@forwardimpact/outpost 3.12.0 → 3.13.0

package/templates/.claude/skills/req-forget/SKILL.md

@@ -4,17 +4,21 @@ description: >
   Process GDPR Article 17 data erasure requests. Finds and removes all personal
   data related to a named individual from the knowledge base, cached data, and
   agent state files. Use when the user receives a right-to-be-forgotten
-  request, asks to delete all data about a person, or needs to comply with a
+  request, asks to delete all data about a person, or must comply with a
   data erasure obligation.
 compatibility: Requires macOS filesystem access
 ---
 
 # Right to Be Forgotten
 
-Process data erasure requests under GDPR Article 17. Given a person's name,
-systematically find and remove all personal data from the knowledge base, cached
-synced data, and agent state files. Produces an **erasure report** documenting
-what was found, deleted, and redacted — the compliance audit trail.
+Write tier: `2-Confidential` (erasure record; sweep every tier present)
+Frontmatter: erasure
+
+Process data erasure requests under GDPR Article 17. Work from the person's
+name and every recorded alias. Sweep every tier present, the owner's personal
+surfaces (`0-Draft/`, `Briefings/`), the cached synced data, and the agent
+state files. Produces an **erasure report** that records what you found,
+deleted, and redacted. The report is the compliance audit trail.
 
 ## Trigger
 
@@ -37,22 +41,24 @@ what was found, deleted, and redacted — the compliance audit trail.
 
 ## Outputs
 
-- `Knowledge/Erasure/{Name}--{YYYY-MM-DD}.md` — erasure report.
-- Deleted files and redacted references across the knowledge base.
+- `2-Confidential/Erasure/{Name}--{YYYY-MM-DD}.md` — erasure report.
+- Deleted files and redacted references across every tier.
 
 <do_confirm_checklist goal="Verify erasure is complete and the audit trail is
 sound">
 
-- [ ] User confirmed intent before any deletion.
-- [ ] All discovery recipes ran; inventory covers knowledge, cache, state,
-      drafts.
-- [ ] All dedicated files and directories deleted.
-- [ ] All mentions and backlinks redacted from other notes.
-- [ ] Cached email threads, attachments, and calendar entries handled.
-- [ ] Agent state and `graph_processed` cleaned.
-- [ ] Erasure report saved; contains **no** personal data beyond the name and
-      actions taken.
-- [ ] Final `rg` search shows only the erasure report as a match.
+- [ ] Get the user's confirmation before any deletion.
+- [ ] Run every discovery recipe for the name and each alias. Cover every tier
+      present, `Briefings/`, cache, and state in the inventory.
+- [ ] Delete all dedicated files and directories.
+- [ ] Redact all mentions and backlinks from other notes.
+- [ ] Handle cached email threads, attachments, and calendar entries.
+- [ ] Clean the agent state and `graph_processed`.
+- [ ] Save the erasure report. Keep **no** personal data in it beyond the name
+      and the actions taken.
+- [ ] Run a final `rg` search. Confirm the erasure report is the only match.
+- [ ] Run `npx fit-outpost validate` on the KB root. Fix the dangles the
+      removal created.
 
 </do_confirm_checklist>
 
@@ -66,18 +72,21 @@ State to the user:
 >
 > This will permanently delete all personal data related to {Name} from:
 >
-> - Knowledge base notes (People, Candidates, Organizations mentions)
+> - Notes in every tier (People, Candidates, Organizations mentions)
+> - Personal surfaces (`0-Draft/`, `Briefings/`)
 > - Cached email threads and attachments
 > - Agent state and triage files
 >
-> This action cannot be undone. Proceed?
+> You cannot undo this action. Proceed?
 
-**Wait for explicit confirmation before continuing.**
+**Wait for explicit confirmation before you continue.**
 
 ### 1. Discovery
 
-Run every recipe in [references/locations.md](references/locations.md) and
-compile a complete inventory of every file and reference found.
+Read the subject's frontmatter `aliases` first. Run every recipe in
+[references/locations.md](references/locations.md) for the name, each alias,
+and each email. Compile a complete inventory of every file and reference
+found.
 
 ### 2. Classify
 
@@ -89,20 +98,21 @@ where redaction is the action.
 
 Process most-specific to most-general.
 
-**3a. Dedicated files and directories:**
+**3a. Dedicated files and directories (repeat per tier present):**
 
 ```bash
-rm -rf "Knowledge/Candidates/{Name}/"
-rm -f "Knowledge/People/{Name}.md"
+rm -rf "2-Confidential/Candidates/{Name}/"
+rm -f "2-Confidential/People/{Name}.md"   # overlay note
+rm -f "3-Team/People/{Name}.md"
 find ~/.cache/fit/outpost/apple_mail/attachments/ -iname "*{Name}*" -delete
 ```
 
-**3b. Redact mentions in other notes:** read each file, remove the specific
+**3b. Redact mentions in other notes:** Read each file. Remove the specific
 lines/bullets/sections per the rules in
-[references/classify.md](references/classify.md#redaction-rules), remove broken
-`[[backlinks]]` to deleted notes, write the file back.
+[references/classify.md](references/classify.md#redaction-rules). Remove broken
+`[[backlinks]]` to deleted notes. Write the file back.
 
-**3c. Email threads:** delete sole-subject threads; redact paragraphs only in
+**3c. Email threads:** Delete sole-subject threads. Redact paragraphs only in
 multi-person threads.
 
 **3d. Agent state files:**
@@ -126,29 +136,38 @@ rg -v "{deleted_path}" ~/.cache/fit/outpost/state/graph_processed \
 
 ### 4. Write the erasure report
 
-Save to `Knowledge/Erasure/{Name}--{YYYY-MM-DD}.md` using the template in
-[references/report-template.md](references/report-template.md). Record **only**
-what was deleted — never CV content, skills, or assessments.
+Use the template in
+[references/report-template.md](references/report-template.md). Save to
+`2-Confidential/Erasure/{Name}--{YYYY-MM-DD}.md`. Record **only** what you
+deleted. Never record CV content, skills, or assessments.
 
 ### 5. Verify
 
+Run from the KB root so the search covers every tier and personal surface:
+
 ```bash
-rg "{Name}" Knowledge/ ~/.cache/fit/outpost/ Drafts/
+rg "{Name}" . ~/.cache/fit/outpost/
 ```
 
 The only match should be the erasure report. If other matches remain, process
-them and update the report.
+them and update the report. Repeat for each alias and email. Then validate the
+graph. The removal creates dangling links. Fix what the validator reports:
+
+```bash
+npx fit-outpost validate {kb-root}
+```
 
 ## Scope variants
 
 **`recruitment-only`** limits erasure to:
 
-- `Knowledge/Candidates/{Name}/`
-- `Knowledge/Candidates/Insights.md` mentions
+- `2-Confidential/Candidates/{Name}/`
+- `2-Confidential/Candidates/Insights.md` mentions
 - Recruitment threads (known agency domains)
 - `recruiter_triage.md`
 
-Leaves `Knowledge/People/{Name}.md` and the wider graph intact — the person may
-be a colleague or non-recruitment contact.
+It leaves `3-Team/People/{Name}.md` and the wider graph intact. The person
+may be a colleague or a non-recruitment contact.
 
-**`all`** (default): full erasure across knowledge base, cache, and state.
+**`all`** (default): full erasure across every tier, personal surfaces, cache,
+and state.

package/templates/.claude/skills/req-forget/references/classify.md

@@ -3,21 +3,23 @@
 Reference for `req-forget` Step 2. For every match in the inventory, pick the
 action below.
 
-| Reference Type                     | Action                                      | Example                                         |
-| ---------------------------------- | ------------------------------------------- | ----------------------------------------------- |
-| **Dedicated note** (sole subject)  | Delete entire file                          | `Knowledge/People/{Name}.md`                    |
-| **Dedicated directory**            | Delete entire directory                     | `Knowledge/Candidates/{Name}/`                  |
-| **Mention in another note**        | Redact: remove lines referencing the person | Backlink in `Knowledge/Organizations/Agency.md` |
-| **Email thread** (sole subject)    | Delete file                                 | `~/.cache/fit/outpost/apple_mail/thread.md`     |
-| **Email thread** (multiple people) | Redact: remove paragraphs about the person  | Thread discussing multiple candidates           |
-| **Attachment** (their CV, etc.)    | Delete file                                 | `attachments/{thread}/CV.pdf`                   |
-| **Triage/state file**              | Redact: remove lines mentioning them        | `recruiter_triage.md`                           |
-| **Insights file**                  | Redact: remove bullets mentioning them      | `Knowledge/Candidates/Insights.md`              |
+| Reference Type                     | Action                                         | Example                                              |
+| ---------------------------------- | ---------------------------------------------- | ---------------------------------------------------- |
+| **Dedicated note** (sole subject)  | Delete the file, in every tier it appears      | `3-Team/People/{Name}.md`                            |
+| **Overlay note** (narrower tier)   | Delete the file                                | `2-Confidential/People/{Name}.md`                    |
+| **Dedicated directory**            | Delete the entire directory                    | `2-Confidential/Candidates/{Name}/`                  |
+| **Mention in another note**        | Redact: remove the lines that name the person  | Backlink in `3-Team/Organizations/Agency.md`         |
+| **Personal-surface mention**       | Redact, or delete a sole-subject draft/brief   | `0-Draft/{file}.md`, `Briefings/{date}.md`           |
+| **Email thread** (sole subject)    | Delete the file                                | `~/.cache/fit/outpost/apple_mail/thread.md`          |
+| **Email thread** (multiple people) | Redact: remove the paragraphs about the person | A thread about multiple candidates                   |
+| **Attachment** (their CV, etc.)    | Delete the file                                | `attachments/{thread}/CV.pdf`                        |
+| **Triage/state file**              | Redact: remove the lines that mention them     | `recruiter_triage.md`                                |
+| **Insights file**                  | Redact: remove the bullets that mention them   | `2-Confidential/Candidates/Insights.md`              |
 
 ## Redaction rules
 
 - Remove entire bullet points that mention the person by name.
-- Remove table rows containing the person's name.
-- Remove `## Connected to` entries linking to deleted notes.
+- Remove the table rows that contain the person's name.
+- Remove the `## Connected to` entries that link to deleted notes.
 - If a section becomes empty after redaction, remove its header too.
-- Do **not** remove surrounding context that doesn't identify the person.
+- Do **not** remove nearby context that does not identify the person.

package/templates/.claude/skills/req-forget/references/locations.md

@@ -1,26 +1,35 @@
 # Discovery Search Recipes
 
-Reference for `req-forget` Step 1. Run every recipe; record every match into the
-inventory.
+Reference for `req-forget` Step 1. Run every recipe from the KB root. Repeat
+each recipe for every recorded alias and email. Record every match into the
+inventory. The tier glob `[0-9]-*/` covers every tier present.
 
-## Knowledge base — direct notes
+## Direct notes, per tier
 
 ```bash
-ls -d "Knowledge/Candidates/{Name}/" 2>/dev/null
-ls "Knowledge/People/{Name}.md" 2>/dev/null
+ls -d "2-Confidential/Candidates/{Name}/" 2>/dev/null
+ls "2-Confidential/Prospects/{Name}.md" 2>/dev/null
+ls "2-Confidential/People/{Name}.md" 2>/dev/null   # overlay note
+ls "3-Team/People/{Name}.md" 2>/dev/null
+
+# Common name variations, in any tier
+ls [0-9]-*/People/"{First} {Last}.md" 2>/dev/null
+ls [0-9]-*/People/"{Last}, {First}.md" 2>/dev/null
+```
+
+## Backlinks and mentions, every tier
 
-# Common name variations
-ls "Knowledge/People/{First} {Last}.md" 2>/dev/null
-ls "Knowledge/People/{Last}, {First}.md" 2>/dev/null
+```bash
+rg -l "{Name}" [0-9]-*/
+rg -l "{First name} {Last name}" [0-9]-*/
+rg -l "\[\[.*{Name}.*\]\]" [0-9]-*/
+rg -l "{email}" [0-9]-*/
 ```
 
-## Knowledge base — backlinks and mentions
+## Personal surfaces
 
 ```bash
-rg -l "{Name}" Knowledge/
-rg -l "{First name} {Last name}" Knowledge/
-rg -l "\[\[.*{Name}.*\]\]" Knowledge/
-rg -l "{email}" Knowledge/
+rg -l "{Name}" 0-Draft/ Briefings/ 2>/dev/null
 ```
 
 ## Cached email threads
@@ -41,19 +50,15 @@ rg -l "{email}" ~/.cache/fit/outpost/apple_calendar/ 2>/dev/null
 ## Agent state files
 
 ```bash
-rg -l "{Name}" ~/.cache/fit/outpost/state/ 2>/dev/null
-```
-
-## Drafts
-
-```bash
-rg -l "{Name}" Drafts/ 2>/dev/null
+rg -l "{Name}" ~/.cache/fit/outpost/ 2>/dev/null
 ```
 
 ## Final verification
 
+Run from the KB root so the search covers every tier and personal surface:
+
 ```bash
-rg "{Name}" Knowledge/ ~/.cache/fit/outpost/ Drafts/
+rg "{Name}" . ~/.cache/fit/outpost/
 ```
 
-Expected: only the erasure report matches.
+Expected: only the erasure report matches. Repeat per alias and email.

package/templates/.claude/skills/req-forget/references/report-template.md

@@ -1,13 +1,19 @@
 # Erasure Report Template
 
 Audit trail for `req-forget` Step 4. Save to
-`Knowledge/Erasure/{Name}--{YYYY-MM-DD}.md`.
+`2-Confidential/Erasure/{Name}--{YYYY-MM-DD}.md`.
 
 **The report itself must not contain personal data** beyond the subject's name
 and the actions taken. Do not copy CV content, skills, or assessments into the
-report — record only what was deleted, not what it contained.
+report. Record only what you deleted. Do not record what it contained.
 
 ````markdown
+---
+type: erasure
+created: {YYYY-MM-DD}
+updated: {YYYY-MM-DD}
+---
+
 # Data Erasure Report — {Full Name}
 
 **Date:** {YYYY-MM-DD HH:MM}
@@ -22,15 +28,17 @@ report — record only what was deleted, not what it contained.
 ## Actions Taken
 
 ### Deleted Files
-- `Knowledge/Candidates/{Name}/brief.md`
-- `Knowledge/Candidates/{Name}/CV.pdf`
-- `Knowledge/Candidates/{Name}/screening.md`
-- `Knowledge/People/{Name}.md`
-- {list all deleted files}
+- `2-Confidential/Candidates/{Name}/brief.md`
+- `2-Confidential/Candidates/{Name}/CV.pdf`
+- `2-Confidential/Candidates/{Name}/screening.md`
+- `2-Confidential/People/{Name}.md` (overlay)
+- `3-Team/People/{Name}.md`
+- {list all deleted files, per tier}
 
 ### Redacted References
-- `Knowledge/Organizations/{Agency}.md` — removed backlink
-- `Knowledge/Candidates/Insights.md` — removed {N} bullet(s)
+- `3-Team/Organizations/{Agency}.md` — removed backlink
+- `2-Confidential/Candidates/Insights.md` — removed {N} bullet(s)
+- `Briefings/{date}.md` — removed {N} line(s)
 - {list all redacted files and what was removed}
 
 ### Cached Data Removed
@@ -49,6 +57,8 @@ The following are outside this tool's reach:
 - **Apple Mail** — original emails remain in the user's mailbox. Search
   Mail.app for "{Name}" and delete threads manually.
 - **Apple Calendar** — events remain in Calendar.app.
+- **Synced tier copies** — teammates who receive a shared tier hold their own
+  copies. Notify them of the deletion.
 - **Recruitment agencies** — notify {Agency} of the deletion and request
   they do the same.
 - **Interview notes** — check physical notebooks and external apps.
@@ -57,11 +67,9 @@ The following are outside this tool's reach:
 ## Verification
 
 ```bash
-rg "{Name}" Knowledge/ ~/.cache/fit/outpost/
-````
-
-Expected: no matches except this erasure report.
-
-```text
-
+rg "{Name}" . ~/.cache/fit/outpost/
+npx fit-outpost validate {kb-root}
 ```
+
+Expected: no matches except this erasure report, and a clean validator run.
+````

package/templates/.claude/skills/req-scan/SKILL.md

@@ -3,26 +3,28 @@ name: req-scan
 description: >
   Scan publicly available sources for candidates who indicate they are open for
   hire. Uses WebFetch to read public APIs (HN Algolia, GitHub, dev.to).
-  Writes prospect notes to Knowledge/Prospects/. Maintains
+  Writes prospect notes to 2-Confidential/Prospects/. Maintains
   cursor/dedup state in ~/.cache/fit/outpost/head-hunter/. Use when the
-  head-hunter agent is woken or when the user asks to scan for open candidates.
+  head-hunter agent wakes or when the user asks to scan for open candidates.
 ---
 
 # Scan Open Candidates
 
+Write tier: `2-Confidential`
+Frontmatter: prospect
+
 Fetch and filter publicly available candidate posts from platforms where people
-**explicitly indicate** they are open for hire. This skill handles fetching,
-filtering, deduplication, benchmarking, prospect-note writing, and memory
-updates.
+**explicitly indicate** they are open for hire. This skill fetches, filters,
+deduplicates, benchmarks, writes prospect notes, and updates memory.
 
 ## Trigger
 
-- The head-hunter agent is woken by the scheduler.
+- The scheduler wakes the head-hunter agent.
 - The user asks to scan for open candidates or prospects.
 
 ## Prerequisites
 
-- `WebFetch` tool available (Claude Code built-in — no curl/wget).
+- `WebFetch` tool available (a Claude Code built-in, no curl/wget).
 - `fit-pathway` CLI available (`bunx fit-pathway`).
 - Memory directory `~/.cache/fit/outpost/head-hunter/`.
 
@@ -34,24 +36,24 @@ updates.
 
 ## Outputs
 
-- `Knowledge/Prospects/{Name}.md`.
+- `2-Confidential/Prospects/{Name}.md`.
 - Updated `cursor.tsv`, `seen.tsv`, `prospects.tsv`, and `log.md`.
 - `~/.cache/fit/outpost/state/head_hunter_triage.md`.
 
 <do_confirm_checklist goal="Verify the wake produced a clean, ethical scan">
 
-- [ ] Selected the least-recently-checked, non-suspended source.
-- [ ] Fetched via `WebFetch` (never curl/wget).
-- [ ] Applied all 5 filters in order; passed candidates have ≥ 2
+- [ ] Select the least-recently-checked source that is not suspended.
+- [ ] Fetch with `WebFetch` (never curl/wget).
+- [ ] Apply all 5 filters in order. Confirm each passed candidate has ≥ 2
       standard-relevant skills.
-- [ ] Deduplicated against `seen.tsv` before processing.
-- [ ] Benchmarked each prospect against a real `bunx fit-pathway job`.
-- [ ] Prospect notes follow the template (no fabricated names).
-- [ ] All state mutations went through `node scripts/state.mjs` — cursor, seen,
-      prospects, failures, log.
-- [ ] Triage report written to the state directory; alternative queries (if any)
-      logged.
-- [ ] Failures recorded; sources with ≥ 3 consecutive failures suspended.
+- [ ] Deduplicate against `seen.tsv` before you process a candidate.
+- [ ] Benchmark each prospect against a real `bunx fit-pathway job`.
+- [ ] Follow the template for every prospect note (no fabricated names).
+- [ ] Route every state mutation through `node scripts/state.mjs`: cursor,
+      seen, prospects, failures, log.
+- [ ] Write the triage report to the state directory. Log any alternative
+      queries.
+- [ ] Record every failure. Suspend a source at ≥ 3 consecutive failures.
 
 </do_confirm_checklist>
 
@@ -75,12 +77,12 @@ follow [references/filters.md](references/filters.md#failure-handling).
 ### 3. Filter
 
 Apply the 5-filter pipeline in
-[references/filters.md](references/filters.md#filter-pipeline) — signal, dedup,
+[references/filters.md](references/filters.md#filter-pipeline): signal, dedup,
 geographic, skill alignment, experience level.
 
 ### 3b. Fallback — zero new prospects
 
-If filtering eliminates every candidate, try up to **3 alternatives** per wake
+If the filters eliminate every candidate, try up to **3 alternatives** per wake
 from [references/fallbacks.md](references/fallbacks.md). Log every alternative
 in `log.md`.
 
@@ -99,17 +101,17 @@ Classify match strength:
 - **moderate** — some overlap, level roughly right, minor gaps.
 - **weak** — few matching signals, significant gaps.
 
-Write notes for **strong** and **moderate** matches only, using the template in
+Write notes for **strong** and **moderate** matches only. Use the template in
 [references/template.md](references/template.md).
 
 ```bash
-mkdir -p "Knowledge/Prospects"
+mkdir -p "2-Confidential/Prospects"
 ```
 
 ### 5. Update state
 
-All state changes go through `node scripts/state.mjs` — full command reference:
-[references/state.md](references/state.md). Each wake:
+All state changes go through `node scripts/state.mjs`. The full command
+reference is [references/state.md](references/state.md). Each wake:
 
 1. Update the cursor (`cursor set`).
 2. Reset failure count on success or increment on failure.

package/templates/.claude/skills/req-scan/references/fallbacks.md

@@ -1,16 +1,16 @@
 # Fallback Strategies
 
 Reference for `req-scan` when a primary source query yields zero new prospects
-after filtering. Try at most **3 alternatives per wake** to stay within rate
-limits.
+after the filters run. Try at most **3 alternatives per wake** to stay within
+rate limits.
 
 ## Strategy 1 — alternative search terms
 
 ### HN
 
 - Check the **previous** month's "Who Wants to Be Hired?" thread.
-- Search for `"Who is hiring"` threads (candidates sometimes post in the wrong
-  thread; comments may link to candidate profiles).
+- Search for `"Who is hiring"` threads. (Candidates sometimes post in the wrong
+  thread. Comments may link to candidate profiles.)
 - Try
   `https://hn.algolia.com/api/v1/search?query=%22freelancer+available%22&tags=comment`.
 
@@ -47,9 +47,9 @@ WebFetch URL: https://dev.to/api/articles?tag=career&per_page=25
 If geography eliminated everyone, re-scan without the location filter. Mark
 unmatched-location prospects as "location unconfirmed" in the prospect note.
 
-If skill alignment filtered everyone out: lower the bar from 2 standard skills
-to 1; consider transferable skills (strong Python ⇒ likely data integration
-capability); accept adjacent indicators ("machine learning" implies data
+If skill alignment filtered everyone out, lower the bar from 2 standard skills
+to 1. Consider transferable skills (strong Python ⇒ likely data integration
+capability). Accept adjacent indicators ("machine learning" implies data
 skills).
 
 ## Strategy 3 — cross-reference
@@ -57,11 +57,11 @@ skills).
 When a source yields very few results, enrich what you do find:
 
 - A GitHub profile that links to a blog/portfolio → WebFetch it for more detail
-  before deciding skill fit.
+  before you decide skill fit.
 - An HN post that mentions a GitHub username → fetch their GitHub profile for
   richer signal.
 
-## Logging alternatives
+## Log the alternatives
 
 Log every alternative in `log.md`:
 

package/templates/.claude/skills/req-scan/references/filters.md

@@ -11,7 +11,7 @@ Apply in order. Stop at the first that excludes the candidate.
 - HN "Who Wants to Be Hired?" → **auto-pass** (thread is opt-in).
 - GitHub → must have `hireable: true` **or** bio contains an open-to-work
   phrase.
-- dev.to → must be tagged `opentowork` or `lookingforwork`.
+- dev.to → the post must carry the tag `opentowork` or `lookingforwork`.
 
 ### 2. Deduplication
 
@@ -31,8 +31,8 @@ Prefer or accept candidates in or open to:
 - **Remote / Anywhere / Global**.
 
 Skip candidates explicitly locked to incompatible regions ("San Francisco only",
-"APAC only"). When location is ambiguous or unstated, include the candidate —
-let the user decide.
+"APAC only"). When location is ambiguous or unstated, include the candidate.
+Let the user decide.
 
 ### 4. Skill alignment
 
@@ -46,8 +46,8 @@ non-traditional path (law, policy, academia → tech), AI/ML tool proficiency
 **Platform:** infrastructure / cloud / DevOps, architecture and system design,
 API design and shared services, performance / scalability / reliability.
 
-**Minimum bar:** at least 2 standard-relevant skills must be identifiable from
-the post. Skip candidates with purely non-technical profiles.
+**Minimum bar:** the post must show at least 2 standard-relevant skills. Skip
+candidates with purely non-technical profiles.
 
 ### 5. Experience level
 
@@ -68,16 +68,16 @@ block page):
 1. Increment the failure count:
    `node scripts/state.mjs failure increment {source}`.
 2. **Do not retry** the same source in this wake cycle.
-3. Suspend after 3 consecutive failures — skip during source selection. Retry
-   suspended sources once every 7 days to detect recovery.
+3. Suspend after 3 consecutive failures. Skip a suspended source during source
+   selection. Retry suspended sources once every 7 days to detect recovery.
 4. Log the failure in `log.md` with HTTP status and error.
 5. Reset on success: `node scripts/state.mjs failure reset {source}`.
 
 ### Common failure patterns
 
-| Symptom                  | Likely cause                                           |
-| ------------------------ | ------------------------------------------------------ |
-| 503 with HTML redirect   | Corporate proxy blocking the domain (won't recover)    |
-| 403 Forbidden            | Auth required or automated requests blocked            |
-| 429 Too Many Requests    | Rate limited — will recover; don't suspend permanently |
-| Empty response / timeout | Transient — likely recovers next wake                  |
+| Symptom                  | Likely cause                                             |
+| ------------------------ | -------------------------------------------------------- |
+| 503 with HTML redirect   | A corporate proxy blocks the domain. It will not recover |
+| 403 Forbidden            | The site needs auth, or it blocks automated requests     |
+| 429 Too Many Requests    | Rate limited. It recovers. Do not suspend permanently    |
+| Empty response / timeout | Transient. It likely recovers next wake                  |

package/templates/.claude/skills/req-scan/references/sources.md

@@ -4,31 +4,31 @@ Reference for `req-scan` Step 2 (fetch & scan). One source per wake cycle.
 
 ## 1. Hacker News "Who Wants to Be Hired?"
 
-Monthly thread, posted on the 1st.
+A monthly thread that appears on the 1st.
 
 ```text
 WebFetch URL: https://hn.algolia.com/api/v1/search?query=%22Who+wants+to+be+hired%22&tags=ask_hn&hitsPerPage=5
 ```
 
-The first hit whose title matches "Who wants to be hired?" with `created_at` in
-the current or previous month is the target thread.
+The target thread is the first hit whose title matches "Who wants to be hired?"
+and whose `created_at` falls in the current or previous month.
 
 ```text
 WebFetch URL: https://hn.algolia.com/api/v1/items/{objectID}
 ```
 
-`children[]` contains top-level comments — each is one candidate. Parse the
-`text` field for:
+`children[]` contains top-level comments. Each comment is one candidate. Parse
+the `text` field for:
 
 - **Location** ("Location: New York", "NYC / Remote").
 - **Remote** ("Remote: Yes", "Open to remote").
 - **Skills** — tech stack, language/standard mentions.
 - **Experience** — years, role titles, past companies.
-- **Contact** — email (often obfuscated: "name [at] domain [dot] com").
+- **Contact** — email, often obfuscated as "name [at] domain [dot] com".
 - **Resume / CV** — links to personal sites, GitHub, LinkedIn.
 
 **Cursor:** thread `objectID` plus the ID of the last processed child comment.
-**Rate:** no strict limit; one fetch per wake cycle.
+**Rate:** no strict limit. One fetch per wake cycle.
 
 ## 2. GitHub Open to Work
 

package/templates/.claude/skills/req-scan/references/state.md

@@ -40,7 +40,7 @@ node scripts/state.mjs failure increment mastodon_hachyderm
 node scripts/state.mjs failure reset github_open_to_work
 ```
 
-## Logging
+## Logs
 
 ```bash
 node scripts/state.mjs log-wake github_open_to_work "Primary query: 'open to work' location:UK — 30 results, 2 new prospects"

package/templates/.claude/skills/req-scan/references/template.md

@@ -1,8 +1,18 @@
 # Prospect Note Template
 
-Reference for `req-scan` Step 4. Save to `Knowledge/Prospects/{Name}.md`.
+Reference for `req-scan` Step 4. Save to `2-Confidential/Prospects/{Name}.md`.
+The note opens with the frontmatter block. Select `status` from the registry
+vocabulary (`registry.yaml`).
 
 ```markdown
+---
+type: prospect
+created: {YYYY-MM-DD}
+updated: {YYYY-MM-DD}
+aliases: [{username or display-name variants, or an empty list}]
+status: {registry status: identified / contacted / responded / converted / closed}
+---
+
 # {Name}
 
 ## Info