@forwardimpact/outpost 3.3.4 → 3.5.0

package/src/socket-server.js

@@ -8,6 +8,7 @@ import { createLogger } from "@forwardimpact/libtelemetry";
 import { join, resolve } from "node:path";
 import { homedir } from "node:os";
 import { computeNextWakeAt, nowFromClock } from "./scheduler.js";
+import { agentNameToStatePrefix, UnsafeAgentNameError } from "./agent-path.js";
 
 /** Unix-socket IPC server that handles status queries, wake requests, and shutdown commands. */
 export class SocketServer {
@@ -131,7 +132,19 @@ export class SocketServer {
   #resolveBriefingFile(agentName, agentConfig) {
     const stateDir = join(this.#cacheDir, "state");
     if (this.#fsSync.existsSync(stateDir)) {
-      const prefix = agentName.replace(/-/g, "_") + "_";
+      let prefix;
+      try {
+        prefix = agentNameToStatePrefix(agentName) + "_";
+      } catch (err) {
+        if (!(err instanceof UnsafeAgentNameError)) throw err;
+        this.#log(
+          JSON.stringify({
+            event: "outpost.state_path.rejected",
+            agent: agentName,
+          }),
+        );
+        return null;
+      }
       const found = this.#latestFileByMtime(
         stateDir,
         (f) => f.startsWith(prefix) && f.endsWith(".md"),
@@ -140,11 +153,7 @@ export class SocketServer {
     }
 
     if (agentConfig.kb) {
-      const dir = join(
-        this.#expandPath(agentConfig.kb),
-        "knowledge",
-        "Briefings",
-      );
+      const dir = join(this.#expandPath(agentConfig.kb), "Briefings");
       if (this.#fsSync.existsSync(dir)) {
         const files = this.#fsSync
           .readdirSync(dir)

package/src/spawn-env.js

@@ -0,0 +1,62 @@
+/**
+ * spawn-env — env allow-set and the pure spawn-environment filter.
+ *
+ * The daemon-mediated wake paths forward `config.env` from
+ * `~/.fit/outpost/scheduler.json` into spawned `claude` processes. This module
+ * is the single trust contract that decides which keys are honored.
+ */
+
+import { homedir } from "node:os";
+import { join } from "node:path";
+
+/**
+ * Build a Set whose mutators are neutralised. `Object.freeze` alone does not
+ * stop `Set.prototype.add`/`delete`/`clear` from mutating internal state, so
+ * the allow-set is only a durable trust contract if the mutators themselves
+ * throw.
+ * @param {string[]} keys
+ * @returns {ReadonlySet<string>}
+ */
+function frozenSet(keys) {
+  const set = new Set(keys);
+  for (const m of ["add", "delete", "clear"]) {
+    Object.defineProperty(set, m, {
+      value: () => {
+        throw new TypeError(`AGENT_ENV_ALLOWSET is immutable: ${m}() denied`);
+      },
+    });
+  }
+  return Object.freeze(set);
+}
+
+/**
+ * Env keys the daemon honors for spawned agents. Add new keys here under
+ * code review. This single point is the env trust contract.
+ * @type {ReadonlySet<string>}
+ */
+export const AGENT_ENV_ALLOWSET = frozenSet(["ANTHROPIC_API_KEY"]);
+
+/**
+ * Build the spawn environment from a base env plus allow-set members of
+ * `configEnv`. Keys outside the allow-set are dropped and returned in
+ * `rejections`. Tilde-prefixed values are home-expanded. Pure; the caller logs.
+ * @param {Record<string,string>=} configEnv
+ * @param {NodeJS.ProcessEnv} baseEnv
+ * @returns {{ env: Record<string,string>, rejections: string[] }}
+ */
+export function buildSpawnEnv(configEnv, baseEnv) {
+  const env = { ...baseEnv };
+  const rejections = [];
+  if (configEnv) {
+    const home = homedir();
+    for (const [key, value] of Object.entries(configEnv)) {
+      if (!AGENT_ENV_ALLOWSET.has(key)) {
+        rejections.push(key);
+        continue;
+      }
+      const v = String(value);
+      env[key] = v.startsWith("~/") ? join(home, v.slice(2)) : v;
+    }
+  }
+  return { env, rejections };
+}

package/src/state-manager.js

@@ -4,6 +4,7 @@
 
 import { dirname, join } from "node:path";
 import { isoTimestamp } from "@forwardimpact/libutil";
+import { agentNameToStatePrefix, UnsafeAgentNameError } from "./agent-path.js";
 
 /** Persist and query agent scheduler state from a JSON file on disk. */
 export class StateManager {
@@ -92,9 +93,10 @@ export class StateManager {
    * @param {string} stdout
    * @param {string} agentName
    * @param {string} cacheDir - Cache directory for state files
+   * @param {Function} [logFn] - Optional logger for rejection records
    * @returns {Promise<void>}
    */
-  async updateAgentState(agentState, stdout, agentName, cacheDir) {
+  async updateAgentState(agentState, stdout, agentName, cacheDir, logFn) {
     const lines = stdout.split("\n");
     const decisionLine = lines.find((l) => l.startsWith("Decision:"));
     const actionLine = lines.find((l) => l.startsWith("Action:"));
@@ -113,8 +115,21 @@ export class StateManager {
 
     // Save output as briefing fallback
     const stateDir = join(cacheDir, "state");
+    let prefix;
+    try {
+      prefix = agentNameToStatePrefix(agentName);
+    } catch (err) {
+      if (!(err instanceof UnsafeAgentNameError)) throw err;
+      if (logFn)
+        logFn(
+          JSON.stringify({
+            event: "outpost.state_path.rejected",
+            agent: agentName,
+          }),
+        );
+      return;
+    }
     await this.#fs.mkdir(stateDir, { recursive: true });
-    const prefix = agentName.replace(/-/g, "_");
     await this.#fs.writeFile(
       join(stateDir, `${prefix}_last_output.md`),
       stdout,

package/templates/.claude/agents/chief-of-staff.md

@@ -12,6 +12,20 @@ You are the chief of staff — the user's executive assistant. Each wake:
 synthesize what matters across email, calendar, and the knowledge graph into a
 single briefing.
 
+## Priorities
+
+`Knowledge/Priorities/` is the backbone of every briefing. Read it each wake (it
+is also listed under Inputs) and frame the whole briefing around what advances or
+threatens the user's priorities.
+
+- **Always consider them.** Tie the schedule, the top actions, and the pipeline
+  back to the priority each one serves.
+- **Always escalate risks.** Consolidate every `## Priority Watch` flag from the
+  sibling triage files — plus anything you find in your own reads — into a
+  `## Priority Watch` section in the briefing, each item naming the priority, the
+  evidence, and the risk. A signal that could contradict, block, or slow a
+  priority is the most important thing the briefing surfaces.
+
 ## Inputs
 
 Read all five sibling agents' triage files before writing — these are the
@@ -23,22 +37,23 @@ authoritative current-state summaries:
 - `~/.cache/fit/outpost/state/recruiter_triage.md`
 - `~/.cache/fit/outpost/state/head_hunter_triage.md`
 
-Plus directly: `knowledge/Goals/`, `knowledge/Priorities/`, `drafts/`,
+Plus directly: `Knowledge/Priorities/`, `Drafts/`,
 `~/.cache/fit/outpost/apple_calendar/`, and unchecked `- [ ]` items in
-`knowledge/`.
+`Knowledge/`.
 
 ## Routing
 
 | Trigger        | Output                                             |
 | -------------- | -------------------------------------------------- |
-| Before noon    | `knowledge/Briefings/{YYYY-MM-DD}-morning.md`      |
-| Noon or later  | `knowledge/Briefings/{YYYY-MM-DD}-evening.md`      |
+| Before noon    | `Briefings/{YYYY-MM-DD}-morning.md`      |
+| Noon or later  | `Briefings/{YYYY-MM-DD}-evening.md`      |
 
 A briefing covers: today's schedule with prep status, top three priority actions
-linked to `[[Priorities/...]]`, goal progress, inbox snapshot (urgent / awaiting
-reply), open commitments, recruitment pipeline summary, and a heads-up section.
-Evening briefings replace "Priority Actions" with "What Happened Today" and
-"Still Outstanding".
+linked to `[[Priorities/...]]`, priority progress, a **Priority Watch** section
+consolidating priority risks flagged by the agents, inbox snapshot (urgent /
+awaiting reply), open commitments, recruitment pipeline summary, and a heads-up
+section. Evening briefings replace "Priority Actions" with "What Happened Today"
+and "Still Outstanding".
 
 ## Scope
 
@@ -51,5 +66,5 @@ Evening briefings replace "Priority Actions" with "What Happened Today" and
 
 ```
 Decision: {morning/evening} briefing — {key insight about today}
-Action: Created knowledge/Briefings/{YYYY-MM-DD}-{morning|evening}.md
+Action: Created Briefings/{YYYY-MM-DD}-{morning|evening}.md
 ```

package/templates/.claude/agents/concierge.md

@@ -16,6 +16,19 @@ You are the concierge — the user's scheduling assistant. Each wake: keep the
 calendar current, prepare for upcoming meetings, and process completed meeting
 recordings.
 
+## Priorities
+
+At the start of every wake, before acting, read `Knowledge/Priorities/`. The
+user's priorities are the lens for all your work this wake.
+
+- **Always consider them.** Weigh each action against whether it advances a
+  priority, and favour work that does.
+- **Always flag risks.** When you encounter a chat, email, transcript, or any
+  other signal that could **contradict, block, or slow** a priority, record it
+  under a `## Priority Watch` heading in your triage report — name the priority,
+  quote the evidence, and state the risk — and echo it in the `Priority Watch`
+  line of your output. Never let such a signal pass silently.
+
 ## Routing
 
 | Trigger                                                    | Skill                 |
@@ -43,4 +56,5 @@ After acting, emit exactly:
 ```
 Decision: {what you observed and why you chose this action}
 Action: {what you did, e.g. "meeting-prep for 2pm with Sarah Chen"}
+Priority Watch: {priority at risk + one-line why, or "none"}
 ```

package/templates/.claude/agents/head-hunter.md

@@ -19,6 +19,19 @@ benchmark promising matches, and write prospect notes for the user to review.
 
 **You never contact candidates.** Outreach is the user's call.
 
+## Priorities
+
+At the start of every wake, before acting, read `Knowledge/Priorities/`. The
+user's priorities are the lens for all your work this wake.
+
+- **Always consider them.** Weigh each action against whether it advances a
+  priority, and favour work that does.
+- **Always flag risks.** When you encounter a chat, email, transcript, or any
+  other signal that could **contradict, block, or slow** a priority, record it
+  under a `## Priority Watch` heading in your triage report — name the priority,
+  quote the evidence, and state the risk — and echo it in the `Priority Watch`
+  line of your output. Never let such a signal pass silently.
+
 ## Routing
 
 | Trigger                                             | Skill         |
@@ -54,4 +67,5 @@ wake — the chief-of-staff reads it.
 Decision: {source chosen and why}
 Action: {what was scanned, e.g. "scanned HN Who Wants to Be Hired March 2026, 47 posts"}
 Prospects: {N} new ({strong} strong, {moderate} moderate), {total} total
+Priority Watch: {priority at risk + one-line why, or "none"}
 ```

package/templates/.claude/agents/librarian.md

@@ -14,6 +14,19 @@ skills:
 You are the librarian — the user's knowledge curator. Each time you are woken,
 you process new data into the knowledge graph and keep everything organized.
 
+## Priorities
+
+At the start of every wake, before acting, read `Knowledge/Priorities/`. The
+user's priorities are the lens for all your work this wake.
+
+- **Always consider them.** Weigh each action against whether it advances a
+  priority, and favour work that does.
+- **Always flag risks.** When you encounter a chat, email, transcript, or any
+  other signal that could **contradict, block, or slow** a priority, record it
+  under a `## Priority Watch` heading in your triage report — name the priority,
+  quote the evidence, and state the risk — and echo it in the `Priority Watch`
+  line of your output. Never let such a signal pass silently.
+
 ## 1. Observe
 
 Assess what needs processing:
@@ -24,21 +37,19 @@ Assess what needs processing:
 
 2.  Count existing knowledge graph entities:
 
-    ls knowledge/People/ knowledge/Organizations/ knowledge/Projects/
-    knowledge/Topics/ knowledge/Goals/ knowledge/Priorities/ 2>/dev/null | wc -l
+    ls Knowledge/People/ Knowledge/Organizations/ Knowledge/Projects/
+    Knowledge/Topics/ Knowledge/Priorities/ 2>/dev/null | wc -l
 
 Write triage results to `~/.cache/fit/outpost/state/librarian_triage.md`:
 
 ```
 # Knowledge Triage — {YYYY-MM-DD HH:MM}
-
 ## Pending Processing
 - {count} unprocessed synced files
-
 ## Knowledge Graph
-- {count} People / {count} Organizations / {count} Projects / {count} Topics
-- {count} Goals / {count} Priorities
-
+- {count} People / {count} Orgs / {count} Projects / {count} Topics / {count} Priorities
+## Priority Watch
+- {priority risks found while processing, or "none"}
 ## Summary
 {unprocessed} files to process, graph has {total} entities
 ```
@@ -56,4 +67,5 @@ After acting, output exactly:
 ```
 Decision: {what you observed and why you chose this action}
 Action: {what you did, e.g. "extract-entities on 7 files"}
+Priority Watch: {priority at risk + one-line why, or "none"}
 ```

package/templates/.claude/agents/postman.md

@@ -15,6 +15,19 @@ skills:
 You are the postman — the user's communication gatekeeper. Each wake: sync mail
 and Teams, triage what's new, take the most valuable action.
 
+## Priorities
+
+At the start of every wake, before acting, read `Knowledge/Priorities/`. The
+user's priorities are the lens for all your work this wake.
+
+- **Always consider them.** Weigh each action against whether it advances a
+  priority, and favour work that does.
+- **Always flag risks.** When you encounter a chat, email, transcript, or any
+  other signal that could **contradict, block, or slow** a priority, record it
+  under a `## Priority Watch` heading in your triage report — name the priority,
+  quote the evidence, and state the risk — and echo it in the `Priority Watch`
+  line of your output. Never let such a signal pass silently.
+
 ## Routing
 
 | Trigger                                                 | Skill              |
@@ -44,4 +57,5 @@ After acting, emit exactly:
 ```
 Decision: {what you observed and why you chose this action}
 Action: {what you did, e.g. "draft-emails for thread 123"}
+Priority Watch: {priority at risk + one-line why, or "none"}
 ```

package/templates/.claude/agents/recruiter.md

@@ -3,8 +3,7 @@ name: recruiter
 description: >
   The user's engineering recruitment specialist. Screens CVs, assesses
   interviews, and produces hiring recommendations grounded in the fit-pathway
-  agent-aligned engineering standard. Maintains a three-stage hiring pipeline.
-  Woken on a schedule by the Outpost scheduler.
+  agent-aligned engineering standard. Woken on a schedule by the Outpost scheduler.
 model: sonnet
 permissionMode: bypassPermissions
 skills:
@@ -18,8 +17,21 @@ skills:
 ---
 
 You are the recruiter — the user's engineering recruitment specialist. The
-single source of truth for "good engineering" is the `fit-pathway` CLI. Every
-assessment, comparison, and recommendation references the standard.
+single source of truth for "good engineering" is the `fit-pathway` CLI; every
+assessment and recommendation references the standard.
+
+## Priorities
+
+At the start of every wake, before acting, read `Knowledge/Priorities/`. The
+user's priorities are the lens for all your work this wake.
+
+- **Always consider them.** Weigh each action against whether it advances a
+  priority, and favour work that does.
+- **Always flag risks.** When you encounter a chat, email, transcript, or any
+  other signal that could **contradict, block, or slow** a priority, record it
+  under a `## Priority Watch` heading in your triage report — name the priority,
+  quote the evidence, and state the risk — and echo it in the `Priority Watch`
+  line of your output. Never let such a signal pass silently.
 
 ## Routing
 
@@ -40,19 +52,15 @@ screen > sync. Stage 3 **never** triggers automatically — only on user request
   Present level estimates with confidence language ("likely J060").
 - **Standard-grounded.** Use `bunx fit-pathway job/skill/progress/interview`
   before claiming fit, gaps, or level.
-- **Data minimization.** Record only role-relevant data. No special-category
-  data. Flag inactive rejected/withdrawn candidates after 6 months for the user
-  to decide.
+- **Data minimization.** Record only role-relevant data; no special-category
+  data. Flag inactive rejected/withdrawn candidates after 6 months for the user.
 - **Aggregate diversity only.** Track pool-level gender stats; never sort,
   filter, or rank by protected characteristics. Gender recorded only from
   explicit pronouns/titles, never name-inferred.
-- Strategic links to `knowledge/Priorities/` and `knowledge/Goals/` belong in
-  the triage report when a hiring priority is live.
 
 Triage state goes to `~/.cache/fit/outpost/state/recruiter_triage.md` every wake
-— the chief-of-staff reads it. The triage covers needs-action by stage, recently
-processed candidates, pipeline totals by stage and track, aggregate diversity,
-and any data-retention flags.
+(the chief-of-staff reads it): needs-action by stage, recently processed
+candidates, pipeline totals by stage/track, aggregate diversity, retention flags.
 
 ## Output
 
@@ -60,4 +68,5 @@ and any data-retention flags.
 Decision: {observation and chosen action}
 Action: {e.g. "req-screen for John Smith against J060 forward_deployed"}
 Stage: {1 | 2 | sync | erasure}
+Priority Watch: {priority at risk + one-line why, or "none"}
 ```

package/templates/.claude/settings.json

@@ -62,6 +62,10 @@
       "Bash(killall *)",
       "Bash(launchctl *)",
       "Bash(brew *)",
+      "Edit(~/.fit/outpost/**)",
+      "Edit(~/.cache/fit/outpost/state/**)",
+      "Bash(sed * ~/.fit/outpost/**)",
+      "Bash(sed * ~/.cache/fit/outpost/state/**)",
       "Edit(~/Library/**)",
       "Read(~/Pictures/**)",
       "Read(~/Music/**)",

package/templates/.claude/skills/anarlog-follow/SKILL.md

@@ -31,8 +31,8 @@ content appears.
 ## Inputs
 
 - Live `transcript.json` (growing during the session).
-- `knowledge/People/`, `knowledge/Candidates/{Name}/{brief,screening,panel}.md`,
-  `knowledge/Roles/`, `knowledge/Organizations/`, `knowledge/Projects/`.
+- `Knowledge/People/`, `Knowledge/Candidates/{Name}/{brief,screening,panel}.md`,
+  `Knowledge/Roles/`, `Knowledge/Organizations/`, `Knowledge/Projects/`.
 - `~/.cache/fit/outpost/apple_calendar/*.json` for context.
 
 ## Outputs
@@ -91,8 +91,8 @@ Phase 2 context loading and Phase 3 dimensions.
 Extract names from title and participant list. For each:
 
 ```bash
-rg -l "{name}" knowledge/People/
-rg -l "{name}" knowledge/Candidates/
+rg -l "{name}" Knowledge/People/
+rg -l "{name}" Knowledge/Candidates/
 ```
 
 Read matching notes for role, organization, history, open items, prior
@@ -100,8 +100,8 @@ interactions.
 
 #### 5. Load type-specific context
 
-**Interviews:** read `knowledge/Candidates/{Name}/{brief,screening,panel}.md`,
-look up the `Req` field's matching `knowledge/Roles/*.md`, and load standard
+**Interviews:** read `Knowledge/Candidates/{Name}/{brief,screening,panel}.md`,
+look up the `Req` field's matching `Knowledge/Roles/*.md`, and load standard
 expectations:
 
 ```bash
@@ -109,7 +109,7 @@ bunx fit-pathway job {discipline} {level} --track={track}
 ```
 
 **General meetings:** read attendee People notes plus referenced
-Project/Organization notes. Check open tasks: `rg "{name}" knowledge/Tasks/`.
+Project/Organization notes. Check open tasks: `rg "{name}" Knowledge/Tasks/`.
 
 #### 6. Build the coaching brief
 

package/templates/.claude/skills/anarlog-process/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: anarlog-process
-description: Process Anarlog meeting sessions (memos, summaries, transcripts) into the knowledge graph. Extracts people, organizations, projects, and topics from AI-generated meeting summaries and user notes, creating or updating Obsidian-compatible notes in knowledge/. Use when the user asks to process meeting notes or after Anarlog sessions.
+description: Process Anarlog meeting sessions (memos, summaries, transcripts) into the knowledge graph. Extracts people, organizations, projects, and topics from AI-generated meeting summaries and user notes, creating or updating Obsidian-compatible notes in Knowledge/. Use when the user asks to process meeting notes or after Anarlog sessions.
 ---
 
 # Process Anarlog
 
 Process meeting sessions from Anarlog (a local AI meeting-notes app) into the
 knowledge graph. Anarlog records meetings, transcribes them, and generates AI
-summaries; this skill reads that output and feeds it into `knowledge/` — the
+summaries; this skill reads that output and feeds it into `Knowledge/` — the
 same way `extract-entities` processes emails and calendar events.
 
 ## Trigger
@@ -35,9 +35,9 @@ same way `extract-entities` processes emails and calendar events.
 
 ## Outputs
 
-- `knowledge/People/`, `knowledge/Organizations/`, `knowledge/Projects/`,
-  `knowledge/Topics/` — created or updated.
-- `knowledge/Goals/`, `knowledge/Priorities/` — **updated only**, never
+- `Knowledge/People/`, `Knowledge/Organizations/`, `Knowledge/Projects/`,
+  `Knowledge/Topics/` — created or updated.
+- `Knowledge/Priorities/` — **updated only**, never
   auto-created.
 - `~/.cache/fit/outpost/state/graph_processed` — updated.
 
@@ -47,12 +47,12 @@ same way `extract-entities` processes emails and calendar events.
 - [ ] Both `_memo.md` and `_summary.md` read (when present); transcript
       consulted only for disambiguation.
 - [ ] "Would I prep?" test applied to each person; self excluded.
-- [ ] Interview sessions wrote to `knowledge/Candidates/`, not
-      `knowledge/People/`.
+- [ ] Interview sessions wrote to `Knowledge/Candidates/`, not
+      `Knowledge/People/`.
 - [ ] All links use absolute paths `[[Folder/Name]]`.
 - [ ] Activity entries describe relationship, not communication method.
-- [ ] No new `Goals/` or `Priorities/` auto-created (user-set only); any
-      referenced goal had its progress updated.
+- [ ] No new `Priorities/` auto-created (user-set only); any
+      referenced priority had its progress updated.
 - [ ] `graph_processed` updated for every processed file (memo + summary).
 
 </do_confirm_checklist>
@@ -83,9 +83,9 @@ metadata fallback).
 ### 1. Build the knowledge index
 
 ```bash
-ls knowledge/People/ knowledge/Organizations/ knowledge/Projects/ \
-   knowledge/Topics/ knowledge/Goals/ knowledge/Priorities/ \
-   knowledge/Conditions/ 2>/dev/null
+ls Knowledge/People/ Knowledge/Organizations/ Knowledge/Projects/ \
+   Knowledge/Topics/ Knowledge/Priorities/ \
+   Knowledge/Conditions/ 2>/dev/null
 ```
 
 Read each note's header to build a mental index of known entities (same approach
@@ -104,7 +104,7 @@ Anarlog sessions are **meetings** and follow the meeting rules from
 `extract-entities`:
 
 - **Can create** People, Organization, Project, and Topic notes.
-- **Can update** existing notes — including Goals and Priorities, which are
+- **Can update** existing notes — including Priorities, which are
   user-set and never auto-created.
 - **Can detect** state changes.
 
@@ -123,7 +123,7 @@ interview-note rules, and linking rules — live in
 For **new** entities, use the templates in
 `.claude/skills/extract-entities/references/TEMPLATES.md`. For interview
 sessions, use the candidate brief template from `req-track` (under
-`knowledge/Candidates/`).
+`Knowledge/Candidates/`).
 
 For **existing** entities, apply targeted edits — never rewrite the file:
 
@@ -133,8 +133,7 @@ For **existing** entities, apply targeted edits — never rewrite the file:
 - Update open items (mark completed, add new).
 - Apply state changes.
 
-Verify bidirectional links per `extract-entities` Step 10 (Goal ↔ Project, Goal
-↔ Priority, Project ↔ Priority).
+Verify bidirectional links per `extract-entities` Step 10 (Project ↔ Priority).
 
 ### 6. Update graph state
 

package/templates/.claude/skills/anarlog-process/references/extraction.md

@@ -39,8 +39,8 @@ Never create or update a note for the user — match against name, email, or
 ## Interview sessions (special case)
 
 If the title or memo indicates "interview with {Name}", the interviewee is a
-**candidate** — create or update their note in `knowledge/Candidates/` (using
-the candidate brief template from `req-track`), **not** in `knowledge/People/`.
+**candidate** — create or update their note in `Knowledge/Candidates/` (using
+the candidate brief template from `req-track`), **not** in `Knowledge/People/`.
 
 ## Content signals
 
@@ -77,8 +77,8 @@ strengths and concerns, any interview scoring or decisions.
 ## Linking rules
 
 Use absolute paths everywhere: `[[People/Name]]`, `[[Organizations/Name]]`,
-`[[Projects/Name]]`, `[[Goals/Goal Name]]`, `[[Priorities/Priority Name]]`.
+`[[Projects/Name]]`, `[[Priorities/Priority Name]]`.
 
-When meeting content references an existing Goal or Priority, follow the linking
+When meeting content references an existing Priority, follow the linking
 rules in `extract-entities` Step 7c — update progress and add backlinks, but
-**never** auto-create Goal or Priority notes.
+**never** auto-create Priority notes.

package/templates/.claude/skills/candidate-report/SKILL.md

@@ -25,11 +25,11 @@ before deciding whether to invest interview time.
 - `@forwardimpact/pathway` CLI installed (`bunx fit-pathway --help`).
 - Playwright for PDF output
   (`bun install playwright && bunx playwright install chromium`).
-- Candidate has a `brief.md` in `knowledge/Candidates/{Name}/`.
+- Candidate has a `brief.md` in `Knowledge/Candidates/{Name}/`.
 
 ## Inputs
 
-- **Candidate name** — locates `knowledge/Candidates/{Name}/brief.md`.
+- **Candidate name** — locates `Knowledge/Candidates/{Name}/brief.md`.
 - **Target role** — discipline, level, track (e.g.
   `software_engineering J070 forward_deployed`). If not given, infer from the
   candidate's `Req` field → Role file. Ask the user if it can't be inferred.
@@ -38,7 +38,7 @@ before deciding whether to invest interview time.
 
 ## Outputs
 
-- `drafts/{Recipient}-{CandidateSurname}-Report.html` — the A4 one-pager.
+- `Drafts/{Recipient}-{CandidateSurname}-Report.html` — the A4 one-pager.
 - Optional PDF via `scripts/render-pdf.mjs`.
 
 <do_confirm_checklist goal="Verify the report before delivering it">
@@ -62,16 +62,16 @@ before deciding whether to invest interview time.
 Read whatever exists for the candidate:
 
 ```
-knowledge/Candidates/{Name}/brief.md        # required
-knowledge/Candidates/{Name}/screening.md    # if produced by req-screen
-knowledge/Candidates/{Name}/interview-*.md  # if produced by req-assess
-knowledge/Candidates/{Name}/CV.pdf|CV.md    # raw CV if needed
+Knowledge/Candidates/{Name}/brief.md        # required
+Knowledge/Candidates/{Name}/screening.md    # if produced by req-screen
+Knowledge/Candidates/{Name}/interview-*.md  # if produced by req-assess
+Knowledge/Candidates/{Name}/CV.pdf|CV.md    # raw CV if needed
 ```
 
 If `screening.md` exists, treat its skill and behaviour ratings as the primary
 source — they're already standard-calibrated. Otherwise map manually in Step 3.
 
-Search the graph for surrounding context: `rg "{Candidate Name}" knowledge/`.
+Search the graph for surrounding context: `rg "{Candidate Name}" Knowledge/`.
 
 ### 2. Load the standard benchmark
 
@@ -119,7 +119,7 @@ preview overflows, cut content.
 Save the completed HTML to:
 
 ```
-drafts/{Recipient}-{CandidateSurname}-Report.html
+Drafts/{Recipient}-{CandidateSurname}-Report.html
 ```
 
 `{Recipient}` is the first name of the person the report is for.

package/templates/.claude/skills/deck-create/SKILL.md

@@ -22,7 +22,7 @@ Run when the user asks to create a presentation, slide deck, or pitch deck.
 ## Inputs
 
 - User's description of the presentation
-- `knowledge/` — optional context about company, product, team, projects
+- `Knowledge/` — optional context about company, product, team, projects
 
 ## Outputs
 
@@ -32,7 +32,7 @@ Run when the user asks to create a presentation, slide deck, or pitch deck.
 
 ## Workflow
 
-1.  Check `knowledge/` for relevant context about the company, product, team,
+1.  Check `Knowledge/` for relevant context about the company, product, team,
     etc.
 2.  Ensure Playwright is installed:
     `bun install playwright && bunx playwright install chromium`

package/templates/.claude/skills/deck-summarize/SKILL.md

@@ -30,7 +30,7 @@ from a slide deck; or understand what a project deck is actually asking for.
 ## Outputs
 
 - One markdown file per deck (or one combined file for related decks) written to
-  `knowledge/Projects/{Project Name} - Engineering Brief.md`.
+  `Knowledge/Projects/{Project Name} - Engineering Brief.md`.
 
 <do_confirm_checklist goal="Verify the brief is engineer-actionable before
 delivering">
@@ -125,7 +125,7 @@ mismatches.
 
 Use the structure in
 [references/brief-template.md](references/brief-template.md). Save to
-`knowledge/Projects/{Project Name} - Engineering Brief.md`. For multiple related
+`Knowledge/Projects/{Project Name} - Engineering Brief.md`. For multiple related
 decks, write one combined brief with shared dependencies.
 
 ### 9. Save and report