Tre defektklasser av samme slag: tall som ser sourcet ut, men ikke er det.
Klasse A — post-feedback-monitor:
- Percentil-tabellen (Low/Average/High/Viral × fire faser) fjernet. Ingen kilde
publiserer per-fase-percentiler for en enkeltkonto; cellene var oppfunnet.
Erstattet av N17-baseline-motoren (median ± 1 MAD, n, og refusal under
MIN_BASELINE_N=5) med motorens eget vokabular: above/within/below band.
- Velocity Score fjernet i sin helhet, inkl. fase-multiplikatorene (5,0x/3,0x/
1,5x/1,0x/0,5x). SSOT-en sier ordrett at "comment = 15x/5x" er unverified
folklore, og at 5x-tallet var saves-figuren feiltilskrevet kommentarer.
Erstattet av rå tellinger + engagement rate slik csv-parser.ts definerer den.
- Output-malen har nå en eksplisitt refusal-gren. Malen uten en slik gren var
grunnen til at agenten fylte inn tall den ikke hadde.
- To folklore-multiplikatorer i Principles ("5x the impact", "worth 15 likes").
Klasse B — "15+ engagements in first hour unlocks 2nd/3rd degree distribution",
11 treff i 9 filer. SSOT-en sier "Directional, not a fixed threshold". Påstanden
overlevde både hardening-gaten og kald-review (log.md:1099 sjekket ~70%-
misattribusjonen, ikke terskelen).
Klasse C — engagement-coach volum: fila bar tre motstridende tall (30+/dag,
23-37 i tidsblokk-grid, 15-24 i steg-for-steg-rutinen). Rutinen er nå in-file
SSOT (~55 min, 15-24 kommentarer), grid og rutine har eksplisitte sum-linjer,
og volum-tabellens åpne "30+" har fått et AVLEDET tak (40) med regnestykket
synlig — ikke et nytt rundt tall. Uverifiserbar superlativ ("110K followers,
#2 global creator") fjernet.
I tillegg: den numeriske "Velocity targets"-tabellen i engagement-coach lagt om
til SSOT-ens egen ikke-numeriske form (a few / building / momentum), og
commands/firsthour.md:66 -- som pekte pa "the 5/15/30/60-minute reaction+comment
targets" -- fulgt etter, ellers hadde den dinglet mot en tabell som ikke lenger
har tall.
docs/hardening/log.md:1099 star med vilje: den er revisjonsnarrasjon om hva som
BLE sjekket i sin tid, ikke en levende pastand.
Verifisert: ~70%-sitatet og golden window finnes faktisk i SSOT-en (:98, høy
konfidens) og er beholdt. Alle ti suiter grønne, floors uendret.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017Pwb1oWLqKB2oBJHSoWNcy
81 load-bearing stier i 16 kommandofiler pinnet til ${CLAUDE_PLUGIN_ROOT}/.
Rene prefikser: 81 inn / 81 ut, ingen linje lagt til eller fjernet.
FASIT-VERIFISERING (premiss-sjekk mot BASELINE, ikke bare HEAD): planens
68 linjer / 17 filer er RIKTIG mot sin egen baseline 882f6ee. HEAD ga 73/18 —
altså ekte kode-drift siden baseline (newsletter.md 11→15, calendar.md 0→1),
ikke en telle-feil som i N19.
SCOPE UTVIDET ETTER GO: planens grep (references|hooks/scripts|scripts) har en
blindsone — skills/ assets/ config/ render/ agents/ commands/ er samme defekt-
klasse og allerede anerkjent som pin-verdig av mønsteret (audit.md:24 og
competitive.md:22 pinner skills/, batch.md:214 og pipeline.md:211 pinner
assets/). Under planens scope kunne dens EGEN verifisering ikke passere:
quick.md:229-230 ville stått upinnet rett over en pinnet linje, og setup.md
(3 load-bearing Read, 0 pins) var ikke i settet i det hele tatt.
Full defektklasse: 117 linjer / 19 filer → 81 pinnet, 36 bevisst urørt.
KLASSIFISERINGSREGEL (utledet av mønsteret, ikke oppfunnet):
- PIN = stien skal åpnes/kjøres/skrives — Read/Reference/See-pekere,
ref-fil-lister, Bash/node/npm, edit-mål.
- PROSA = stien står som sitat bak en påstand, eller som beskrivelse av
oppførsel/plassering. Ingen inline «(see …)» er pinnet noe sted i repoet
(0 av 25 filer) — den grensen er arvet, ikke satt her.
36 BEVISST URØRTE, tre klasser:
1. Inline sitat/attribusjon (17): carousel.md:37 · pipeline.md:70,75 ·
newsletter.md:999,1082,1211,1433 · report.md:273 · video.md:69 ·
react.md:115 · calendar.md:87 · profile.md:28,34 · firsthour.md:112 ·
monetize.md:343,492 · outreach.md:922
2. Beskrivelse av oppførsel/plassering (10): newsletter.md:50,1097,1205,1694,
1744,1944 · report.md:45 · linkedin.md:218 · import.md:121,200
3. newsletter.md fase-tabellens Tooling-kolonne (9): :100,102,105,106,111,112,
113,115,116 — tabellen er et register, og hvert steg pinner sitt eget
faktiske kall i brødteksten.
S13-LINTEN (M0 data-dir): alle assets/-stiene som ble pinnet står eksplisitt i
lintens NEGATIVE13-unntaksliste, og lintens egen kommentar (test-runner.sh:552)
sier at shipped read-only assets SKAL bære ${CLAUDE_PLUGIN_ROOT}.
VERIFISERING: 76 unike pinnede stier hentet ut og resolvet med cwd=/tmp —
75 finnes. Den ene som ikke gjør det, config/personas.local.md, er en
gitignored valgfri fallback («else personas.template.md») som var pinnet på
newsletter.md:205 før denne endringen. Re-grep: gjenstående 36 er utelukkende
prosa, listet over.
Alle ti suiter grønne, alle floors uendret: test-runner 270/0 (269 assertions
>= floor 251) · trends 300/0 · analytics 202/0 · hooks 191/0 · brain 134/0 ·
editions 72/0 · render 63/0 · specifics-bank 45/0 · tests 35/0 ·
contract-gate 33/0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01M31cw43gqiSSDrKzcwUi7L
Every reading now leads with "vs your own baseline", and no verdict is given
when N is too small to carry one.
- stats.ts: median + medianAbsoluteDeviation (robust pair; mean/stddev stay for
the alert engine, which wants outlier sensitivity), rollingBaseline with a
10-post positional window, median ± 1·MAD band floored at 0, and a typed
insufficient-data refusal below MIN_BASELINE_N=5. readAgainstBaseline returns
above/within/below-band, or no-verdict when the baseline was refused.
- baselineByGroup + buildBaselineBlock: per-format/per-pillar baselines, each
judged on its own N; the reported period is excluded from its own baseline and
compared on its median, not its mean.
- queue-join.ts (new): read-only date join supplying format/pillar from the post
queue. Every ambiguity resolves to unlabelled, an entry labels at most one
post, and a missing/broken queue degrades to no labels.
- weekly/monthly reports attach the block unconditionally (refusal included);
optional in the types, so pre-N17 reports load unchanged.
- CLI: report output leads with the baseline; new `baseline [--by format|pillar]`
verb with coverage reporting.
- report.md leads with baseline framing and prints the code's reading rather
than judging the band by eye; WoW loses to the baseline on disagreement.
analyze.md Step 2a tests whether the drop is real before diagnosing it.
TDD: 58 analytics tests written red first (144 -> 202). test-runner Section 16x,
23 unconditional checks + self-test (247 -> 270; anti-erosion floor 228 -> 251).
tsc clean. All suites green: trends 300, brain 134, editions 72,
specifics-bank 45, contract-gate 33, hooks 191, tests 35, render 60.
Also closes the OKF phase-4 scope follow-up in docs/okf-ingestion/plan.md §8
(coord round 2026-07-25): phase 4 tracks the contract, parse is in scope, and
our claim on read_concept/navigate_bundle is withdrawn as unnecessary.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QxvWAjte7vPcF79QeSRvRJ
Reach-splitten (in/out-of-network) er native i LinkedIns post-analytics siden juni
2026, men vises som PROSENT og finnes ikke i CSV-eksporten. Planen antok to
manuelle antall; verifiseringen viste prosent, så modellen er ett felt —
outOfNetworkPct — og in-network er komplementet.
- parseOptionalPercent: egen parser, ikke parseOptionalCount. Komma er desimal
(36,5 -> 36.5, aldri 365), og verdi >100 avvises: i én kolonne kan ikke et
absolutt antall skilles fra en andel, så svaret er unknown, ikke en gjetning.
Blank/ikke-numerisk/negativ -> unknown; ekte 0 beholdes.
- Ett lagret halvpart, kryssjekket: In-network godtas og lagres som komplement;
et transkribert par som ikke summerer til ~100 (±1 avrunding) forkastes som
unknown i stedet for å bli halvveis trodd.
- weightedOutOfNetworkPct: impressions-vektet roll-up (avgOutOfNetworkPct, uke +
måned). Flatt snitt lar en 50-visnings-post slå en på 10 000; poster uten
avlesning ekskluderes, og null vekt gir undefined — aldri 0, aldri NaN.
- Reach inngår ALDRI i engagementRate (distribusjon != engasjement). Rapporten
leser den som akvisisjon (ut) vs resonans (inn), og sier «ikke ført for denne
perioden» framfor å estimere. En reach-innsikt går inn i N15s do-next-kanal.
- Step 7c (A2-F11): rapporten tilbyr diff mot brukerens engagement-patterns.md
med eksplisitt go — aldri stille skriving, aldri inn i den shippede malen.
- Boundary-map (E#9): dwell eksplisitt umålbar, saves partner-gated, reach
native men CSV-eksport uverifisert.
- Reach-frie importer er byte-identiske med før, på skjerm og på disk.
TDD: rødt bevist først (10 feilende), analytics 119 -> 144 tester, tsc ren.
test-runner 232 -> 247 (Section 16w, gulv 213 -> 228). Alle suiter grønne.
CHANGELOG: N15-oppføringen manglet og er backfilt sammen med N16.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QxvWAjte7vPcF79QeSRvRJ
Hardening, multiplier class (S31, batch b). SSOT-reconciliation of unsourced
generic "Nx" reach/growth multipliers asserted as platform fact across commands
and agents. Same discipline as S31a: read-and-show (Read tool, not Bash-tail) ->
edit -> re-grep final; 8-step gate.
5 edits / 5 files (+5/-5):
- report:249 (PDF/Carousels 3.4x reach multiplier) -> top organic format, no
reliable multiplier.
- outreach:652 (collab content 2-3x reach, ref collaborations-guide) -> above-
baseline reach, aligned with the S31a collab scrub.
- engagement-coach:120 (2-3 touchpoints = 3.6x more likely) -> far more likely
(figure unverified).
- strategy-advisor:241 (saves drive 3x faster audience growth) -> faster growth
(figure unverified).
- content-repurposer:591 (Expected reach multiplier: [2-5x original]) -> Expected
reach: above the original (no reliable multiplier).
KEPT (operator-ruled measured-data class — report/hypothesize from the USER's own
analytics, not a platform norm; the number is an illustrative-computed example or
a pure placeholder, and removing it adds no honesty): report:303 ("[format] ...
2x more shares" example), report:335 ("your one carousel got 3x" rendered
example), ab-test:418 ("Your data shows ... 2x ... test whether this holds"),
outreach:1234 ("Average reach multiplier (collab vs solo): [X]x" output field).
KEPT INTACT: engagement-coach:148 SSOT comment ~= 2x a like. OUT (untouched):
strategy-advisor:239 4-5x/week frequency.
VERIFY: re-grep generic-claim targets in the 5 files -> 0; measured-data class +
KEEP/OUT intact; gate scripts/test-runner.sh = 81/0/0 exit 0, counts 29/19/26
+ v0.5.0 unchanged.
Push held: origin = open/ (public namespace), STATE.md must not go there.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016qgzo6rxthw7KuxHjn5vyE
Resolves the orphan-agent audit finding by the locked default: wire all, no deletions, so the agent count stays 19. Per agent, added Task to the target command's allowed-tools and a coherent 'subagent_type: linkedin-studio:<name>' delegation at a real point in the command's flow (not a token grep-match).
Wired (agents 1-9 of 11): video-scripter -> video.md (Step 4); content-optimizer -> post.md (Step 7 refinement) + ab-test.md (2a.4 optimized challenger); analytics-interpreter -> report.md (Step 7, report mode) + analyze.md (Step 2, interpret mode); content-planner -> batch.md (Step 2) + pipeline.md (Step 1); trend-spotter -> batch.md (Step 1) + pipeline.md (Step 1); network-builder -> outreach.md (Step 3a); strategy-advisor -> strategy.md (Step 3); voice-trainer -> setup.md (Step 3a); post-feedback-monitor -> calendar.md (publish action, 48h monitor).
Deferred to their dedicated steps: #10 differentiation-checker -> Step 14 (short-form de-AI gate), #11 engagement-coach -> Step 16 (first-hour command). Namespaced subagent_type form requires a session reload before the wired agents are invokable.
Verify: each of the 9 has >=1 invocation in commands/; structural lint 61/61 (counts 19/26/25/6 intact); agent-fixtures 35/35; hook tests 62/62. Three-doc + version reconciliation deferred to Step 21 per the locked plan [skip-docs].
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wave 3 / Step 10 of the remediation plan (Phase 1 — usable by a non-author), per
research/02.
State what the plugin can and cannot do for a PERSONAL profile, dated 'as of
2026-05', without replacing one false claim with another:
- README.md: new 'Boundaries (as of 2026-05)' section. (a) post-level analytics API
EXISTS but is partner-gated (vetted Community Management app + verified org +
Page) — not self-serve; CSV is the practical floor; saves visible natively
(count-only, ~Sept 2025) with no self-serve API pull. (b) auto-publish is
technically POSSIBLE self-serve (w_member_social) but deliberately NOT built — a
design + ToS choice, explicitly 'not an impossibility' (avoids the new false
'cannot auto-publish' claim). (c) dwell internal-only for organic, not exportable.
- commands/calendar.md: the publish action now states plainly it marks a post YOU
posted manually as published — the tool does not post on your behalf.
- commands/report.md: dated the saves/no-self-serve-API note ('as of 2026-05').
- commands/import.md: dated 'Why CSV' note — API is partner-gated, CSV is the floor.
Verify: grep -niE 'cannot auto-publish|only way to (get|access)' README.md
commands/*.md -> no matches; grep -ni 'as of 2026' README.md -> 2.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wave 2 / Step 7 of the remediation plan (research/02 D2/D4).
The tool parses the LinkedIn analytics CSV export, which has no saves/dwell — and
there is no self-serve API to pull them. Stop implying it tracks them:
- report.md: replace "Saves (10x weight) and expert comments (7-9x) are the
highest-impact signals" with honest wording — saves rank highest in the
engagement ORDER (cite references/algorithm-signals-reference.md, not a restated
coefficient), but are visible only in native LinkedIn post analytics (count-only,
~Sept 2025+) with no self-serve API, so this tool does not auto-track them; dwell
is internal to LinkedIn for organic posts.
- types.ts: document why PostMetrics intentionally omits saves/dwell (no ingest
source) so a future contributor does not "add the missing fields".
- strategy.md: reconcile two saves references (signature-content criterion +
authority scorecard) to say the count is read from native LinkedIn analytics, not
captured by this tool.
No new metric field, no manual-entry feature (operator Q3).
Verify: report.md has no "Saves (10x"/"highest-impact signals" and does say "no
self-serve API"; tsc --noEmit clean; analytics suite 106/106; structural lint
0 failed (report.md cites the reference, so stat-consistency stays green).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wave 2 / Step 4 of the remediation plan (docs/remediation/plan.md).
PRIMARY (the real fresh-clone failure):
- scripts/analytics/node_modules is gitignored, so a fresh clone has neither
tsx nor csv-parse. Surface an idempotent `npm install --silent` prerequisite
at point-of-use in report.md (Step 1b) and import.md (Step 4).
DEVIATION FROM PLAN (correction-in-scope, to satisfy the plan's own Verify gate):
- The plan assumed prepending `npm install` was sufficient. Verified it is NOT:
the commands invoke the CLI with an absolute src/cli.ts path but from the
user's arbitrary CWD, and `node --import tsx` resolves the `tsx` specifier
relative to CWD, not the script. There is no global tsx, so the call still
fails with ERR_MODULE_NOT_FOUND from any CWD other than scripts/analytics.
- Complete fix: invoke the locally-installed tsx by its absolute
node_modules/.bin/tsx path in all CLI calls (report.md x10, import.md x3), so
they resolve from any working directory once the install above has run.
Verified: 0 ERR_MODULE_NOT_FOUND running `report` from /tmp.
SECONDARY (latent correctness / hardening):
- Add findPluginRoot(): walks up to the dir holding .claude-plugin/plugin.json
and anchors getAnalyticsRoot() on it, falling back to the legacy 4-up count.
MEASURED that ../../../../ already resolved to the plugin root from BOTH
src/utils and build/utils (both 4 levels deep), so the plan's "src-vs-build
depth miscalibration" premise was false — this is correct-by-construction
hardening (survives a future source move), not a live-bug fix.
- Reconcile cli.ts usage/help text: `node build/cli.js` -> `node --import tsx
src/cli.ts` (the real runtime).
- Fix report.md troubleshooting: "Verify tsx is available" -> the actual
install command on ERR_MODULE_NOT_FOUND.
Test-first: scripts/analytics/tests/storage-root.test.ts (red on missing
findPluginRoot export, green after). Full suite 106/106, tsc --noEmit clean,
structural lint 0 failed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
BREAKING CHANGE: the marketplace slug, the agent namespace
(linkedin-studio:<agent>), and the runtime state-file path
(~/.claude/linkedin-studio.local.md) all change. Reinstall required;
existing state migrated in place (post metrics, streak, history preserved).
The /linkedin:* commands are unchanged — the command namespace is set
per-command in frontmatter and was always independent of the plugin slug.
Functionality is byte-identical to v2.4.0; this release is pure identity.
- dir + manifests: plugins/linkedin-studio + plugin.json + root marketplace.json
- agent namespace updated in commands/newsletter.md (only functional invoker)
- state path updated in 4 hook scripts + topic-rotation prompt + state template
- catch-all skill dir renamed skills/linkedin-studio (5 functional skills unchanged)
- docs + version bump to 3.0.0 across README badge, CHANGELOG, root README/CLAUDE.md
- historical records (CHANGELOG past entries, docs/ build artifacts,
config-audit v5.0.0 snapshots) intentionally retain the old slug
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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>
