The LAST second-brain slice; the S0–S3e arc is now complete.
(b) Retire the dead, zero-reader content-history.md across its 8 plumbing
surfaces: the flaky Stop-hook writer prose, the template (git-rm'd), the
migrate-data.mjs B1 MOVE entry + its test assertions, .gitignore, the gate
SC2_CLASSES guard, the data-path ref-doc, and a session-start comment. SC1
grep = 0; migrate suite 5/5 (R8 idempotency demonstrated).
(c) `brain reconcile` — read-side triple-post reconciliation joining silo 1
(## Recent Posts, auto-tracked creation) to the silo 2↔3 graph, surfacing the
coverage gap: posts created via the plugin but never `brain ingest`-ed. New
pure core scripts/brain/src/reconcile.ts (parseRecentPosts tracks the WRITER
format state-updater.mjs:116, NOT the date-only pruner; reconcileRecentPosts
matches hook→record.body→graph for the in-graph/in-brain-only/orphaned tiers;
loadRecentPosts reads STATE_FILE via the canonical getStateFile() chain — a new
cross-seam read, the state file lives outside the brain dataRoot). Wired as the
`brain reconcile` CLI subcommand (inline parsePublishedRecord loader, not the
body-less listPublished). Read-only: never writes the state silo.
Tests (verified live): gate 99/0/0 (ASSERT floor 82→84; new Section 16f
self-test + CLI grep) · brain 127/127 (floor 114→127, +13 reconcile) · hook
suite 136/136. SC4/SC6 end-to-end run is a real behavioural pass (STATE_FILE
seam read + fallback). Honest limit: read-side cannot reconstruct un-captured
specifics/trends — auto-capture is the flagged follow-up.
Brief/plan: docs/second-brain/{brief,plan}-sb-s3e.md (fbad29d). Go-before-code
gate cleared (operator: retire · read-side · build-now).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RigJBiRFNtFZKCz21qNbQ4
Declaration/config groundwork that slice 2b's trend-spotter upgrade reads.
Standalone (no agent wiring yet — that's 2b), mirroring slice 1's pattern;
[skip-docs] for the same reason slice 1 was — user-facing docs land when 2b
wires the engine live.
- references/trend-scoring-modes.md: methodology SSOT for two rubrics —
kortform (feed post, timing 20%) + long-form (chronicle, depth 25% / timing 10%,
per tema-research-motor-spec §4.2). Both sum to 100%. trend-spotter renders from
this in 2b instead of inlining a matrix (S12-consistent).
- config/trends-sources.template.md: shipped generic source-list defaults →
user override at ${LINKEDIN_STUDIO_DATA}/trends/sources.md (data-dir, survives
reinstall; same template->data-dir pattern as user-profile).
- user-profile.template.md: new "Research Tooling" section — declared research MCPs
(Tavily/Gemini/Perplexity/Other) + WebSearch/WebFetch floor. 2b routes MCP-first.
- setup.md Step 3f + onboarding.md Phase 2: ask "which research MCPs?" -> profile.
Store only what the user declares; no hard-coded MCP names.
- test-runner.sh: EXPECT_REFS 26->27; generalized the M0 +1 delta-guard into a
named-post-M0-additions guard (POSTM0_REFS) so a legit later ref doc passes while
the anti-masking intent holds. Gate green 84/0/0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBMKqPSVbvSZHtQ4heM1UY
Wire the kilde-så-draft binding (slices 1–2) into the live /linkedin:newsletter
pipeline so a draft is grounded in the operator's real material BEFORE any prose.
- New Step 1.5 "Lived-specifics extraction" BETWEEN brief (1) and research (2):
query the bank → 3–5 sharp elicitation questions (vagueness refused, never
fabricated — invariant 3) → `add` to the specifics-bank → populate the
articles.NN.livedSpecifics slot-map → render the NN-kilder.md ledger. First
phase to write machine state (persists brief + personas + binding).
- Deterministic binding-gate (`validate-binding`, exit 1 = BLOCK) wired as a new
step 5 of the Step 2.5 skeleton-gate (renumbered 5→9): no prose is written on
an unresolved load-bearing claim; livedSpecifics → "bound" on pass.
- Step 2 re-scoped BY the binding: research fills the ekstern/unresolved slots +
verifies the operator's own numbers (regel 6/7) → flips bank unverified→verified
→ re-renders NN-kilder.md, instead of re-sourcing what is already grounded.
- Pipeline 17 → 18 phases: new `lived-specifics` phase id in edition-state
_doc.phases; resumption table + pipeline overview + CLAUDE.md + README updated.
- Lint: new Section 15 "Specifics-Bank Binding" wires the specifics-bank suite
into CI (suite green + case-count floor 28, KTG-only/adopter-skip); the
assertion-count anti-erosion floor moves to Section 16.
Verification: structure gate 84/0/0 (was 83), specifics-bank 28/28, contract-gate
ratify 1:1, edition-state template valid JSON (18 phases), gitleaks clean on all
5 files. Design record: docs/fix2/slice2-binding.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Slice 2 of fix#2 (kilde-så-draft): the per-edition bridge between the global
specifics-bank (slice 1) and a draft. In scripts/specifics-bank:
- binding.ts — livedSpecifics slot-map model + validateBinding, the «vaghet
avvises» gate (G4). BLOCK on unresolved / dangling specific-id / unjustified
abstrakt; WARN on an unverified-number-backed slot (regel 6/7); PASS otherwise.
- kilder.ts — renderKilder, the read-only NN-kilder.md sources ledger, rendered
deterministically from the slot-map + bank (coverage via validateBinding, so
the artifact and the skeleton-gate cannot disagree).
- cli.ts — validate-binding (exit 1 = BLOCK) + render-kilder subcommands.
edition-state schema gains articles.NN.livedSpecifics ({ slots, status }) + _doc.
Design record + the Step 2 research re-scope spec: docs/fix2/slice2-binding.md.
Wiring into newsletter.md (Step 1.5 elicitation + Step 2.5 gate + pipeline 17->18)
is slice 3 — not in this commit.
Tests 28/28 (specifics-bank; +9 binding +4 kilder), tsc clean, plugin gate 83/0/0
unaffected, gitleaks clean on all 8 files.
[skip-docs] internal plumbing — no command/agent/pipeline surface change until
slice 3 wires it; documenting it in the user-facing root CLAUDE.md/README now would
overclaim unreachable functionality. Docs ARE updated where they belong: the design
record docs/fix2/slice2-binding.md, scripts/specifics-bank/README.md, and the
edition-state _doc. Root-doc update lands with the slice-3 wiring feat.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Slice 3 of fix#1 (§C2 bindende + akkumulerende): wire the deterministic
§B/§C1 contract-gate into the long-form pipeline as a pre-handoff step, so
mechanical violations die deterministically BEFORE the costly AI gates and
never reach the operator at a judgment gate ("rettelser fester seg").
Newsletter pipeline:
- New Step 4.5 (between Step 4 consistency/quality and Step 5 fact-check):
(1) ratify the gate (rules.ts <-> §E-manifest 1:1; DRIFT escalates to
operator, not a draft fix) and (2) gate the draft (exit 0 PASS / exit 1
BLOCK -> fix by tightening + re-run; WARN = direction, never blocks).
Adopter-safe: no-op when contract-gate deps / the maskinrommet contract
are absent.
- Pipeline phase count 16 -> 17 across every LIVE surface (overview table +
build-status + narrative + banner + schema pointer in newsletter.md;
command-table rows in CLAUDE.md and README). Historical version-narrative
entries left untouched.
- edition-state.template.json: new "contract-gate" phase string (Step 4.5),
between consistency-quality and factcheck-sweep. JSON valid; phases 16->17.
CI integration (test-runner.sh, Section 14 — new):
- 14a: contract-gate suite stays green (npm test exit 0) with a 33-test
case-count floor (anti-erosion).
- 14b: ratify invariant — rules.ts bound 1:1 to the §E-manifest.
- Both KTG-internal and adopter-safe (warn/skip, never fail, when deps or the
contract are absent). set +e inside the test command-substitution keeps a
red suite from aborting the runner; ratify exit 1 captured via if-subshell.
- SC6 anti-erosion section renumbered 14 -> 15; header comment updated.
Verification:
- Structure lint 81 -> 83/0/0 (contract-gate suite + ratify both green).
- Documented Step 4.5 command smoke-tested on a real draft
(serier/silvija-seres-motsvar/utkast/04-utkast.md): 0 BLOCK / 2 WARN ->
"Gate passert", exit 0.
- edition-state.template.json valid JSON; phases array = 17.
foldIns capture into the pipeline phases deferred to a later slice (scope A).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Slice 2 av fix#1 («rettelser fester seg»): binder rules.ts til den menneskelige
sannhetskilden (skrivekontrakt §E), så en korreksjon gjort én gang håndheves for
alltid i stedet for å gjenoppdages hver utgave (diagnose-gap 2).
- ratify.ts: importerer RULES direkte (ingen skjør tekst-parsing), krever en
bijeksjon mot §E gate-bindings-manifestet (id ↔ ref ↔ severity) + dangling-
§-anker-sjekk. CLI: `--ratify [kontrakt]` / `npm run ratify`. Sti: arg > env
MASKINROMMET_CONTRACT > default (relativt til modulen).
- edition-state.template: foldIns[] fangst-kø (per-artikkel proveniens,
pending|promoted|rejected, mekanisk→rules.ts / dømmekraft→§C2).
- 12 nye tester (33 totalt), tsc rent. Live-kontrakt-integrasjonstest ratify-er
det ekte §E-manifestet rent (10 regler bundet 1:1).
Companion: skrivekontrakt §E (JA-promoter-prosedyre + manifest) i maskinrommet.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fourth sub-pass of the S29 plugin-wide terminology scrub: the banned brand phrase
"thought leadership" (FORM A) removed from the remaining surfaces — skills, a config template,
shipped assets, and a test fixture. 8 edits across 6 files. Vocabulary consistent with
S29a-S29c: "thought leadership angle(s)" -> "content angle(s)"; the "Value Test" family ->
"Authority Value Test"; "Standard Thought Leadership Post" -> "Standard Post" (matches the
S29a/S29c "Standard Post Structure" equivalent).
Edits: skills/linkedin-content-creation (3) "Identify Thought Leadership Angles" -> "Content
Angles", "Standard Thought Leadership Post" -> "Standard Post", "The 8 Thought Leadership
Angles" -> "The 8 Content Angles"; skills/linkedin-strategy:176 phase-focus cell "Thought
leadership, cross-platform" -> "Signature content, ..." (avoids the Authority-phase column
echo); config/user-profile.template:35 "Build thought leadership & authority" -> "Build
authority & influence"; assets/checklists/quality-scorecard:136 "Passes thought leadership
test" -> "Passes Authority Value Test"; assets/case-studies/case-study-template:173 "Best for:
Thought leadership" -> "Authority content"; hooks/scripts/__tests__/clipboard-helper.test:61
unicode fixture "Thought leadership" -> "Authority" (emoji + arrow retained; coverage unchanged).
Scope (operator-locked, inherits S29a-S29c): FORM A only. FORM B = 8 untouched -- the 5
buzzword-denylist entries MUST list the banned word ("thought leader"), plus 3 role usages
(linkedin-networking x2, README "niche thought leaders"). The 21 thought-leadership-angles.md
filename pointers deferred to S29e. No anchor links to the changed headers anywhere in the
plugin. Forward-looking docs already clean.
Verify: FORM A in scope = NONE; FORM B unchanged (8); filename pointers unchanged (21);
clipboard-helper test 13/0; 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
Step 17 (Wave 4 S4) of the audit remediation. Applies research/03 §D5 + the
two S2 residual fixes folded in. No new commands/agents (counts stay 27/19).
Newsletter (commands/newsletter.md): new "Distribution channel" section after
Step 10 teaching the HONEST native-newsletter mechanics — bypasses organic feed
ranking via ONE deduplicated notification per subscriber per edition (NOT a
three-touchpoint blast); the mass invite fires once → ~1-2K follower floor
(wait until you can spend it); realistic cold-start 0-100 subs months 1-3;
discloses non-export / no-canonical / no-read-analytics / per-subscriber decay;
explicit below-vs-above-floor decision rule. Sourced to research/03 D5.
Profile (commands/profile.md): new "Profile SEO" section — headline as the
highest-weight search field + a per-section keyword-target table
(headline/about/experience/skills/featured), consistency-over-stuffing rule.
Outreach (commands/outreach.md): Step 8c persists the pipeline board to tracked
state via the new recordOutreachContact mutation (mirrors Step 16's
recordFirstHourPlan): additive last_outreach_date/outreach_active scalars + a
non-R-initial ## Outreach Pipeline section in state-updater.mjs +
config/state-file.template.md + --record-outreach CLI branch. +7 tests
(state-updater 26→33, full hook suite 83→90).
Residual 1 (growth-playbook:216): 9:16 "distribution boost" → 4:5/1:1 guidance
(9:16 mobile-only opt-in; "immersive distribution" = uncorroborated heuristic).
Residual 2 (video-strategy-guide:300): "3-second test determines 70% retention"
→ "front-load value for muted autoplay" (three-second hook is folklore, not a
LinkedIn signal).
Verify: grep checks 1-5 pass; test-runner.sh exit 0 (stat-consistency green);
state-updater 33/33. [skip-docs] — tre-doc + version bump deferred to Step 21.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wire orphan agent #11 (engagement-coach) by giving it a command surface, and
add the tracked first-hour state the plan calls for (remediation Step 16).
- commands/firsthour.md (new, 27th command): post-publish first-hour /
reply-loop sprint. Delegates plan construction to engagement-coach via
Task (subagent_type: linkedin-studio:engagement-coach) — returns a grouped
target list (whales/inner-circle/ICPs/new connections), 2-3 seed
self-comments + 3-5 CEA replies in the user's voice, and a minute-by-minute
timeline anchored to publish time. Presents timeline/targets/drafts +
velocity checkpoints, auto-copies the drafts to clipboard, persists the
plan, then hands off to post-feedback-monitor for the 48h window.
- hooks/scripts/state-updater.mjs: new pure mutation recordFirstHourPlan()
mirroring updatePostTracking — additive by contract (inserts
last_firsthour_date after last_post_date when absent, creates the
## First-Hour Plans section when absent, never touches existing fields).
Section name is deliberately non-R-initial so it stays outside
pruneContentHistory's "## Recent Posts ... (?=\n## [^R])" capture window.
+ a --record-firsthour CLI branch for parity with the other mutations.
- config/state-file.template.md: additive scalars (last_firsthour_date,
firsthour_active) + the ## First-Hour Plans section.
- hooks/scripts/__tests__/state-updater.test.mjs: extend (existing file) with
7 recordFirstHourPlan tests — section creation, field insertion vs in-place
update (no duplication), round-trip non-interference, graceful empty
defaults, changes array.
- CLAUDE.md: register the command (## Commands 26 -> 27, table row).
- scripts/test-runner.sh: EXPECT_COMMANDS 26 -> 27 (registration guard).
Verify: grep 'subagent_type: linkedin-studio:engagement-coach' commands/ ->
firsthour.md; node --test state-updater -> 26/26; full hook suite -> 83/83;
bash scripts/test-runner.sh -> exit 0 (62 passed, commands 27/27).
Plan Step 16 (Wave 4 S3).
[skip-docs]: tre-doc + version bump deferred to Step 21 per remediation plan.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wave 3 / Step 9 of the remediation plan (Phase 1 — usable by a non-author).
The long-form review layer shipped Norwegian-locked: language-reviewer graded
unconditional Norwegian, voice-scrubber's gold standard was 'approved Norwegian
editions', and the editorial/content craft gates pointed at a 'skrivekontrakt §C2'
that does not ship. A non-Norwegian adopter would get English prose graded against
Norwegian idiom and a gate that depends on an unshipped contract.
- config/edition-state.template.json: add additive 'language' field (top-level,
default 'en') + a _doc entry. Threads into the language-dependent agents.
- agents/language-reviewer.md: new 'Language parameter' section — Norwegian-specific
checks (anglicism->Norwegian idiom, kanselli-stil) apply only when language=='no';
any other value grades that language's equivalents and never flags idiomatic
English as an anglicism. Default 'en'.
- agents/voice-scrubber.md: gold standard reframed to 'approved editions in the
configured language'; the Norwegian-chronicle calibration is the language=='no'
instantiation.
- agents/editorial-reviewer.md + agents/content-reviewer.md: the in-tree checklist
is now the operative, self-contained source of truth; Maskinrommet §C2 is an
optional upstream contract that does NOT ship (available only on the author's
runs). The gates work for an adopter without it.
- commands/newsletter.md: thread 'language' through the Step 6.5 cold-inputs and the
per-reviewer call inputs; the writing contract is now 'if it ships'.
Norwegian remains fully working when language: no (the author's case).
fact-reviewer.md was in the plan's file list but needed no change on inspection:
its F1-F4 checks (claims/quotes/numbers/sources) are language-agnostic; its
'Norwegian' mentions are boundary notes vs language-reviewer, which stay correct.
[skip-docs]: three-doc + version reconciliation is Step 21 (pre-review-gate); these
intermediate Wave commits are not pushed before the /trekreview gate.
Verify: edition-state JSON parses + has top-level language 'en'; language-reviewer
has 'language ==' references and no unconditional-Norwegian assertion; editorial
§C2 reframed to in-tree fallback ('operative source', 'does not ship'); agent
fixtures 35/35 pass; structural lint exit 0 (61 passed).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wave 3 / Step 8 of the remediation plan (Phase 1 — usable by a non-author).
The flagship long-form engine shipped bespoke-as-general: a maintainer-private
absolute series path and a hardcoded 'Maskinrommet' brand in the renderers. Both
are now generalized so a non-author can run the pipeline without inheriting the
author's filesystem or publication identity.
- commands/newsletter.md + config/edition-state.template.json: series-root default
/Users/ktg/repos/maskinrommet/serier -> $HOME/linkedin-series; reconciled the
prose that called the maskinrommet folder 'the default' so it no longer
contradicts the new neutral default. LTL_SERIES_ROOT override contract preserved.
- render/build-linkedin.mjs + render/build-carousel.mjs: brand is now an LTL_BRAND
env-var (empty default -> generic). Samle-post title, carousel footer brand-span,
and cover-eyebrow fallback are de-branded; empty brand renders clean chrome. The
operator sets LTL_BRAND=Maskinrommet in their own env to re-brand (same pattern
as LTL_SERIES_ROOT).
- config/image-credit-caption.template.md: 'Maskinrommet-/serie-badge' -> generic
'serie-badge'.
Out of scope (Step 9): the residual 'Maskinrommet skrivekontrakt §C2/§A'
references in newsletter.md are the writing-contract generalization, handled next.
[skip-docs]: three-doc + version reconciliation is Step 21 (pre-review-gate, per
plan: 'LAST so it captures everything'). These intermediate Wave commits are NOT
pushed before the /trekreview gate, so the three-doc obligation (which governs
pushed changes) is satisfied at Step 21, not per local checkpoint commit.
Verify: grep -rIn '/Users/ktg' config/ commands/ render/ (excl .local) -> no
matches; grep -rn 'Maskinrommet' render/ -> no matches (de-branded); node --check
on both render scripts -> OK; LTL_SERIES_ROOT still present in newsletter.md.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Cold, adversarial review package for the long-form pipeline + configurable
per-edition personas. Motivated by Del 4 (Security Champions pivot): the
in-session editor + persona sweep shared the drafting session's framing-bias,
so the shipped version was never independently re-reviewed.
Headless package (9a/9b):
- New Step 6.5 (headless-review) in /linkedin:newsletter, after the persona
sweep, before lock — the independence layer the in-session gates can't be.
- New standalone /linkedin:headless-review command (run in a fresh session for
maximum isolation; reconstructs frozen draft + contract + personas from disk).
- 3 new Opus archetypes, each with a cardinal context-isolation block that
refuses drafting-session framing as "context pollution":
- content-reviewer (argument integrity C1–C5, ≤8 flags)
- language-reviewer (Norwegian language L1–L5, ≤10 flags)
- fact-reviewer (cold re-verification F1–F4, risk-sort + pivot-risk, WebSearch)
- Deliberate redundancy with fact-checker / editorial-reviewer documented so
the pairs are never de-duplicated.
Pivot-reopen (9c):
- New /linkedin:pivot command: logs articles.NN.pivots[], resets currentPhase,
un-locks, marks gates to re-run.
- Pivot-detection gate in Step 8 lock precondition (>20% word-count change or
>2 new sections re-opens cleared gates). Del 4 v8→v11 worked example.
Per-artifact personas (new requirement):
- articles.NN.personas with resolution order (edition-state → series file →
plugin library → interactive). One or more readers configurable per edition.
Schema/docs:
- edition-state.template.json: additive personas[], pivots[], headlessReview,
headless-review phase (16 phases); personaSweep.resonance.wordCount baseline.
- 3 fasit fixtures + 3 structural lint tests (Del 4 worked cases).
- Counts: 24→26 commands, 16→19 agents, 15→16 newsletter phases.
- README + CLAUDE.md (plugin + root) + CHANGELOG synced.
Verification: 35 agent-fixture + 59 hook + 20 render tests green. Backward-
compatible (additive state); reload required before the 3 new agents resolve.
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>
Endring 8 from the change spec (Del 4 production, Maskinrommet). The persona
resonance sweep measures reader-response (does it land?); nothing measured prose
craft or narrative architecture (is it well-made?). In Del 4 every persona
reported PASS, yet the editor found 8 fresh editorial points on first reading —
~6/8 craft/architecture blind spots no agent could see. v2.4.0 adds the missing
editor role.
New Step 5.5 (editorial-review) runs between fact-check (Step 5) and the persona
sweep (Step 6): a new editorial-reviewer agent (Opus) judges two axes —
prosa-handverk (em-dash density, verbatim repetition, postulated numbers,
contradictions, versal-tic) + narrativ-arkitektur (concrete instantiation,
theory-anchored hypotheses, series-title symmetry, equal action per addressee,
un-overloaded conclusion). Returns <=10 flags as direction (never copy), each
BLOCK/REWORK/NICE, operator-gated via SendUserFile. Runs before the persona
sweep so the personas measure resonance instead of stumbling on craft noise.
Mirrors the Maskinrommet writing-contract section C2 (bidirectional mirror rule).
- agents/editorial-reviewer.md (NEW, Opus, orange) + fasit fixture
(editorial-reviewer-cases.md: Del 4 v5 gold standard, 8 points -> 2 axes +
severities, 3 BLOCK / 5 REWORK, 6/8 blind spots) + structural lint (7 tests).
- Step 5.5 wired into commands/newsletter.md; pipeline 14 -> 15 phases.
- editorial-review phase + additive editorialReview state in
config/edition-state.template.json; resumption: factcheck-sweep -> Step 5.5,
editorial-review -> Step 6 (spec said fact-check; canonical key is
factcheck-sweep).
- persona-reviewer contract unchanged: editorial-reviewer is supplementary
(one measures craft, one measures response).
- All doc levels synced (plugin + root README/CLAUDE.md, CHANGELOG, plugin.json
2.3.0 -> 2.4.0; agents 15 -> 16). 94 tests green.
Acceptance-criterion #8 (live run on Del 4 v5) delivered as fasit fixture:
a live run needs a session reload (new agent not invokable until then) + read
access to the Del 4 v5 draft in Maskinrommet.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Implements the 6-change spec from the Seres-serien production
(linkedin-plugin-endringsspec.md). All acceptance criteria met.
1. Avoid-patterns (modell-/navne-katalog, completeness-over-reader-action,
self-referential overhead openings) → longform-quality-rules.md (rule 1+3)
+ user-profile.template.md.
2. Persona gate now BLOCKING with explicit hard-fail list (primær mistet meg /
doesn't own action / sjargong-mur / modell-navne-katalog → BLOCK;
"JA med store forbehold" = NEI) → persona-reviewer.md + personas.template.md.
3. Fact-check declared orthogonal to narrative strength + post-cutoff
web-search mandate + high-frequency-error checklist → fact-checker.md.
4. NEW agent voice-scrubber.md (Opus) — de-AI scrub + Norwegian-chronicle
voice-drift; gold standard = approved Norwegian editions, NOT the English
post corpus. Wired into newsletter.md Step 4.
5. Operator gates = render+annotate rounds (build-html.mjs to file://) as
primary flow, AskUserQuestion as receipt/fallback → newsletter.md 2.5+3a.
6. Edition state reconciled with STATE.md (ONE-system). edition-HANDOVER
template deleted; narrative to <serie>/STATE.md, machine data
(factcheckLog, personaSweep, immutableRules) to edition-state.json.
Agents 14 to 15; commands unchanged (24). Backward-compatible (additive
state-shape only). Docs updated across all three levels + CHANGELOG.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two new pipeline phases gate the spine before any prose is written:
- Step 2.5 — Skeleton + section pitch: writes <serie>/NN-skjelett.md with
the five-line spine (premiss / problem / anbefaling / gevinst / vei
videre) + one-line section pitches. Operator-gate (JA / REVIDER / NEI)
AND parallel persona-skjelett-sweep must both return JA before the
pipeline can advance.
- Step 3a — Spine prose: one paragraph per section against the gated
skeleton, ~20-30% of final edition length. Operator-gate on whether the
axis lands now that there is prose on it. Old Step 3 (Draft) split into
3a (spine) and 3b (full expansion); 3b owns the multi-session
draft-cursor logic.
Third persona-reviewer mode added: skjelett (alongside resonans + konverter).
Five spine axes scored HOLDER / TVILER / MANGLER, max 3 direction-only flags,
per-pitch section-pay-in check. Reads the skeleton + pitches only.
Pipeline grows from 11 to 13 phases; commands (24) and agents (14) counts
unchanged. Encodes the Maskinrommet writing-contract section A discipline
(premiss / problem / anbefaling / gevinst / vei videre) into the pipeline.
Empirically motivated by the Seres-serien Del 3 + Del 4 production:
a spine error caught at the skeleton stage costs 5-15 min, the same
error caught at Step 6 (resonance) costs 4-12 h, post-lock it costs a
day of cascading rework (delingstekst, hooks, carousel, doc refs).
Backward-compatible: existing editions stop at currentPhase: "research"
and now resume at Step 2.5 instead of Step 3 — an intended deterministic
improvement, never a contract break. Steps 1, 2, 4-10 bit-for-bit
unchanged. Renderers (build-html.mjs, build-linkedin.mjs) untouched.
New phase strings in edition-state.template.json _doc.phases:
- skeleton-pitch (between research and draft)
- spine-prose (between skeleton-pitch and draft)
Files changed (10):
- plugin.json: 2.0.0 -> 2.1.0
- CHANGELOG.md: new [2.1.0] entry
- CLAUDE.md (plugin + marketplace): pipeline 11->13 phases noted
- README.md (plugin + marketplace): What's New v2.1.0 + version row
- agents/persona-reviewer.md: third mode skjelett added; resonans + konverter unchanged
- commands/newsletter.md: Step 2.5 + 3a + 3b sections, resumption + pipeline tables
- config/edition-state.template.json: 11 -> 13 phases in _doc.phases
- references/longform-quality-rules.md: Rule 8 (Skjelett foer prosa)
Verification: 9/9 criteria PASS pre-commit. Phase strings consistent
across template + command + resumption table. Renderer files git-untouched.
All 11 original step headings preserved (Step 0/1/2/4-10).
Co-Authored-By: Claude Opus 4.7 <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>
