Teach workflow skills in specialist playbooks

2026-04-04 14:39:10 -04:00
parent 2ddda436a9
commit e5c616e021
5 changed files with 62 additions and 30 deletions
--- a/cron/jobs.json
+++ b/cron/jobs.json
@@ -3,7 +3,7 @@
    {
      "id": "9e0624269ba7",
      "name": "Triage Heartbeat",
-      "prompt": "Scan all Timmy_Foundation/* repos for unassigned issues, auto-assign to appropriate agents based on labels/complexity",
+      "prompt": "Scan Timmy_Foundation/the-nexus, timmy-home, timmy-config, and hermes-agent for unassigned issues. Route them using the audited lane map, avoid duplicate backlog churn, and escalate governing or cross-boundary work to Timmy or Allegro instead of assigning blindly.",
      "schedule": {
        "kind": "interval",
        "minutes": 15,
@@ -25,13 +25,17 @@
      "state": "paused",
      "paused_at": "2026-03-24T16:23:01.614552-04:00",
      "paused_reason": "Dashboard repo frozen - loops redirected to the-nexus",
-      "skills": [],
-      "skill": null
+      "skills": [
+        "triage",
+        "deduplication",
+        "dispatch"
+      ],
+      "skill": "issue-triager"
    },
    {
      "id": "e29eda4a8548",
      "name": "PR Review Sweep",
-      "prompt": "Check all Timmy_Foundation/* repos for open PRs, review diffs, merge passing ones, comment on problems",
+      "prompt": "Review open PRs in Timmy_Foundation/the-nexus, timmy-home, timmy-config, and hermes-agent. Post severity-ordered findings, protect sensitive control surfaces, and auto-merge only low-risk PRs that are fully verified and non-governing.",
      "schedule": {
        "kind": "interval",
        "minutes": 30,
@@ -53,13 +57,17 @@
      "state": "paused",
      "paused_at": "2026-03-24T16:23:02.731437-04:00",
      "paused_reason": "Dashboard repo frozen - loops redirected to the-nexus",
-      "skills": [],
-      "skill": null
+      "skills": [
+        "review",
+        "governance",
+        "merge-safety"
+      ],
+      "skill": "pr-reviewer"
    },
    {
      "id": "a77a87392582",
      "name": "Health Monitor",
-      "prompt": "Check Ollama is responding, disk space, memory, GPU utilization, process count",
+      "prompt": "Check Hermes gateway health, local inference surface, pipeline freshness, disk space, memory, and active process count. Prefer the live Hermes sidecar reality over any stale Ollama-era assumptions.",
      "schedule": {
        "kind": "interval",
        "minutes": 5,
@@ -83,7 +91,7 @@
    {
      "id": "5e9d952871bc",
      "name": "Agent Status Check",
-      "prompt": "Check which tmux panes are idle vs working, report utilization",
+      "prompt": "Check workflow utilization instead of tmux panes: unassigned issues, review queue pressure, overloaded assignees, and stale PRs across the core Timmy Foundation repos.",
      "schedule": {
        "kind": "interval",
        "minutes": 10,
@@ -105,13 +113,17 @@
      "state": "paused",
      "paused_at": "2026-03-24T16:23:03.869047-04:00",
      "paused_reason": "Dashboard repo frozen - loops redirected to the-nexus",
-      "skills": [],
-      "skill": null
+      "skills": [
+        "queue-hygiene",
+        "review-pressure",
+        "dispatch"
+      ],
+      "skill": "ops-workflow-status"
    },
    {
      "id": "36fb2f630a17",
      "name": "Hermes Philosophy Loop",
-      "prompt": "Hermes Philosophy Loop: File issues to Timmy_Foundation/hermes-agent",
+      "prompt": "Review Hermes-agent against the current doctrine from the-nexus issue #542. Only file narrowly scoped issues that materially improve Heartbeat, Harness, or Portal Interface, and collapse duplicates instead of generating philosophy drift.",
      "schedule": {
        "kind": "interval",
        "minutes": 1440,
@@ -133,4 +145,4 @@
    }
  ],
  "updated_at": "2026-03-24T16:23:03.869797-04:00"
-}
+}
--- a/playbooks/bug-fixer.yaml
+++ b/playbooks/bug-fixer.yaml
@@ -21,6 +21,8 @@ trigger:

 repos:
  - Timmy_Foundation/the-nexus
+  - Timmy_Foundation/timmy-home
+  - Timmy_Foundation/timmy-config
  - Timmy_Foundation/hermes-agent

 steps:
@@ -40,16 +42,20 @@ system_prompt: |

  YOUR ISSUE: #{{issue_number}} — {{issue_title}}

-  APPROACH (test-first):
+  APPROACH (prove-first):
  1. Read the bug report. Understand the expected vs actual behavior.
-  2. Write a test that REPRODUCES the bug (it should fail).
-  3. Fix the code so the test passes.
-  4. Run tox -e unit — ALL tests must pass, not just yours.
-  5. Commit: fix: <description> Fixes #{{issue_number}}
-  6. Push, create PR.
+  2. Reproduce the failure with the repo's existing test or verification tooling whenever possible.
+  3. Add a focused regression test if the repo has a meaningful test surface for the bug.
+  4. Fix the code so the reproduced failure disappears.
+  5. Run the strongest repo-native verification you can justify — all relevant tests, not just the new one.
+  6. Commit: fix: <description> Fixes #{{issue_number}}
+  7. Push, create PR, and summarize verification plus any residual risk.

  RULES:
-  - Never fix a bug without a test that proves it was broken.
+  - Never claim a fix without proving the broken behavior and the repaired behavior.
+  - Prefer repo-native commands over assuming tox exists.
+  - If the issue touches config, deploy, routing, memories, playbooks, or other control surfaces, flag it for Timmy review in the PR.
  - Never use --no-verify.
-  - If you can't reproduce the bug, comment on the issue with what you tried.
+  - If you can't reproduce the bug, comment on the issue with what you tried and what evidence is still missing.
  - If the fix requires >50 lines changed, decompose into sub-issues.
+  - Do not widen the issue into a refactor.
--- a/playbooks/refactor-specialist.yaml
+++ b/playbooks/refactor-specialist.yaml
@@ -21,6 +21,8 @@ trigger:

 repos:
  - Timmy_Foundation/the-nexus
+  - Timmy_Foundation/timmy-home
+  - Timmy_Foundation/timmy-config
  - Timmy_Foundation/hermes-agent

 steps:
@@ -43,15 +45,18 @@ system_prompt: |
  RULES:
  - Lines of code is a liability. Delete as much as you create.
  - All changes go through PRs. No direct pushes to main.
-  - Run tox -e format before committing. Run tox -e unit after.
+  - Use the repo's own format, lint, and test commands rather than assuming tox.
+  - Every refactor must preserve behavior and explain how that was verified.
+  - If the change crosses repo boundaries, model-routing, deployment, or identity surfaces, stop and ask for narrower scope.
  - Never use --no-verify on git commands.
  - Conventional commits: refactor: <description> (#{{issue_number}})
  - If tests fail after 2 attempts, STOP and comment on the issue.
+  - Refactors exist to simplify the system, not to create a new design detour.

  WORKFLOW:
  1. Read the issue body for specific file paths and instructions
  2. Understand the current code structure
-  3. Make the refactoring changes
-  4. Format: tox -e format
-  5. Test: tox -e unit
-  6. Commit, push, create PR
+  3. Name the simplification goal before changing code
+  4. Make the refactoring changes
+  5. Run formatting and verification with repo-native commands
+  6. Commit, push, create PR with before/after risk summary
--- a/playbooks/security-auditor.yaml
+++ b/playbooks/security-auditor.yaml
@@ -21,6 +21,8 @@ trigger:

 repos:
  - Timmy_Foundation/the-nexus
+  - Timmy_Foundation/timmy-home
+  - Timmy_Foundation/timmy-config
  - Timmy_Foundation/hermes-agent

 steps:
@@ -46,12 +48,16 @@ system_prompt: |
  6. Dependencies with known CVEs (check requirements.txt/package.json)
  7. Missing input validation
  8. Overly permissive file permissions
+  9. Privilege drift in deploy, orchestration, memory, cron, and playbook surfaces
+  10. Places where private data or local-only artifacts could leak into tracked repos

  OUTPUT FORMAT:
  For each finding, file a Gitea issue with:
    Title: [security] <severity>: <description>
-    Body: file + line, description, recommended fix
+    Body: file + line, description, why it matters, recommended fix
    Label: security

  SEVERITY: critical / high / medium / low
  Only file issues for real findings. No false positives.
+  Do not open duplicate issues for already-known findings; link the existing issue instead.
+  If a finding affects sovereignty boundaries or private-data handling, flag it clearly as such.
--- a/playbooks/test-writer.yaml
+++ b/playbooks/test-writer.yaml
@@ -21,6 +21,8 @@ trigger:

 repos:
  - Timmy_Foundation/the-nexus
+  - Timmy_Foundation/timmy-home
+  - Timmy_Foundation/timmy-config
  - Timmy_Foundation/hermes-agent

 steps:
@@ -42,14 +44,15 @@ system_prompt: |

  RULES:
  - Write tests that test behavior, not implementation details.
-  - Use tox -e unit to run tests. Never run pytest directly.
+  - Use the repo's own test entrypoints; do not assume tox exists.
  - Tests must be deterministic. No flaky tests.
  - Conventional commits: test: <description> (#{{issue_number}})
-  - If the module is hard to test, file an issue explaining why.
+  - If the module is hard to test, explain the design obstacle and propose the smallest next step.
+  - Prefer tests that protect public behavior, migration boundaries, and review-critical workflows.

  WORKFLOW:
  1. Read the issue for target module paths
  2. Read the existing code to understand behavior
  3. Write focused unit tests
-  4. Run tox -e unit — all tests must pass
-  5. Commit, push, create PR
+  4. Run the relevant verification commands — all related tests must pass
+  5. Commit, push, create PR with verification summary and coverage rationale