposing the app beyond localhost. Those actions
+require explicit human approval and the onboarding safety rules still apply.
+If verification is blocked, report the blocker rather than claim completion.
 
 ## Local state and secrets
 
@@ -113,6 +106,11 @@ Hermes WebUI can read and write real agent state, sessions, workspaces,
 credentials, and cron data. Treat local validation as potentially destructive
 unless you have confirmed the active state directories.
 
+For authority, capability, identity, or containment checks, fail closed when
+safety cannot be confirmed: unknown is not allowed. Validate adversarial inputs
+at the point of use, account for check-then-use races, and scope caches by the
+complete identity so profiles and sessions cannot leak into each other.
+
 Prefer isolated trial state for experiments:
 
 ```bash