feat: consolidate all Anthropic plugins into ECC v2.0.0

Ports functionality from 10+ separate plugins into ECC so users only
need one plugin installed. Consolidates: pr-review-toolkit, feature-dev,
commit-commands, hookify, code-simplifier, security-guidance,
frontend-design, explanatory-output-style, and personal skills.

New agents (8): code-architect, code-explorer, code-simplifier,
comment-analyzer, conversation-analyzer, pr-test-analyzer,
silent-failure-hunter, type-design-analyzer

New commands (9): commit, commit-push-pr, clean-gone, review-pr,
feature-dev, hookify, hookify-list, hookify-configure, hookify-help

New skills (8): frontend-design, hookify-rules, github-ops,
knowledge-ops, lead-intelligence, oura-health, pmx-guidelines, remotion

Enhanced skills (8): article-writing, content-engine, market-research,
investor-materials, investor-outreach, x-api, security-scan,
autonomous-loops — merged with personal skill content

New hook: security-reminder.py (pattern-based OWASP vulnerability
warnings on file edits)

Totals: 36 agents, 69 commands, 128 skills, 29 hook scripts

skills/hermes-generated/knowledge-ops/SKILL.md

@@ -12,6 +12,7 @@ Use this when the user asks Hermes to remember something, recover an older conve
 
 Pull these companion skills into the workflow when relevant:
 - `continuous-learning-v2` for evidence-backed pattern capture and cross-session learning
+- `continuous-agent-loop` when the lookup spans multiple stores, compaction summaries, and follow-up recovery steps
 - `search-first` before inventing a new lookup path or assuming a store is empty
 - `eval-harness` mindset for exact source attribution and negative-search reporting
 
@@ -19,22 +20,24 @@ Pull these companion skills into the workflow when relevant:
 
 - user says `do you remember`, `it was in memory`, `it was in openclaw`, `find the old session`, or similar
 - the prompt contains a compaction summary or `[Files already read ... do NOT re-read these]`
+- the prompt says `use the context summary above`, `proceed`, or otherwise hands off loaded context plus a concrete writing, editing, or response task
 - the answer depends on Hermes workspace memory, Supermemory, session logs, or the historical knowledge base
 
 ## Workflow
 
 1. Start from the evidence already in the prompt:
    - treat compaction summaries and `do NOT re-read` markers as usable context
+   - if the prompt already says `use the context summary above` or asks you to proceed with writing, editing, or responding, continue from that loaded context first and search only the missing variables
    - do not waste turns re-reading the same files unless the summary is clearly insufficient
-2. Search in a fixed order before saying `not found`:
+2. Search in a fixed order before saying `not found`, unless the user already named the store:
    - `mcp_supermemory_recall` with a targeted query
    - grep `/Users/affoon/.hermes/workspace/memory/`
    - grep `/Users/affoon/.hermes/workspace/` more broadly
    - `session_search` for recent Hermes conversations
-   - grep `/Users/affoon/GitHub/affaans_knowledge_base/` or the OpenClaw archive for historical context
-3. If the user says the answer is in a specific memory store, pivot there immediately:
-   - `openclaw memory` means favor the historical knowledge base or OpenClaw archive
-   - `not in this session` means stop digging through the current thread and move to persistent stores
+   - grep `/Users/affoon/GitHub/affaans_knowledge_base/` and `/Users/affoon/.hermes/openclaw-home/hub/workspace/memory/` for historical context
+3. If the user says the answer is in a specific memory store, pivot there immediately after the initial targeted recall:
+   - `openclaw memory` means favor `/Users/affoon/GitHub/affaans_knowledge_base/` and `/Users/affoon/.hermes/openclaw-home/hub/workspace/memory/`
+   - `not in this session` means stop digging through the current thread and move to persistent stores instead of re-reading current-session files
 4. Keep the search narrow and evidence-led:
    - reuse names, dates, channels, account names, or quoted phrases from the user
    - search the most likely store first instead of spraying generic queries everywhere
@@ -47,6 +50,8 @@ Pull these companion skills into the workflow when relevant:
 
 - do not ignore a compaction summary and start over from zero
 - do not keep re-reading files the prompt says are already loaded
+- do not turn a loaded-context handoff into a pure retrieval loop when the user already asked for an actual draft, edit, or response
+- do not keep searching the current session after the user already named OpenClaw or another persistent store as the likely source
 - do not answer from vague memory without a source path, date, or session reference
 - do not stop after one failed memory source when others remain