fix(linkedin-studio): S22 harden outreach — add missing Bash grant, drop orphan WebFetch+Write, re-source fabricated pod/DM stats to SSOT

Outreach is the first command in the hardening queue that both delegates to an
agent (network-builder) and mutates real state (recordOutreachContact), so the
weight fell on axis-d. Five fixes across two files (operator-approved scope
extension to the SSOT-diverging guide source):

- allowed-tools: ADD Bash (Step 8c runs `node state-updater.mjs --record-outreach`
  and needs it — firsthour precedent grants Bash for the same pattern; the command
  promised a mutation it couldn't execute), DROP orphan WebFetch + Write grants
  (zero body use; :410/:1040 "Write a post" is prose). Now
  Read·Glob·WebSearch·AskUserQuestion·Task·Bash.
- Step 7 pod-warning (axis-b'): replaced fabricated magnitudes ("30-55% reach
  reduction", "shadow suppression", "credibility score", "penalizes",
  "Post-March 2025", "low dwell") with the SSOT statement
  (algorithm-signals-reference.md:98 — demote out of "Most Relevant" / scope to
  own network / restrict repeat offenders) + cite.
- :652 DM-amplification "2-3x first-hour" (axis-b'): re-attributed 2-3x to collab
  reach (where SSOT places it), kept the first-hour effect qualitative.
- collaborations-guide.md:349-370 (axis-b', scope extension): same SSOT rewrite of
  the "March 2025 Crackdown" section so the Step 7 fix can't be re-rendered from a
  stale reference (dropped "shadow banning ALL future content / 90+ days / 6+
  months / permanent penalty" + speculative detection methods).

Verify: re-grep both files clean (orphans/fabricated stats NONE, Bash :21, SSOT
text in place); recordOutreachContact throwaway-fixture 10/10 PASS (additive,
$-safe, newest-first, untouched undeclared fields); test-runner 81/0/0 exit 0;
counts 29/19 unchanged (.md-only).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016qgzo6rxthw7KuxHjn5vyE

references/collaborations-guide.md

@@ -346,28 +346,22 @@ Include collaborator content in Featured:
 
 ---
 
-## Engagement Pods: March 2025 Crackdown
+## Engagement Pods: An Active Crackdown
 
-LinkedIn's March 2025 update dramatically increased pod detection capabilities.
+LinkedIn runs an active engagement-pod crackdown and keeps expanding how it
+detects them (see `algorithm-signals-reference.md` — the algorithm SSOT).
 
-### Detection Methods Now in Use
+### How Pods Get Detected
 
-- Browser extension tracking (LinkedIn detects pod-organizing extensions)
-- Pattern analysis on comment timing (simultaneous engagement = red flag)
+- Comment-timing analysis (simultaneous engagement = red flag)
 - Cross-account engagement correlation (same people always first to engage)
-- Linguistic fingerprinting (similar comment patterns across accounts)
+- Reciprocal engagement loops (the same accounts engaging each other)
 
-### Consequences
+### What LinkedIn Does
 
-- Shadow banning affects ALL future content (not just the flagged post)
-- Reach penalties persist for 90+ days
-- Can take 6+ months to recover algorithmic trust
-- Some accounts never fully recover
-
-### The Math Has Changed
-
-- **Old:** Pod engagement boosted first-hour metrics → more reach
-- **New:** Pod engagement triggers detection → permanent reach penalty
+- Pod-style auto-comments are demoted out of "Most Relevant"
+- Their reach is scoped to your own network — it stops spreading beyond it
+- Repeat offenders get restricted
 
 **Pods now hurt more than help.** Build authentic communities instead:
 - Genuine relationships with 3-5 aligned creators