@theronap/cortex-mcp 0.9.71 → 0.9.73

package/README.md

@@ -1,10 +1,10 @@
 # cortex-mcp
 
-Connect your AI assistant to **Cortex** — your org's projects, recent activity, gaps, and directives, scoped to exactly what you're permitted to see.
+Connect your AI assistant to **Agnoclast** — your org's projects, recent activity, gaps, and directives, scoped to exactly what you're permitted to see.
 
 ## Setup
 
-1. Get your personal token from the Cortex console → **Connect your AI**.
+1. Get your personal token from the Agnoclast console → **Connect your AI**.
 2. Add this to your Claude Code config (`~/.claude.json`, under `mcpServers`):
 
 ```json
@@ -21,7 +21,7 @@ Connect your AI assistant to **Cortex** — your org's projects, recent activity
 
 3. Restart Claude Code. Your AI now sees your org context automatically, the managed startup skill
    will prefer query-centered `session_context` on substantive session opens, and each session start
-   will log the exact baseline Cortex context to `~/.cortex/context-snapshots/`.
+   will log the exact baseline Agnoclast context to `~/.cortex/context-snapshots/`.
 
 No clone, no path, no build step — `npx` fetches and runs it.
 

package/bin/cortex-mcp.mjs

@@ -1,6 +1,6 @@
 #!/usr/bin/env node
 /**
- * cortex-mcp — connect your AI assistant to Cortex.
+ * cortex-mcp — connect your AI assistant to Agnoclast.
  *
  * Subcommands:
  *   (none)            run the MCP server (stdio) — used by your Claude config
@@ -8,14 +8,14 @@
  *   doctor            live health check — is the token actually working? (no restart needed)
  *   capture           the Stop-hook capturer (invoked by Claude Code, not by hand)
  *   ingest-folder <path>  ingest a local markdown folder as your authored records
- *   snapshot-context  save the exact startup context served by Cortex to a local log file
+ *   snapshot-context  save the exact startup context served by Agnoclast to a local log file
  *   --version | -v
  *   --help | -h
  *
  * Zero-install onboarding:
  *   npx -y @theronap/cortex-mcp setup <your-token>
  *
- * Get your token from the Cortex console → Connect your AI.
+ * Get your token from the Agnoclast console → Connect your AI.
  */
 
 import { readFileSync } from 'node:fs'
@@ -35,31 +35,31 @@ if (cmd === '--version' || cmd === '-v') {
 
 if (cmd === '--help' || cmd === '-h' || cmd === 'help') {
   process.stdout.write(
-    `cortex-mcp ${VERSION} — connect your AI assistant to Cortex\n\n` +
+    `cortex-mcp ${VERSION} — connect your AI assistant to Agnoclast\n\n` +
     `Onboard (one command, no token to copy):\n` +
     `  npx -y @theronap/cortex-mcp login\n\n` +
     `This opens your browser, you click Approve, and it wires everything up. Restart\n` +
-    `Claude Code after, and your AI sees your Cortex context while your sessions flow\n` +
+    `Claude Code after, and your AI sees your Agnoclast context while your sessions flow\n` +
     `into the org automatically.\n\n` +
     `Subcommands:\n` +
     `  login [--label <name>]  browser-approved sign-in — gets a token for you, then runs setup\n` +
     `  setup <token>   wire MCP server + capture hook into ~/.claude config (single editor)\n` +
-    `  install [<token>] [--editor auto|all|<id,...>]  wire Cortex into EVERY detected editor + write the capability manifest\n` +
+    `  install [<token>] [--editor auto|all|<id,...>]  wire Agnoclast into EVERY detected editor + write the capability manifest\n` +
     `  repair          re-run setup at the latest version using your existing token (no token needed)\n` +
-    `  uninstall       remove ALL Cortex wiring (MCP, hooks, skills, launchd, cron). --dry-run to preview, --purge to also wipe ~/.cortex + npx cache\n` +
+    `  uninstall       remove ALL Agnoclast wiring (MCP, hooks, skills, launchd, cron). --dry-run to preview, --purge to also wipe ~/.cortex + npx cache\n` +
     `  doctor          live health check — confirm your token works (no restart needed)\n` +
     `  status          one-line connected/not-connected check (used by the SessionStart hook)\n` +
-    `  skills          install/repair the managed Cortex skills — bundled + org-published (also wired by setup)\n` +
+    `  skills          install/repair the managed Agnoclast skills — bundled + org-published (also wired by setup)\n` +
     `  skills push <file>     publish a SKILL.md to your org (owner/manager/admin)\n` +
-    `  docs-scan       detect new/changed local docs pending Cortex authoring (used by /cortex-author-docs)\n` +
+    `  docs-scan       detect new/changed local docs pending Agnoclast authoring (used by /cortex-author-docs)\n` +
     `  graphify-sync [path]  rebuild the local code graph (graphify) + log an evidence-tier timeline event\n` +
-    `  snapshot-context save the exact startup context Cortex served to a local snapshot\n` +
+    `  snapshot-context save the exact startup context Agnoclast served to a local snapshot\n` +
     `  hydrate         UserPromptSubmit hook — inject query-centered context on the first substantive turn\n` +
     `  statusline      ambient presence line for the Claude Code statusline (local read only)\n` +
     `  capture         Stop-hook capturer (invoked by Claude Code)\n` +
     `  ingest-folder <path>   ingest a local markdown folder as your authored records\n` +
     `  (no args)       run the MCP server (used by your Claude config)\n\n` +
-    `Get your token from the Cortex console → Connect your AI.\n`,
+    `Get your token from the Agnoclast console → Connect your AI.\n`,
   )
   process.exit(0)
 }
@@ -84,14 +84,14 @@ if (cmd === 'login') {
   const { closeFetch } = await import('../lib/diagnose.mjs')
   await closeFetch()
 } else if (cmd === 'install') {
-  // The cross-editor hub installer: wire Cortex into every detected editor via the adapter
+  // The cross-editor hub installer: wire Agnoclast into every detected editor via the adapter
   // registry, then write the capability manifest (~/.cortex/editors.json). Superset of `setup`.
   const { runInstall } = await import('../lib/install.mjs')
   await runInstall(rest, VERSION)
   const { closeFetch } = await import('../lib/diagnose.mjs')
   await closeFetch()
 } else if (cmd === 'uninstall' || cmd === 'remove') {
-  // Full reverse of setup: strip every Cortex touch-point (MCP entries, hooks, skills, launchd, cron).
+  // Full reverse of setup: strip every Agnoclast touch-point (MCP entries, hooks, skills, launchd, cron).
   // --dry-run prints the plan and changes nothing; --purge also removes ~/.cortex, the npx cache, and
   // backups. No network — safe to run even when the token is dead or the server is unreachable.
   const { runUninstall } = await import('../lib/uninstall.mjs')
@@ -153,7 +153,7 @@ if (cmd === 'login') {
   const { closeFetch } = await import('../lib/diagnose.mjs')
   await closeFetch()
 } else if (cmd === 'hydrate') {
-  // UserPromptSubmit hook (① discovery): hydrate the model with query-centered Cortex context on the
+  // UserPromptSubmit hook (① discovery): hydrate the model with query-centered Agnoclast context on the
   // FIRST substantive turn, before it answers — then never again this session (topic-shift refresh stays
   // the cortex-context skill's job). Synchronous by necessity, but once-per-session + 8s + fail-open.
   const { runHydrate } = await import('../lib/hydrate.mjs')
@@ -166,7 +166,7 @@ if (cmd === 'login') {
   const { runStatusline } = await import('../lib/statusline.mjs')
   process.exitCode = runStatusline()
 } else if (cmd === 'skills') {
-  // Install / repair the managed Cortex skills — bundled + org-published (`skills push` publishes).
+  // Install / repair the managed Agnoclast skills — bundled + org-published (`skills push` publishes).
   // Org sync is network-fail-soft so the SessionStart hook stays safe offline.
   const { runSkills } = await import('../lib/skills.mjs')
   process.exitCode = await runSkills(rest)

package/lib/capture.mjs

@@ -35,7 +35,7 @@ export function projectFrom(cwd) {
   return base ?? 'general'
 }
 
-// Claude Code Stop hook → POSTs a session digest to Cortex cloud, which
+// Claude Code Stop hook → POSTs a session digest to Agnoclast cloud, which
 // summarizes server-side and upserts ONE record per session. Node-native
 // SHR-01/T6 — parse a git remote URL into GitHub 'owner/name', or null.
 //

package/lib/code_graph_cli.mjs

@@ -4,7 +4,7 @@ import { join } from 'path'
 
 // Thin local wrapper around the `graphify` CLI's read-only query subcommands. Deliberately NOT a
 // fetchCortex client like grep/read_page: this is LOCAL-MACHINE data (a tree-sitter AST graph of
-// whatever repo the session's cwd happens to be in), not org-shared Cortex content, and it never
+// whatever repo the session's cwd happens to be in), not org-shared Agnoclast content, and it never
 // becomes the wiki graph — see cortex-wiki-primary-spec (structural/extracted data is evidence,
 // never auto-promoted into authored pages). No LLM, no network call; graphify already built the
 // graph on disk, this just queries it.

package/lib/context_log.mjs

@@ -49,7 +49,7 @@ export async function runSnapshotContext() {
   const out = (m) => process.stdout.write(m + '\n')
   const token = resolveToken()
   if (!token) {
-    out('Cortex: context snapshot skipped — no token found.')
+    out('Agnoclast: context snapshot skipped — no token found.')
     return 0
   }
 
@@ -58,13 +58,13 @@ export async function runSnapshotContext() {
   try {
     res = await fetchCortex(`${base}/api/mcp-context`, { headers: { Authorization: `Bearer ${token}` } })
   } catch (e) {
-    out(`Cortex: context snapshot failed — ${e?.message ?? String(e)}`)
+    out(`Agnoclast: context snapshot failed — ${e?.message ?? String(e)}`)
     return 0
   }
 
   if (!res.ok) {
     const body = await res.text()
-    out(`Cortex: context snapshot failed — ${classify(res.status, res.headers.get('content-type'), body, res.headers.get('x-vercel-id')).message}`)
+    out(`Agnoclast: context snapshot failed — ${classify(res.status, res.headers.get('content-type'), body, res.headers.get('x-vercel-id')).message}`)
     return 0
   }
 
@@ -76,7 +76,7 @@ export async function runSnapshotContext() {
   const capturedAt = new Date().toISOString()
   const file = join(dir, `${stamp()}.md`)
   const header = [
-    '# Cortex startup context snapshot',
+    '# Agnoclast startup context snapshot',
     `- Captured: ${capturedAt}`,
     `- Source: ${base}/api/mcp-context`,
     '',
@@ -94,6 +94,6 @@ export async function runSnapshotContext() {
 
   pruneSnapshots(dir)
 
-  out(`Cortex: logged startup context → ${file}`)
+  out(`Agnoclast: logged startup context → ${file}`)
   return 0
 }

package/lib/diagnose.mjs

@@ -1,12 +1,12 @@
 // Shared health / diagnosis helpers for the cortex MCP client.
 //
 // The whole reason this file exists: a transient infrastructure block (Vercel firewall / bot
-// protection / deployment protection) once surfaced as a bare "Cortex API 403: unknown", which
+// protection / deployment protection) once surfaced as a bare "Agnoclast API 403: unknown", which
 // read like an auth failure and sent everyone chasing token regeneration for hours. The fix is
 // to tell the truth about WHAT failed.
 //
-// KEY SIGNAL: the Cortex app ALWAYS returns JSON ({ error: ... }). So a NON-JSON body on a
-// 4xx/5xx means infrastructure handled the request, not Cortex auth — re-running setup or
+// KEY SIGNAL: the Agnoclast app ALWAYS returns JSON ({ error: ... }). So a NON-JSON body on a
+// 4xx/5xx means infrastructure handled the request, not Agnoclast auth — re-running setup or
 // regenerating the token will not help; it is usually transient and worth a retry.
 
 import { readFileSync } from 'fs'
@@ -85,7 +85,7 @@ const sleep = (ms) => new Promise((r) => setTimeout(r, ms))
 // A non-OK response → an actionable diagnosis: { kind, retriable, message }.
 //   kind: 'auth'  → token bad/revoked/wrong-deployment (NOT retriable)
 //         'infra' → blocked by infrastructure, non-JSON body (retriable, usually transient)
-//         'app'   → a real Cortex API error with a JSON message (retriable only if 5xx)
+//         'app'   → a real Agnoclast API error with a JSON message (retriable only if 5xx)
 export function classify(status, contentType, bodyText, requestId) {
   const isJson = (contentType ?? '').includes('application/json')
   let appError = null
@@ -109,20 +109,20 @@ export function classify(status, contentType, bodyText, requestId) {
       kind: 'auth', retriable: false,
       message: `Token rejected (HTTP ${status}: ${appError ?? 'unauthorized'}). The token is invalid, ` +
         `revoked, or for a different deployment — not an infrastructure problem. Get a fresh token from ` +
-        `the Cortex console → Connect your AI, then re-run setup.${rid}`,
+        `the Agnoclast console → Connect your AI, then re-run setup.${rid}`,
     }
   }
   if (!isJson) {
     return {
       kind: 'infra', retriable: true,
-      message: `Blocked by infrastructure (HTTP ${status}, non-JSON response) — NOT by Cortex auth. This is ` +
+      message: `Blocked by infrastructure (HTTP ${status}, non-JSON response) — NOT by Agnoclast auth. This is ` +
         `usually a transient firewall / bot-protection hiccup; retrying often clears it. If it persists, check ` +
         `Vercel firewall / deployment protection on the API route. Re-running setup will not help.${rid}`,
     }
   }
   return {
     kind: 'app', retriable: status >= 500,
-    message: `Cortex API ${status}: ${appError ?? 'unknown error'}.${appHint ? ` ${appHint}` : ''}${rid}`,
+    message: `Agnoclast API ${status}: ${appError ?? 'unknown error'}.${appHint ? ` ${appHint}` : ''}${rid}`,
   }
 }
 
@@ -176,7 +176,7 @@ export async function fetchCortex(url, opts = {}, { retries = 2, baseDelayMs = 4
     }
   }
   throw new Error(
-    `Could not reach Cortex at ${url} — ${lastErr?.message ?? 'network error'}. ` +
+    `Could not reach Agnoclast at ${url} — ${lastErr?.message ?? 'network error'}. ` +
     `Check your connection (and CORTEX_URL if you set it).`,
   )
 }
@@ -190,7 +190,7 @@ export async function checkToken(token, base) {
   }
   if (!isUuid(token)) {
     return { ok: false, status: 0, diagnosis: { kind: 'config', retriable: false,
-      message: `Token "${String(token).slice(0, 8)}…" is not a valid Cortex token (expected a UUID). ` +
+      message: `Token "${String(token).slice(0, 8)}…" is not a valid Agnoclast token (expected a UUID). ` +
         `Re-run setup with the token from the console.` } }
   }
   const url = `${(base ?? 'https://cortex-console.vercel.app').replace(/\/$/, '')}/api/mcp-context`

package/lib/docs_scan.mjs

@@ -6,7 +6,7 @@ import { join, resolve, dirname } from 'path'
 // Documentation ingestion — detection half (D1 of docs/documentation-ingestion-spec.md).
 //
 // Specs/plans/design docs get written to disk (repo docs/, ~/.gstack/projects/…) and never reach
-// Cortex as pages. This subcommand DETECTS new/changed markdown under registered roots by content
+// Agnoclast as pages. This subcommand DETECTS new/changed markdown under registered roots by content
 // hash; the AUTHORING is done by the live session (the cortex-author-docs skill reads each pending
 // doc and calls the `author` MCP tool) — the agent is the pipe, never a raw-markdown dump.
 //
@@ -90,7 +90,7 @@ export function markFiles(state, paths, now = new Date().toISOString()) {
 }
 
 // Heuristic soak guardrail (spec D5): the Robin parity experiment forbids re-syncing the local
-// brain into Cortex during the window, so warn when a root looks like the brain repo.
+// brain into Agnoclast during the window, so warn when a root looks like the brain repo.
 const looksLikeBrain = (dir) => /\/Documents\/brain(\/|$)/.test(dir)
 
 export async function runDocsScan(argv = []) {
@@ -111,7 +111,7 @@ export async function runDocsScan(argv = []) {
     const abs = resolve(dir)
     if (!existsSync(abs)) { process.stderr.write(`Not a directory: ${abs}\n`); return 1 }
     if (looksLikeBrain(abs)) {
-      out(`⚠ ${abs} looks like the local brain repo — the Robin parity soak forbids re-syncing it into Cortex.`)
+      out(`⚠ ${abs} looks like the local brain repo — the Robin parity soak forbids re-syncing it into Agnoclast.`)
       out('  Registering anyway is on you; the cortex-author-docs skill will also warn.')
     }
     if (!state.roots.includes(abs)) state.roots.push(abs)
@@ -163,7 +163,7 @@ export async function runDocsScan(argv = []) {
   }
   if (!pending.length) out(`✓ up to date — ${scanned} doc(s) scanned, nothing pending`)
   else {
-    out(`${pending.length} doc(s) pending Cortex authoring (of ${scanned} scanned):`)
+    out(`${pending.length} doc(s) pending Agnoclast authoring (of ${scanned} scanned):`)
     for (const p of pending) out(`  ${p.status === 'new' ? '+ ' : '~ '}${p.path}`)
     out('Author them via the cortex-author-docs skill, then:  docs-scan --mark <file>...')
   }

package/lib/doctor.mjs

@@ -6,7 +6,7 @@ import { checkToken, resolveBase } from './diagnose.mjs'
 // `npx @theronap/cortex-mcp doctor` — a live, one-command health check.
 //
 // This is the "is it ACTUALLY working?" tool that was missing: it reads your token, calls the
-// real Cortex API, and prints a clear PASS/FAIL with the actual cause. No Claude Code restart
+// real Agnoclast API, and prints a clear PASS/FAIL with the actual cause. No Claude Code restart
 // needed — so onboarding can confirm the connection independently of "did the server load."
 
 // Token resolution: env first, then the Claude config the setup command wrote (so `doctor`
@@ -24,7 +24,7 @@ function resolveToken() {
   return { token: null, source: null }
 }
 
-// `status` — the one-line SessionStart variant of doctor: a visible "is Cortex capturing?"
+// `status` — the one-line SessionStart variant of doctor: a visible "is Agnoclast capturing?"
 // signal inside Claude Code itself (three-machine dry-run finding 2026-06-09: with no
 // indicator, a user can't tell whether their sessions are flowing to the org).
 // Always returns 0 — a status line must never break a session start.
@@ -33,19 +33,19 @@ export async function runStatus() {
   const out = (m) => process.stdout.write(m + '\n')
   const { token } = resolveToken()
   if (!token) {
-    out('Cortex: NOT connected — no token found. Run: npx -y @theronap/cortex-mcp setup <token>')
+    out('Agnoclast: NOT connected — no token found. Run: npx -y @theronap/cortex-mcp setup <token>')
     return 0
   }
   try {
     const r = await checkToken(token, base)
     if (r.ok) {
       const n = typeof r.projectCount === 'number' ? ` · ${r.projectCount} project${r.projectCount === 1 ? '' : 's'} visible` : ''
-      out(`Cortex: connected — sessions on this machine are captured to your org${n}.`)
+      out(`Agnoclast: connected — sessions on this machine are captured to your org${n}.`)
     } else {
-      out(`Cortex: NOT connected — ${r.diagnosis?.message ?? 'check failed'}. Run: npx -y @theronap/cortex-mcp doctor`)
+      out(`Agnoclast: NOT connected — ${r.diagnosis?.message ?? 'check failed'}. Run: npx -y @theronap/cortex-mcp doctor`)
     }
   } catch (e) {
-    out(`Cortex: status check failed (${e?.message ?? String(e)}) — run doctor.`)
+    out(`Agnoclast: status check failed (${e?.message ?? String(e)}) — run doctor.`)
   }
   return 0
 }
@@ -55,7 +55,7 @@ export async function runDoctor() {
   const out = (m) => process.stdout.write(m + '\n')
 
   out('')
-  out('Cortex doctor — checking your connection…')
+  out('Agnoclast doctor — checking your connection…')
   const { token, source } = resolveToken()
   out(`  token source: ${source ?? 'NONE FOUND'}`)
   out(`  endpoint:     ${base}`)
@@ -64,11 +64,11 @@ export async function runDoctor() {
   const r = await checkToken(token, base)
 
   if (r.ok) {
-    out('  ✓ PASS — your token authenticates and Cortex returned your context.')
+    out('  ✓ PASS — your token authenticates and Agnoclast returned your context.')
     if (typeof r.projectCount === 'number') out(`    You can currently see ${r.projectCount} project(s).`)
     if (r.requestId) out(`    (request id: ${r.requestId})`)
     out('')
-    out('  If your AI still does not see Cortex, the server just is not loaded yet —')
+    out('  If your AI still does not see Agnoclast, the server just is not loaded yet —')
     out('  fully quit and reopen Claude Code (the MCP server starts on launch).')
     out('')
     return 0

package/lib/editors/antigravity.mjs

@@ -55,7 +55,7 @@ export function renderAntigravityPlist({ home = homedir() } = {}) {
  *  NOTE the AGENT_DIR line is the portability blocker documented above. */
 export function renderAntigravitySyncSh() {
   return `#!/bin/bash
-# Cortex ⇄ Antigravity one-shot sync, triggered by launchd WatchPaths on the Antigravity
+# Agnoclast ⇄ Antigravity one-shot sync, triggered by launchd WatchPaths on the Antigravity
 # trajectory store. There is no resident daemon — launchd wakes this on change and it exits.
 # Token is resolved from the wired MCP config at runtime (never stored in plist/script).
 # ⚠ AGENT_DIR points at a local dev checkout — see antigravity.mjs BLOCKER note (not coworker-portable).

package/lib/editors/claude.mjs

@@ -6,7 +6,7 @@ import { existsSync } from 'node:fs'
 import { join } from 'node:path'
 import { readJson, backupFile, ensureDir, writeJson } from './_fsutil.mjs'
 
-/** Merge the Cortex MCP server into a ~/.claude.json object. Pure + idempotent: sets only the
+/** Merge the Agnoclast MCP server into a ~/.claude.json object. Pure + idempotent: sets only the
  *  `cortex` entry (type:'stdio'), preserves every other server. `spec` = the package@dist-tag string. */
 export function mergeClaudeMcp(existing, spec, token) {
   const cfg = existing && typeof existing === 'object' ? { ...existing } : {}
@@ -15,7 +15,7 @@ export function mergeClaudeMcp(existing, spec, token) {
   return cfg
 }
 
-/** The Cortex tools every seat may run WITHOUT a permission prompt: the read surface, the live
+/** The Agnoclast tools every seat may run WITHOUT a permission prompt: the read surface, the live
  *  authoring core, and trivially-reversible maintenance. The contract this enforces: authoring is
  *  EXPECTED agent behavior — a page update must never stall on a yes/no dialog the user won't read
  *  (the ask-permission failure mode is how pages go stale). Safe because every page edit is
@@ -38,7 +38,7 @@ export const CORTEX_ALLOWED_TOOLS = [
   'set_page_validity', 'snooze_red_link', 'attribute_thread',
 ].map((t) => `mcp__cortex__${t}`)
 
-/** Merge Cortex's Claude Code hooks into a ~/.claude/settings.json object. Pure + idempotent: drops
+/** Merge Agnoclast's Claude Code hooks into a ~/.claude/settings.json object. Pure + idempotent: drops
  *  any prior cortex entry (old token/path/version) from each hook array before appending the current
  *  one — capture (Stop), status + skills-repair + snapshot-context (SessionStart), hydrate
  *  (UserPromptSubmit), precompact (PreCompact). Commands carry NO inline token (each subcommand

package/lib/editors/codex.mjs

@@ -6,7 +6,7 @@ import { existsSync, readFileSync, writeFileSync } from 'node:fs'
 import { join } from 'node:path'
 import { readJson, backupFile, ensureDir, writeJson } from './_fsutil.mjs'
 
-/** Merge the Cortex MCP server into a Codex config.toml. Pure + idempotent: strips any existing
+/** Merge the Agnoclast MCP server into a Codex config.toml. Pure + idempotent: strips any existing
  *  [mcp_servers.cortex] / [mcp_servers.cortex.env] tables (so re-runs update in place rather than
  *  duplicating — a duplicate TOML table would break Codex's parser), preserves every other table,
  *  and appends a fresh block. Only touches the cortex tables; never rewrites the user's config. */

package/lib/editors/cursor.mjs

@@ -6,7 +6,7 @@ import { existsSync, readFileSync, writeFileSync, mkdirSync } from 'node:fs'
 import { join } from 'node:path'
 import { backupFile } from './_fsutil.mjs'
 
-/** Merge the Cortex MCP server into a Cursor mcp.json object. Pure + idempotent: sets only the
+/** Merge the Agnoclast MCP server into a Cursor mcp.json object. Pure + idempotent: sets only the
  *  `cortex` entry, preserves every other server. `spec` is the package@dist-tag STRING — the same
  *  convention claude/codex/setup.mjs use, so one install driver can pass a single spec to every adapter. */
 export function mergeCursorMcp(existing, spec, token) {

package/lib/editors/index.mjs

@@ -1,4 +1,4 @@
-// Editor adapter registry (P0-b task 1). One place that knows every editor Cortex can wire.
+// Editor adapter registry (P0-b task 1). One place that knows every editor Agnoclast can wire.
 // Adding an editor = add a module here; the install driver + capability manifest fall out of it.
 //
 // EditorAdapter shape (see the four modules):

package/lib/graphify_sync.mjs

@@ -82,7 +82,7 @@ export async function runGraphifySync(argv = []) {
   }
   const payload = await res.json()
   process.stdout.write(
-    `Logged to Cortex timeline: ${repo}@${commitSha.slice(0, 7)} (${nodeCount} nodes, ${edgeCount} edges, ${communityCount} communities)` +
+    `Logged to Agnoclast timeline: ${repo}@${commitSha.slice(0, 7)} (${nodeCount} nodes, ${edgeCount} edges, ${communityCount} communities)` +
       `${payload.inserted ? '' : ' (already logged)'}\n`,
   )
   return 0

package/lib/grep_cli.mjs

@@ -56,7 +56,7 @@ export async function runGrep(rest = []) {
   const TOKEN = process.env.CORTEX_TOKEN
   const BASE = resolveBase(process.env.CORTEX_URL)
   if (!TOKEN) {
-    process.stderr.write('cortex grep: CORTEX_TOKEN is required (get yours from the Cortex console).\n')
+    process.stderr.write('cortex grep: CORTEX_TOKEN is required (get yours from the Agnoclast console).\n')
     return 1
   }
   const { query, mode, max } = parseGrepArgs(rest)

package/lib/hydrate.mjs

@@ -7,7 +7,7 @@ import { formatReceipt, renderUncounted, subjectOf } from './presence.mjs'
 import { writePresence } from './statusline.mjs'
 
 // UserPromptSubmit hook (① discovery): on the FIRST substantive turn of a session, hydrate the model
-// with query-centered Cortex context BEFORE it answers — then never again this session. It closes the
+// with query-centered Agnoclast context BEFORE it answers — then never again this session. It closes the
 // gap that read-triggered authoring can't: an agent that never READS the wiki (works from code + memory)
 // never triggers a currency update, and re-derives already-authored truth. cortex-context is a SKILL the
 // model may forget to invoke; this makes the first hydration non-discretionary (the same move that made

package/lib/imessage_send.mjs

@@ -1,5 +1,5 @@
 // send_imessage — outbound iMessage via Messages.app. This is a personal automation, NOT org
-// intelligence: it writes nothing to Cortex. Three layers of safety (eng-review D3/D6/D10):
+// intelligence: it writes nothing to Agnoclast. Three layers of safety (eng-review D3/D6/D10):
 //   D6  argv-safe: recipient + body are passed as osascript `on run argv` arguments, NEVER
 //       interpolated into the script source → no AppleScript injection, no quote/newline breakage.
 //   D3  draft-by-default: nothing sends unless the caller explicitly passes send:true.

package/lib/ingest_folder.mjs

@@ -3,7 +3,7 @@ import { join, relative, basename, extname } from 'node:path'
 import { fetchCortex, classify, resolveBase } from './diagnose.mjs'
 
 // `cortex-mcp ingest-folder <path>` — walk a local markdown folder and upsert each file as an
-// AUTHORED record in Cortex (source='brain'), so a user's personal digest is built from THEIR
+// AUTHORED record in Agnoclast (source='brain'), so a user's personal digest is built from THEIR
 // notes (Robin parity). Only an EXCERPT of each file leaves the machine (frontmatter + first
 // ~800 chars), never the full body. The server clamps privacy for source='brain' and treats
 // sessionId (the file's relative path) as the stable dedupe key, so re-running updates in place.
@@ -100,7 +100,7 @@ export async function runIngestFolder(argv) {
   if (!path) {
     process.stderr.write(
       'usage: cortex-mcp ingest-folder <path>\n' +
-      '  Ingest a local markdown folder as your authored Cortex records.\n',
+      '  Ingest a local markdown folder as your authored Agnoclast records.\n',
     )
     return
   }

package/lib/install.mjs

@@ -1,4 +1,4 @@
-// `cortex install` — the cross-editor hub installer (P0-b). One command that wires the Cortex MCP
+// `cortex install` — the cross-editor hub installer (P0-b). One command that wires the Agnoclast MCP
 // server + client shim into EVERY detected editor via the adapter registry, then writes a capability
 // manifest so later pillars (session sync, skill sync, doc sync) know which channels each editor
 // supports. `setup <token>` stays as the single-editor path the console prints; `install` is the
@@ -78,7 +78,7 @@ export async function runInstall(argv, version) {
     process.stderr.write(
       'Usage: npx @theronap/cortex-mcp install [<CORTEX_TOKEN>] [--editor auto|all|<id,...>]\n\n' +
       'No token was given and none is already wired.\n' +
-      'Get your token from the Cortex console → Connect your AI.\n',
+      'Get your token from the Agnoclast console → Connect your AI.\n',
     )
     process.exit(1)
   }
@@ -92,7 +92,7 @@ export async function runInstall(argv, version) {
   }
 
   log('')
-  log('Cortex install — wiring your AI editors…')
+  log('Agnoclast install — wiring your AI editors…')
   if (editor === 'auto' && targets.length === 0) {
     log('  (no supported editors detected — pass --editor all to force, or install an editor first)')
   }
@@ -135,7 +135,7 @@ export async function runInstall(argv, version) {
   // Verify the token against the live API — writing config proves "files written", not "it works".
   const base = resolveBase(process.env.CORTEX_URL)
   log('')
-  log('Verifying your token against Cortex…')
+  log('Verifying your token against Agnoclast…')
   try {
     const health = await checkToken(token, base)
     if (health.ok) {
@@ -147,13 +147,13 @@ export async function runInstall(argv, version) {
       log('     The files are in place; fix the above, then re-check with `doctor`.')
     }
   } catch (e) {
-    log(`  ⚠ Could not reach Cortex to verify (${e.message}). Config is written; re-check with 'doctor'.`)
+    log(`  ⚠ Could not reach Agnoclast to verify (${e.message}). Config is written; re-check with 'doctor'.`)
   }
 
   const wired = entries.filter((e) => targetIds.has(e.adapter.id) && e.wired).map((e) => e.adapter.displayName)
   log('')
   log(`⟳ Wired ${wired.length} editor(s): ${wired.join(', ') || '(none)'}`)
-  log('   Fully quit and reopen each editor to load the Cortex server.')
+  log('   Fully quit and reopen each editor to load the Agnoclast server.')
   log(`   Console: ${base}`)
   log('')
 }

package/lib/precompact.mjs

@@ -8,7 +8,7 @@
 // Output goes to stdout, which the Claude Code harness surfaces as additional context for the next turn.
 export function runPrecompactReminder() {
   process.stdout.write(
-    'Cortex: context is about to compact. If your understanding of any node (the project(s) you worked ' +
+    'Agnoclast: context is about to compact. If your understanding of any node (the project(s) you worked ' +
     'on, people you coordinated with, or yourself) advanced this session, AUTHOR it into the wiki NOW ' +
     'before it is lost: call `authoring_context` then `author` for each. This is a synthesis of your ' +
     'compiled understanding with inline [[links]], not a transcript dump. Skip nodes you did not advance.\n',

package/lib/redact.mjs

@@ -21,7 +21,7 @@ const PATTERNS = [
   [/xox[baprs]-[A-Za-z0-9-]{10,}/g, '[REDACTED:slack]'],
   [/eyJ[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}/g, '[REDACTED:jwt]'],
   [/(Bearer\s+)[A-Za-z0-9._-]{20,}/g, '$1[REDACTED]'],
-  // Cortex's own login token wherever it appears in KEY=value / KEY: value form (hooks.json,
+  // Agnoclast's own login token wherever it appears in KEY=value / KEY: value form (hooks.json,
   // config.toml, shell commands — the 2026-07-02 finding: a grep of hooks.json put the live token
   // in a transcript and nothing below caught it). Specific pattern first for the accurate label.
   [/(CORTEX_TOKEN["']?\s*[=:]\s*["']?)[0-9a-fA-F][0-9a-fA-F-]{30,}/g, '$1[REDACTED:cortex-token]'],

package/lib/server.mjs

@@ -40,7 +40,7 @@ async function redLinkTriage(BASE, TOKEN, name) {
 // file-request tools, and a module-level `fail` would be silently shadowed by it from that point on.
 const toolError = (text) => ({ content: [{ type: 'text', text }], isError: true })
 
-// The Cortex MCP server (stdio). Serves the signed-in employee's scoped org
+// The Agnoclast MCP server (stdio). Serves the signed-in employee's scoped org
 // context to their AI assistant. CORTEX_TOKEN identifies the user + org.
 
 export async function runServer(version) {
@@ -48,7 +48,7 @@ export async function runServer(version) {
   const BASE = resolveBase(process.env.CORTEX_URL)
 
   if (!TOKEN) {
-    process.stderr.write('cortex-mcp: CORTEX_TOKEN is required. Get yours from the Cortex console → Connect your AI.\n')
+    process.stderr.write('cortex-mcp: CORTEX_TOKEN is required. Get yours from the Agnoclast console → Connect your AI.\n')
     process.exit(1)
   }
 
@@ -90,7 +90,7 @@ export async function runServer(version) {
     const now = Date.now()
     if (cache && now - cache.ts < 5 * 60 * 1000) return cache.text
     // fetchCortex retries transient infra/5xx; classify turns a failure into an honest message
-    // (token vs infra-block vs network) instead of a bare "Cortex API 403: unknown".
+    // (token vs infra-block vs network) instead of a bare "Agnoclast API 403: unknown".
     const res = await fetchCortex(`${BASE}/api/mcp-context`, { headers: { Authorization: `Bearer ${TOKEN}` } })
     if (!res.ok) {
       const body = await res.text()
@@ -117,7 +117,7 @@ export async function runServer(version) {
   server.registerTool(
     'my_context',
     {
-      title: 'My Cortex context',
+      title: 'My Agnoclast context',
       description: 'Your current work context from the org. Pass a question to get query-centered session context seeded from the most relevant node and its neighborhood; omit it for the baseline snapshot.',
       inputSchema: { question: z.string().optional().describe('optional opening user question to center the context around') },
     },
@@ -144,8 +144,8 @@ export async function runServer(version) {
   server.registerTool(
     'log_session',
     {
-      title: 'Log this session to Cortex',
-      description: 'Persist a CURATED summary of this work session as its durable Cortex record (authoritative — supersedes the auto-capture hook). Call at session close after composing the summary. Pass sessionId (the Claude Code session id) if you have it so this dedupes with the auto-capture of the same session.',
+      title: 'Log this session to Agnoclast',
+      description: 'Persist a CURATED summary of this work session as its durable Agnoclast record (authoritative — supersedes the auto-capture hook). Call at session close after composing the summary. Pass sessionId (the Claude Code session id) if you have it so this dedupes with the auto-capture of the same session.',
       inputSchema: {
         summary: z.string().describe('the curated session summary (what was done, decided, left open) — becomes the durable record'),
         project: z.string().optional().describe('project key/name this session worked in'),
@@ -172,7 +172,7 @@ export async function runServer(version) {
         throw new Error(classify(res.status, res.headers.get('content-type'), body, res.headers.get('x-vercel-id')).message)
       }
       const j = await res.json().catch(() => ({}))
-      return { content: [{ type: 'text', text: `Logged to Cortex (authoritative): "${j.title ?? title ?? 'session'}" — ${j.inserted ? 'new record' : 'updated existing'}.` }] }
+      return { content: [{ type: 'text', text: `Logged to Agnoclast (authoritative): "${j.title ?? title ?? 'session'}" — ${j.inserted ? 'new record' : 'updated existing'}.` }] }
     },
   )
 
@@ -354,7 +354,7 @@ export async function runServer(version) {
     {
       title: 'Query the local code structure graph (graphify)',
       description:
-        'Query a structural code graph for the repo at the CURRENT working directory, built locally by graphify (tree-sitter AST — deterministic, no LLM, no server round-trip; this is LOCAL MACHINE data, not org-shared Cortex content, and reflects a snapshot of one commit, not live files). Use for MULTI-HOP questions a single grep cannot answer: what calls/imports/depends on X, how A structurally reaches B, or a repo-wide overview (hub/community files). Do NOT use for single-hop lookups (does file X import Y) — grep is faster and always current. Structure only — it knows what imports/calls what, never WHY; read the actual files or authored Cortex pages for intent.',
+        'Query a structural code graph for the repo at the CURRENT working directory, built locally by graphify (tree-sitter AST — deterministic, no LLM, no server round-trip; this is LOCAL MACHINE data, not org-shared Agnoclast content, and reflects a snapshot of one commit, not live files). Use for MULTI-HOP questions a single grep cannot answer: what calls/imports/depends on X, how A structurally reaches B, or a repo-wide overview (hub/community files). Do NOT use for single-hop lookups (does file X import Y) — grep is faster and always current. Structure only — it knows what imports/calls what, never WHY; read the actual files or authored Agnoclast pages for intent.',
       inputSchema: {
         action: z.enum(['query', 'path', 'explain']).describe('"query" = open-ended natural-language question (graph traversal); "path" = shortest structural path between two named nodes; "explain" = describe one node and list its direct connections'),
         question: z.string().optional().describe('required for action:"query" — the natural-language question'),
@@ -419,7 +419,7 @@ export async function runServer(version) {
       description:
         'READ the full authored wiki page for one node (project/person/org/you) by its canonical name — every section, every tier you can see. This is how you READ a node; `grep` only LOCATES pages (snippets + their [[links]]), it does not read them. Navigate like a researcher: read the page you need, then FOLLOW its inline [[links]] by calling read_page on each linked name — keep following while the linked pages stay relevant, stop when they do not. You decide how deep to go. Returns only what you are permitted to see.',
       inputSchema: {
-        name: z.string().describe('the canonical node name exactly as written (e.g. "Cortex", "Ben", or a [[link]] target) — identifier links ([[repo:owner/name]]) resolve to their authored HOME + a visible-event count'),
+        name: z.string().describe('the canonical node name exactly as written (e.g. "Agnoclast", "Ben", or a [[link]] target) — identifier links ([[repo:owner/name]]) resolve to their authored HOME + a visible-event count'),
         kind: z.enum(['project', 'person', 'org', 'user']).optional().describe('node kind (default project; pass person/org for people/teams)'),
         expand: z.boolean().optional().describe('identifier names only: also list recent visible timeline events for this identifier (default: home + count)'),
         history: z.boolean().optional().describe('node names only: return the node\'s TIMELINE (events joined via its [[repo:…]] stamps, reverse-chron, viewer-visible) instead of the page body. The page is the present; this is the history.'),
@@ -593,7 +593,7 @@ export async function runServer(version) {
       title: 'See a wiki page\'s edit history',
       description: 'Show the VERSION history of an authored wiki page — every prior version, who changed it and when, newest first. This is how you see "what changed on this page and by whom", and it includes privacy changes (re-tiers). Then use `read_page` with a version to view an old body, or `rollback_page` to restore one. (Distinct from read_page\'s `history: true`, which is the raw event timeline via [[repo:…]] stamps.) RLS-scoped: you see history only for pages you may read.',
       inputSchema: {
-        name: z.string().describe('the canonical node name exactly as written (e.g. "Cortex", "Ben")'),
+        name: z.string().describe('the canonical node name exactly as written (e.g. "Agnoclast", "Ben")'),
         kind: z.enum(['project', 'person', 'org', 'user']).optional().describe('node kind (default project)'),
         limit: z.number().int().optional().describe('how many recent versions to show (default 20, max 200)'),
       },
@@ -1188,7 +1188,7 @@ export async function runServer(version) {
     {
       title: 'Create a new brain under your existing account',
       description: 'Create a brand-new brain (org/workspace) — a fully independent knowledge graph — under your EXISTING account. No new login, no new email/password: this adds a second membership to the account you are already using. Reads never cross brains; new pages default to your active brain, so use pass `brain` when an operation needs one named',
-      inputSchema: { name: z.string().describe('display name for the new brain, e.g. "Cortex Codebase"') },
+      inputSchema: { name: z.string().describe('display name for the new brain, e.g. "Design Team"') },
     },
     async ({ name }) => {
       let res
@@ -1279,7 +1279,7 @@ export async function runServer(version) {
     'my_sessions',
     {
       title: 'My active AI sessions',
-      description: "See what all of YOUR OWN active Cortex/AI sessions are doing right now (working directory + how recently each was active), so you can coordinate across windows/devices. Self-only — only your own sessions, never anyone else's.",
+      description: "See what all of YOUR OWN active Agnoclast/AI sessions are doing right now (working directory + how recently each was active), so you can coordinate across windows/devices. Self-only — only your own sessions, never anyone else's.",
       inputSchema: {},
     },
     async () => {
@@ -1507,10 +1507,17 @@ export async function runServer(version) {
         return toolError(`Could not replace variant: ${d.message}`)
       }
       if (!out) return { content: [{ type: 'text', text: 'Replace reported success, but the server returned no body — re-read the page before assuming it landed.' }] }
+      // The summary rides along with the body, EXCEPT when the source has none — then the target's is
+      // kept rather than erased. Say so on its own line rather than at the tail of `note`: this is the
+      // 2026-08-04 W3 shape, where an empty summary copied over a populated one destroyed 31 of them
+      // under a report that read as success. A rescue the operator does not see is still a silent write.
+      const rescued = out.summaryRescued
+        ? `\n\n⚠ The ${out.moved.from} variant had NO summary. The ${out.moved.to} page's own summary was KEPT rather than overwritten with an empty one — check it still describes the body that just landed, and set_summary if not.`
+        : ''
       return {
         content: [{
           type: 'text',
-          text: `Done — "${out.moved.title}": the ${out.moved.from} body now occupies the ${out.moved.to} page (${out.sections} section${out.sections === 1 ? '' : 's'}), and the ${out.moved.from} variant was removed. The node now has ONE variant. ${out.note}`,
+          text: `Done — "${out.moved.title}": the ${out.moved.from} body now occupies the ${out.moved.to} page (${out.sections} section${out.sections === 1 ? '' : 's'}), and the ${out.moved.from} variant was removed. The node now has ONE variant. Both prior bodies are retained in page history.${rescued}`,
         }],
       }
     },
@@ -1710,7 +1717,7 @@ export async function runServer(version) {
     'decide_file_request',
     {
       title: 'Approve or deny a file request',
-      description: 'As the OWNER of a record, approve or deny someone\'s request for its full original. On approve, your Cortex desktop app fetches + shares the file. Get request_id from file_requests.',
+      description: 'As the OWNER of a record, approve or deny someone\'s request for its full original. On approve, your Agnoclast desktop app fetches + shares the file. Get request_id from file_requests.',
       inputSchema: { request_id: z.string(), decision: z.enum(['approve', 'deny']) },
     },
     async ({ request_id, decision }) => {
@@ -1752,7 +1759,7 @@ export async function runServer(version) {
     },
   )
 
-  // send_imessage — local outbound texting (NOT org intelligence; writes nothing to Cortex). Runs on
+  // send_imessage — local outbound texting (NOT org intelligence; writes nothing to Agnoclast). Runs on
   // this machine via Messages.app. Draft-by-default + recipient allowlist + OOB confirm (D3/D6/D10).
   server.registerTool(
     'send_imessage',
@@ -1776,7 +1783,7 @@ export async function runServer(version) {
   // Two tools the working session uses to AUTHOR its understanding into the org wiki while it's hot:
   //   authoring_context → the companion call (§3): fetch the visible NAMESPACE + the node-type connection
   //     rules BEFORE writing, so the page links canonically (the L2 lever).
-  //   author           → the write (§9 step 3/4): hand Cortex a finished page (summary + sections WITH
+  //   author           → the write (§9 step 3/4): hand Agnoclast a finished page (summary + sections WITH
   //     inline [[links]]); the server runs the resolution pass + tier-safe 2B write.
 
   server.registerTool(
@@ -1784,7 +1791,7 @@ export async function runServer(version) {
     {
       title: 'Authoring context (call before author)',
       description:
-        'Fetch the scaffolding to author a Cortex wiki node: the canonical NAMESPACE (current node names — link to these with the EXACT name inside [[ ]]), any deliberately RETIRED page names and their successors, and the node-type CONNECTION RULES. ALWAYS call this BEFORE `author` so the page links to current knowledge rather than minting synonyms or reviving a retired page. Reference a node in the namespace as [[Name]]; if you reference something real that is NOT in the namespace, still write [[Name]] — that is a red-link marking a node worth creating. If the page IS about a specific code repo or chat channel, also stamp it once — [[repo:owner/name]] or [[channel:name]] (lowercase, no #) — identifier join keys, not page links.',
+        'Fetch the scaffolding to author a Agnoclast wiki node: the canonical NAMESPACE (current node names — link to these with the EXACT name inside [[ ]]), any deliberately RETIRED page names and their successors, and the node-type CONNECTION RULES. ALWAYS call this BEFORE `author` so the page links to current knowledge rather than minting synonyms or reviving a retired page. Reference a node in the namespace as [[Name]]; if you reference something real that is NOT in the namespace, still write [[Name]] — that is a red-link marking a node worth creating. If the page IS about a specific code repo or chat channel, also stamp it once — [[repo:owner/name]] or [[channel:name]] (lowercase, no #) — identifier join keys, not page links.',
       inputSchema: {
         kind: z.enum(['project', 'person', 'org', 'user']).optional().describe('the node type you are about to author (default project)'),
         brain: z.string().optional().describe('which brain\'s namespace to describe — pass the SAME brain you will pass to `author`, so the namespace you plan against is the one your write lands in. Unnecessary when you only have one brain.'),
@@ -1827,7 +1834,7 @@ export async function runServer(version) {
         'Write your CURRENT understanding of a project/person/org/you into the org wiki as a maintained page. Call `authoring_context` FIRST. Author from your own synthesis of the session — the compiled mental model, not a transcript dump: what it IS, where it stands, dated decisions, open threads, key people. Weave inline [[links]] to other nodes (canonical names from the namespace; red-links for wanted-but-absent nodes). The server re-authorizes the tier and resolves links. CREATES the node if it does not exist yet (project/person/org) — the conversation IS the evidence, so a brand-new entity that surfaced only in this session is authorable on the spot; you do NOT need prior records. Because such a node has nothing external to corroborate it, author it DELIBERATELY: only when you genuinely understand it is a real, distinct entity, and use its exact canonical name so it does not duplicate one already in the namespace (`user` nodes are never created). Use this continuously whenever your understanding of a node meaningfully advanced, and at session end (/log). Authoring is PRE-AUTHORIZED — never ask the user "should I update the page?" before calling this (every edit is versioned + reversible via page_history/rollback_page); update, then briefly report what you updated. ⚠ WHICH BRAIN A NEW PAGE GOES IN IS A CONTENT DECISION, SO MAKE IT FROM THE CONTENT. Only a page that exists in NO brain needs this — an update resolves its brain from the page itself. If you hold more than one brain, the server REFUSES a create it cannot attribute (409 `create_needs_brain`) rather than letting the write pointer decide — the pointer is stale out-of-band state that knows nothing about what you are writing. So call `my_brains` (it returns each brain\'s name, page count and sample titles, which is enough to tell what each one is FOR) and pass `brain` up front; that turns a refused round trip into a single call. State which brain you picked and why in one short line, then proceed — do NOT ask when the answer is obvious from the content. DO ask when it is genuinely ambiguous: brains are a confidentiality boundary, so a page born in the wrong one can expose private work to a teammate, and that is not a filing error you can quietly fix later.',
       inputSchema: {
         kind: z.enum(['project', 'person', 'org', 'user']).describe('the node type'),
-        name: z.string().describe('the canonical node name — an EXACT existing name from the namespace to update it, or a new name to create the node (project/person/org). e.g. "Cortex" or "Theron Peterson"'),
+        name: z.string().describe('the canonical node name — an EXACT existing name from the namespace to update it, or a new name to create the node (project/person/org). e.g. "Agnoclast" or "Theron Peterson"'),
         summary: z.string().describe('one-sentence summary of what this is and its current state (may contain [[links]])'),
         sections: z.array(z.object({
           heading: z.string().describe('e.g. Overview, Current state, Decisions, Open threads, People'),

package/lib/setup.mjs

@@ -44,7 +44,7 @@ export async function runSetup(argv, version) {
   if (!token || token.startsWith('-')) {
     process.stderr.write(
       'Usage: npx @theronap/cortex-mcp setup <CORTEX_TOKEN>\n\n' +
-      'Get your token from the Cortex console → Connect your AI.\n'
+      'Get your token from the Agnoclast console → Connect your AI.\n'
     )
     process.exit(1)
   }
@@ -63,7 +63,7 @@ export async function runSetup(argv, version) {
 
   const log = (m) => process.stdout.write(m + '\n')
   log('')
-  log('Cortex setup — wiring your AI assistant…')
+  log('Agnoclast setup — wiring your AI assistant…')
 
   // ── 1. MCP server in ~/.claude.json ──────────────────────────────────────
   try {
@@ -83,7 +83,7 @@ export async function runSetup(argv, version) {
   }
 
   // ── 1b. MCP server in Codex (~/.codex/config.toml), only if Codex is installed ──
-  // Codex gets the same Cortex context tools as Claude Code. Non-fatal: a Codex hiccup must
+  // Codex gets the same Agnoclast context tools as Claude Code. Non-fatal: a Codex hiccup must
   // never block the primary Claude wiring.
   const codexDir = join(home, '.codex')
   if (existsSync(codexDir)) {
@@ -157,7 +157,7 @@ export async function runSetup(argv, version) {
   // ── 4. Self-verify — writing config proves "files written", NOT "connection works".
   // Actually call the API so a bad/expired token is caught HERE, not 40 minutes into debugging.
   log('')
-  log('Verifying your token against Cortex…')
+  log('Verifying your token against Agnoclast…')
   const health = await checkToken(token, base)
   if (health.ok) {
     const n = health.projectCount
@@ -169,8 +169,8 @@ export async function runSetup(argv, version) {
   }
 
   log('')
-  log('⟳ IMPORTANT: fully quit and reopen Claude Code to load the Cortex server.')
-  log('   Then your AI sees your Cortex context and your sessions flow into the org.')
+  log('⟳ IMPORTANT: fully quit and reopen Claude Code to load the Agnoclast server.')
+  log('   Then your AI sees your Agnoclast context and your sessions flow into the org.')
   log('   Re-check anytime:  npx -y @theronap/cortex-mcp doctor')
   log(`   Console: ${base}`)
   log('')
@@ -191,11 +191,11 @@ export async function runRepair(version) {
   const token = readWiredToken()
   if (!token) {
     process.stderr.write(
-      'No existing Cortex token found in ~/.claude.json or ~/.codex/config.toml.\n' +
+      'No existing Agnoclast token found in ~/.claude.json or ~/.codex/config.toml.\n' +
       'Run setup once with your token:  npx -y @theronap/cortex-mcp setup <YOUR_TOKEN>\n',
     )
     process.exit(1)
   }
-  process.stdout.write('Cortex repair — re-running setup with your existing token at this version…\n')
+  process.stdout.write('Agnoclast repair — re-running setup with your existing token at this version…\n')
   await runSetup([token], version)
 }

package/lib/skills.mjs

@@ -3,7 +3,7 @@ import { homedir } from 'os'
 import { join, dirname } from 'path'
 import { fileURLToPath } from 'url'
 
-// Managed Cortex skills.
+// Managed Agnoclast skills.
 //
 // Two sources, one install pipeline:
 //   1. BUNDLED — shipped inside this package (cortex-log, cortex-context, cortex-author-docs).
@@ -155,7 +155,7 @@ export function installSkills(opts = {}) {
 
   if (quiet && (summary.installed.length || summary.repaired.length)) {
     // SessionStart surfaces one line in Claude Code so a silent self-heal isn't invisible.
-    process.stdout.write(`Cortex: synced managed skill(s) into ${summary.targets.join(' + ')}.\n`)
+    process.stdout.write(`Agnoclast: synced managed skill(s) into ${summary.targets.join(' + ')}.\n`)
   }
   return summary
 }
@@ -230,7 +230,7 @@ export async function syncOrgSkills(opts = {}) {
     const bits = []
     if (changed.length) bits.push(`synced ${changed.join(', ')}`)
     if (summary.removed.length) bits.push(`removed ${summary.removed.join(', ')}`)
-    process.stdout.write(`Cortex: org skills — ${bits.join('; ')}${summary.source === 'cache' ? ' (offline cache)' : ''}.\n`)
+    process.stdout.write(`Agnoclast: org skills — ${bits.join('; ')}${summary.source === 'cache' ? ' (offline cache)' : ''}.\n`)
   } else if (!quiet) {
     log(`  ✓ org skills up to date (${currentNames.length} published${skipped.length ? `, ${skipped.length} skipped` : ''})`)
   }
@@ -242,7 +242,7 @@ export async function syncOrgSkills(opts = {}) {
 async function runSkillsPush(argv) {
   const { resolveBase, readWiredToken, fetchCortex } = await import('./diagnose.mjs')
   const token = process.env.CORTEX_TOKEN || readWiredToken()
-  if (!token) { process.stderr.write('No Cortex token wired — run setup first.\n'); return 1 }
+  if (!token) { process.stderr.write('No Agnoclast token wired — run setup first.\n'); return 1 }
   const base = resolveBase(process.env.CORTEX_URL)
 
   let payload
@@ -289,7 +289,7 @@ export async function runSkills(argv = []) {
   if (argv[0] === 'push') return runSkillsPush(argv.slice(1))
 
   const quiet = argv.includes('--quiet')
-  if (!quiet) process.stdout.write('\nCortex skills — installing managed skills…\n')
+  if (!quiet) process.stdout.write('\nAgnoclast skills — installing managed skills…\n')
   const r = installSkills({ quiet })
   if (!quiet) {
     if (!r.targets.length) process.stdout.write('  ! No agent CLI found (~/.claude or ~/.codex). Nothing to install.\n')

package/lib/uninstall.mjs

@@ -3,7 +3,7 @@ import { homedir } from 'os'
 import { join } from 'path'
 import { execFileSync } from 'child_process'
 
-// Full uninstall — the reverse of setup.mjs. Removes EVERY touch-point Cortex writes onto a machine:
+// Full uninstall — the reverse of setup.mjs. Removes EVERY touch-point Agnoclast writes onto a machine:
 //   1. ~/.claude.json          → mcpServers.cortex
 //   2. ~/.claude/settings.json → Stop/SessionStart/PreCompact cortex hooks
 //   3. ~/.codex/config.toml    → [mcp_servers.cortex] + [mcp_servers.cortex.env]
@@ -34,7 +34,7 @@ export function runUninstall(argv = []) {
   const act = (msg) => plan.push(msg)
   const write = (path, data) => { if (!dry) { backup(path); writeFileSync(path, data) } }
 
-  process.stdout.write(dry ? '\nCortex uninstall — DRY RUN (nothing will change):\n\n' : '\nCortex uninstall — removing all wiring…\n\n')
+  process.stdout.write(dry ? '\nAgnoclast uninstall — DRY RUN (nothing will change):\n\n' : '\nAgnoclast uninstall — removing all wiring…\n\n')
 
   // 1. MCP server out of ~/.claude.json
   editJson(CLAUDE_JSON, (cfg) => {
@@ -144,7 +144,7 @@ export function runUninstall(argv = []) {
     }
   }
 
-  if (plan.length === 0) { process.stdout.write('  Nothing to remove — this machine has no Cortex wiring.\n\n'); return }
+  if (plan.length === 0) { process.stdout.write('  Nothing to remove — this machine has no Agnoclast wiring.\n\n'); return }
   process.stdout.write(plan.join('\n') + '\n\n')
   if (dry) {
     process.stdout.write('DRY RUN — nothing changed. Re-run without --dry-run to apply.\n')

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@theronap/cortex-mcp",
-  "version": "0.9.71",
+  "version": "0.9.73",
   "description": "Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.",
   "type": "module",
   "bin": {

package/skills/author-docs/SKILL.md

@@ -1,22 +1,22 @@
 ---
 name: cortex-author-docs
-description: Push new/changed documentation (specs, plans, design docs) from disk into Cortex as authored wiki pages. Run after writing a spec/plan/design doc, when the user asks to sync docs to Cortex, or as part of session close-out.
+description: Push new/changed documentation (specs, plans, design docs) from disk into Agnoclast as authored wiki pages. Run after writing a spec/plan/design doc, when the user asks to sync docs to Agnoclast, or as part of session close-out.
 ---
 
-> **Cortex-managed skill.** This file is installed and kept up to date by Cortex. Local edits are
+> **Agnoclast-managed skill.** This file is installed and kept up to date by Agnoclast. Local edits are
 > restored on the next session (a backup of your version is saved alongside). Don't rely on changes here.
 
 ## Why this exists
 
 Specs, plans, and design docs get written to disk (a repo's `docs/`, skill-generated design docs)
-and never reach Cortex — so the org brain misses its richest artifacts. A spec IS a page: this
+and never reach Agnoclast — so the org brain misses its richest artifacts. A spec IS a page: this
 skill turns pending docs into authored wiki pages. You (the live session) are the pipe — you read
 the doc and author a synthesis. Never dump raw markdown into a page.
 
 ## When to use
 
 - Right after you write or substantially update a spec/plan/design/runbook doc on disk.
-- When the user asks to push/sync docs to Cortex.
+- When the user asks to push/sync docs to Agnoclast.
 - During session close-out (`/cortex-log` runs this as a sweep step).
 
 ## Steps
@@ -67,7 +67,7 @@ the doc and author a synthesis. Never dump raw markdown into a page.
 ## Safety rules
 
 - Do NOT register or sweep the local brain repo (`~/Documents/brain`) while the Robin parity soak
-  is running — the experiment forbids re-syncing Robin into Cortex mid-window.
+  is running — the experiment forbids re-syncing Robin into Agnoclast mid-window.
 - Respect tiers: if a doc is clearly personal/sensitive, author it `confidential` or ask; default
   for work docs is the author path's normal default.
 - This skill writes wiki pages via the `author` tool only. It never sends external messages and

package/skills/context/SKILL.md

@@ -1,9 +1,9 @@
 ---
 name: cortex-context
-description: Automatically hydrate Cortex context at the start of a substantive session. Use when Cortex MCP is available and the user has made a real request, so the first answer is grounded in query-centered org context instead of the static baseline alone.
+description: Automatically hydrate Agnoclast context at the start of a substantive session. Use when Agnoclast MCP is available and the user has made a real request, so the first answer is grounded in query-centered org context instead of the static baseline alone.
 ---
 
-> **Cortex-managed skill.** This file is installed and kept up to date by Cortex. Local edits are
+> **Agnoclast-managed skill.** This file is installed and kept up to date by Agnoclast. Local edits are
 > restored on the next session (a backup of your version is saved alongside). Don't rely on changes here.
 
 ## When to use
@@ -14,12 +14,12 @@ chit-chat and requests where org context is obviously irrelevant.
 ## Steps
 
 1. Call `session_context` with the user's opening request, preserving the actual topic in their words.
-2. Use that returned block as the primary Cortex grounding for the first response.
+2. Use that returned block as the primary Agnoclast grounding for the first response.
 3. If `session_context` is unavailable or errors, fall back to `my_context`.
 4. If the conversation materially changes topics later, call `session_context` again for the new topic.
 
 ## Safety rules
 
-- Do not fabricate Cortex context if the tool fails.
+- Do not fabricate Agnoclast context if the tool fails.
 - Prefer the query-centered `session_context` over static `my_context` whenever the user's topic is clear.
 - Do not call `session_context` for every tiny follow-up; refresh only when the topic meaningfully shifts.

package/skills/log/SKILL.md

@@ -1,14 +1,14 @@
 ---
 name: cortex-log
-description: Close out a work session into Cortex — summarize what happened, confirm it reached the org, and surface anything teammates should know. Run at or near the end of any working session.
+description: Close out a work session into Agnoclast — summarize what happened, confirm it reached the org, and surface anything teammates should know. Run at or near the end of any working session.
 ---
 
-> **Cortex-managed skill.** This file is installed and kept up to date by Cortex. Local edits are
+> **Agnoclast-managed skill.** This file is installed and kept up to date by Agnoclast. Local edits are
 > restored on the next session (a backup of your version is saved alongside). Don't rely on changes here.
 
 ## Model: session-primary, daily-derived
 
-The **session is the primary atomic unit** — one session = one durable Cortex record (via
+The **session is the primary atomic unit** — one session = one durable Agnoclast record (via
 `log_session`, keyed by `sessionId`), which is also the per-record privacy unit (`set_record_privacy`
 is per record). Any "what happened today / this week" view is a **derived rollup** over those session
 records, never a separately-authored primary. This mirrors records(atomic) → digests(derived); the
@@ -16,7 +16,7 @@ personal `/log` skill follows the same shape against the local brain.
 
 ## When to use
 
-At the end of a Claude Code session, or after finishing a meaningful phase of work. Cortex keeps a
+At the end of a Claude Code session, or after finishing a meaningful phase of work. Agnoclast keeps a
 background auto-capture as a fallback, but this skill is the *authoritative* close-out: it composes a
 clean, structured summary and persists THAT as the session's durable record (superseding the
 auto-capture's raw-transcript re-derivation).
@@ -33,7 +33,7 @@ No arguments. Read the conversation context.
    These are the things a teammate or manager would want to know without reading the whole transcript.
 3. **Persist it as the durable record** — call the `log_session` MCP tool with your curated `summary`
    (plus `project`, and the Claude Code `sessionId` if you know it). This writes YOUR summary as the
-   session's authoritative Cortex record (`capture_source='skill'`). The background auto-capture is a
+   session's authoritative Agnoclast record (`capture_source='skill'`). The background auto-capture is a
    fallback and will not overwrite it; passing the same `sessionId` the auto-capture uses dedupes them
    onto one record. This — not the raw-transcript re-derivation — is the canonical record going forward.
 4. **Confirm + flag privacy** — `log_session` returns a confirmation; if it errors, tell the user to
@@ -72,7 +72,7 @@ No arguments. Read the conversation context.
    > verify a write; the result you already have in hand is the strongest.
    >
    > **What replaces it — at the moment of each write, not at the end:** a rejected `author` comes back
-   > as an ORDINARY tool result with **no error flag** — `Could not author "<page>": Cortex API 409:
+   > as an ORDINARY tool result with **no error flag** — `Could not author "<page>": Agnoclast API 409:
    > <reason>` — and `No change to "<page>"` is a **200 OK that wrote nothing**. Neither is an error at
    > the protocol level, so nothing will interrupt you. **Read the result text of every write; never
    > skim it.** That inline read is where this step's value actually was.

package/skills/walkthrough/SKILL.md

@@ -3,7 +3,7 @@ name: cortex-walkthrough
 description: Run the guided Agnoclast walkthrough for someone new. Use when the person asks for the walkthrough, a tutorial, or getting started — "give me the walkthrough", "walk me through this", "how do I use this", "show me around", "what can this do", "remind me how this works" — or when a brand-new user needs orienting for the first time.
 ---
 
-> **Cortex-managed skill.** This file is installed and kept up to date by Cortex. Local edits are
+> **Agnoclast-managed skill.** This file is installed and kept up to date by Agnoclast. Local edits are
 > restored on the next session (a backup of your version is saved alongside). Don't rely on changes here.
 
 # The Agnoclast walkthrough