Bind the layers slices 1 (store) and 2a (config) built: trend-spotter goes from
an amnesiac, niche-hardcoded scanner to a persistent, generic engine.
- Tools: drop the `tools:` allowlist (inherit all session tools incl. any
research MCP) + `disallowedTools: Write, Edit, NotebookEdit`. An explicit
allowlist would block every MCP unless its mcp__server__tool name were
hardcoded — which breaks "prefer whatever MCP the user connected, hardcode
nothing". WebSearch+WebFetch stay as the always-available floor; Bash runs
the deterministic store CLI. (CC mechanic verified vs code.claude.com/docs.)
- Store-wiring (de-amnesia): query prior history before polling; persist every
kept trend through scripts/trends `add` (dedup/union preserved — a raw Write
would bypass it). Mirrors how specifics-bank is wired from the command layer.
- MCP-first routing: read the profile's "### Research Tooling" declaration,
prefer a declared MCP, fall back to the floor, fail soft. No hardcoded names.
- Scoring -> SSOT: replace the inline matrix/composite/bands with a pointer to
references/trend-scoring-modes.md (kortform default, long-form on request).
- Sources from config: replace the hardcoded vendor/outlet list + query bank
with a read of trends/sources.md (user override) -> trends-sources.template.md
(shipped default).
- CI: new test-runner Section 16 (trends-store binding guard, floor 21,
KTG-only skip) mirroring the specifics-bank guard; assertion-count renumbered
to Section 17. Gate 84 -> 85/0/0. model-consistency green (model unchanged).
Reload required: the tools-grant change takes effect only after a session reload.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBMKqPSVbvSZHtQ4heM1UY
Final sub-pass of the S29 plugin-wide terminology scrub. The canonical reference file is
renamed and every functional pointer updated atomically in one commit. The file's in-file
title/headers were already FORM A-scrubbed in S29c (H1 reads "Content Angles"), so S29e is a
pure rename + pointer update — no FORM A remained in the file.
Rename: references/thought-leadership-angles.md -> references/content-angles.md (git mv).
Pointers updated (17 files, 29 occurrences) — token "thought-leadership-angles" -> "content-angles":
- references/ (2): ai-content-framework, glossary
- agents/ (7): content-repurposer, strategy-advisor, network-builder, content-planner,
trend-spotter, video-scripter, differentiation-checker
- commands/ (6): pipeline, video, post, competitive, react, batch
- skills/ (1): linkedin-content-creation/SKILL
- docs/ (1, forward-looking): integration-test-guide
Left URØRT per the standing S29 decision (history = honest record of a past state, not a
runtime load): CHANGELOG.md, docs/hardening/log.md, docs/hardening/plan.md. STATE.md untouched
here (rewritten at session end).
Verify: no thought-leadership-angles* file remains; references/content-angles.md present; zero
residual "thought-leadership-angles" in commands/agents/references/skills/integration-test-guide;
structure gate scripts/test-runner.sh 81/0/0 exit 0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016qgzo6rxthw7KuxHjn5vyE
Second sub-pass of the S29 plugin-wide terminology scrub: the banned brand phrase
"thought leadership" (FORM A) removed from the agent surface. 17 edits across 6 agents
(strategy-advisor, content-planner, voice-trainer, network-builder, differentiation-checker,
trend-spotter). Vocabulary consistent with S29a: "thought leadership angle(s)" → "content
angle(s)"; "thought leadership" (positioning/practice) → "authority …"; the whole "Value Test"
family → "Authority Value Test".
15 in-file phrase occurrences (space-grep) + 2 abbreviated "TL Value Test" instances found
during the header anchor-check (trend-spotter:192/:257, TL = Thought Leadership) — surfaced as
an addendum and operator-approved before edit, scope not expanded silently. The
differentiation-checker:47 web-search query thought leadership → expert insights
(functional-keyword judgment-call, operator option b).
Scope (operator-locked, inherits S29a): FORM A only. FORM B ("thought leader(s)" as role,
agents = 2) untouched. The 11 thought-leadership-angles.md filename pointers deferred to S29e.
Verify: FORM A in agents/ = NONE; abbreviated TL = NONE; FORM B unchanged (2); filename
pointers unchanged (11); diff 6 files 1:1; gate 81/0/0; counts 29/19/26/6 + v0.5.0 unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016qgzo6rxthw7KuxHjn5vyE
Reconcile external-link and topic-relevance reach-loss framing to the algorithm-signals
SSOT across 6 files (10 edits): body links "correlate with lower reach" (LinkedIn denies
an intentional penalty), topic relevance is a positive ranking input with no quantified
off-topic figure. 3 plan-cited lines + 7 same-class siblings surfaced during verify.
Bucket B (link-penalty lines in linkedin-formats.md) folded into S28; Bucket D (other
unsourced reach-coefficients: -68%/-25%/-15-25%/-30-50%/55%) queued as new S30. Engagement-
pod + AI-slop "penalized" framing left intact (officially confirmed). Gate 81/0/0; counts
29/19 unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016qgzo6rxthw7KuxHjn5vyE
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.
New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.
Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.
Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
