@firatcand/roster 0.4.0 → 1.0.0

package/templates/scaffold/gtm/sdr/subagents/enricher.md

@@ -1,49 +0,0 @@
-# Enricher Subagent
-
-## Role
-
-Take an existing prospect list and fill in missing fields needed for personalized outreach. Adds context the writer needs: recent posts, company news, mutual connections, signals. Does not contact, does not score.
-
-## Inputs
-
-- `prospects` (array): list from prospector or external source
-- `required_fields` (array): which fields must be filled — e.g., `[recent_post, company_news, role_tenure]`
-- `enrichment_depth` (string): `light` (search results only) | `deep` (web fetch + multi-source)
-
-## Output
-
-Same prospects array, with new fields added. Mark unfillable fields explicitly:
-
-```yaml
-prospects:
-  - name: "Alice Example"
-    role: "Head of Growth"
-    company: "ExampleCo"
-    enrichment:
-      recent_post:
-        url: "..."
-        snippet: "..."
-        date: "2026-04-22"
-      company_news:
-        - { headline: "...", url: "...", date: "..." }
-      role_tenure_months: 8
-      mutual_signals: []
-    enrichment_status: complete   # complete | partial | failed
-    enrichment_notes: ""
-```
-
-## Tools
-
-- Apollo.io MCP: `apollo_people_match`, `apollo_organizations_enrich`, `apollo_organizations_job_postings`
-- Web search + web_fetch: recent posts, news, signals
-- HeyReach MCP: `get_lead` for LinkedIn URL-based lookup
-
-## Boundaries
-
-- Do NOT score or filter — return everything, even partially enriched.
-- Do NOT make assumptions about missing fields. Mark explicitly.
-- Cap web_fetch at 3 sources per prospect for deep enrichment.
-
-## Quality bar
-
-A prospect with `enrichment_status: complete` must have all required fields. Otherwise `partial` with notes on what's missing.

package/templates/scaffold/gtm/sdr/subagents/prospector.md

@@ -1,44 +0,0 @@
-# Prospector Subagent
-
-## Role
-
-Find prospects matching the orchestrator's criteria. Read-only against external data sources. Returns a scored, deduplicated list. Does not contact, does not enrich beyond search results.
-
-## Inputs
-
-- `criteria` (object): ICP filters from project's `guidelines/icps/*.md` — industry, company stage, role, geography, headcount range, signals
-- `existing_targets` (array, optional): prospects already in the project's CRM — for dedup
-- `cap` (int): max prospects to return
-
-## Output
-
-```yaml
-prospects:
-  - name: "Alice Example"
-    role: "Head of Growth"
-    company: "ExampleCo"
-    company_url: "https://example.com"
-    linkedin_url: "..."
-    email: "alice@example.com"
-    signals: ["raised series-b 2026-03", "hiring founding GTM"]
-    score: 8.5
-    score_reasoning: "Series B fit, role fit, recent funding signal"
-    matched_persona: "founding-team-hiring-manager"
-  - ...
-```
-
-## Tools
-
-- Apollo.io MCP: `apollo_mixed_people_api_search`, `apollo_mixed_companies_search`, `apollo_organizations_job_postings`
-- Web search: signal verification when Apollo lacks it
-
-## Boundaries
-
-- Do NOT enrich beyond what search returns — that's the enricher.
-- Do NOT message prospects or update CRM.
-- Do NOT score below threshold — return all candidates with scores; orchestrator filters.
-- If you can't find at least 50% of requested cap, return what you have and flag in `## Notes`.
-
-## Quality bar
-
-Every prospect must have at minimum: name, role, company, and one verifiable identifier (LinkedIn URL or email or company URL). Drop incomplete records.

package/templates/scaffold/gtm/sdr/subagents/writer.md

@@ -1,51 +0,0 @@
-# Writer Subagent
-
-## Role
-
-Draft a single first-touch outreach message for a single prospect, in the project's voice, using enrichment context. One message per invocation. Does not send, select, or edit other drafts.
-
-## Inputs
-
-- `prospect` (object): single enriched prospect record
-- `voice` (markdown): contents of `projects/<project>/guidelines/voice.md`
-- `do_and_dont` (markdown, optional): contents of `projects/<project>/guidelines/do-and-dont.md`
-- `lessons` (markdown): concatenated relevant project + global lessons
-- `channel` (string): `linkedin` | `email`
-- `goal` (string): what we want the prospect to do (e.g., `book_15min_call`, `reply_with_interest`)
-
-## Output
-
-```yaml
-draft:
-  subject: "..."          # email only; null for linkedin
-  body: "..."
-  cta: "..."
-  word_count: 73
-  reasoning: |
-    Why this opener, why this hook, why this CTA — 3-4 sentences.
-    Reference any specific lesson or signal that influenced the draft.
-  voice_anchors:
-    - "..."
-```
-
-## Tools
-
-None. Pure generation from inputs. No web search, no enrichment, no tool calls.
-
-## Boundaries
-
-- Do NOT invent facts about the prospect. Use only enrichment data provided.
-- Do NOT reference signals you can't verify from inputs.
-- Do NOT exceed channel norms: LinkedIn ≤ 300 chars for first connection note, email ≤ 120 words for cold first-touch unless config overrides.
-- Do NOT use templates. Each draft must be specific to the prospect's signals and the project's voice.
-- If a relevant lesson conflicts with the voice doc, follow the voice doc and flag the conflict in `reasoning`.
-- If do-and-dont rules apply, follow them strictly.
-
-## Quality bar
-
-The draft must:
-1. Reference at least one specific signal from enrichment
-2. Match the voice doc — tone, sentence length, vocabulary, energy
-3. Have a single clear CTA matching `goal`
-4. Pass a "would I send this myself?" check
-5. Violate zero do-and-dont rules

package/templates/scaffold/projects/_demo/CLAUDE.md

@@ -1,35 +0,0 @@
----
-project: _demo
-type: example
-created: 2026-05-03
----
-
-# Acme Corp — Demo Project
-
-This is a sample project demonstrating how `roster` organizes work. Acme Corp is a fictional B2B SaaS company that helps small businesses automate their accounting workflows.
-
-This demo is **safe to delete**. It exists to show the structure of a populated project. Real projects go in `projects/<your-project-name>/`.
-
-## Identity
-
-- Product: Acme Books — accounting automation for SMBs
-- Stage: early-stage SaaS, post-launch
-- Audience: SMB owners and bookkeepers
-- Primary motion: outbound to bookkeeping firms and SMB owners
-
-## Active agent instances
-
-- `gtm/sdr/projects/_demo/` — outbound prospecting and cold outreach
-
-## Files in this project
-
-- `CLAUDE.md` — this file
-- `state.md` — session continuity (auto-updated)
-- `guidelines/` — substrate (voice, ICPs, messaging, brand-book, etc.)
-
-## How to use as a learning example
-
-1. Browse `projects/_demo/guidelines/` to see what filled-in substrate looks like
-2. Browse `gtm/sdr/projects/_demo/config/default.yaml` to see how an agent instance is configured
-3. Try running the agent against this demo: `/sdr run cold-outreach for _demo` (will prompt for filled bindings — feel free to use placeholder values for the test)
-4. Delete this entire `_demo/` directory and its instance(s) when you're ready to start fresh

package/templates/scaffold/projects/_demo/README.md

@@ -1,16 +0,0 @@
-# _demo
-
-Placeholder project for testing roster workflows. Rename or duplicate this directory to
-create a real project — `scripts/new-project.sh <name>` automates that in Phase 2.
-
-## Structure
-
-```
-projects/_demo/
-├── guidelines/           # written by function-level experts (added in Phase 2)
-├── config/default.yaml   # per-project agent config (added in Phase 2)
-└── state.md              # session continuity notes (max 5 lines; updated via /save-state)
-```
-
-In Phase 1 this directory only proves `roster init` writes files to the right place. The
-full project substrate lands when Phase 2 ships `templates/scaffold/` (see ROS-17).

package/templates/scaffold/projects/_demo/config/default.yaml

@@ -1,28 +0,0 @@
----
-project: _demo
-created: 2026-05-03
----
-
-# Project-level config — Acme Corp demo
-#
-# Cross-agent defaults for this project. Agent-scoped config (per-instance
-# tool bindings, channel caps, scoring thresholds) lives at:
-#   <function>/<agent>/projects/<project>/config/default.yaml
-#
-# Keep this file thin. It's read by chief-of-staff for audit reports and
-# by any agent that needs project-wide signals.
-
-# Display name shown in reports and Slack messages.
-display_name: Acme Corp
-
-# Stage: idea | pre-launch | early | growth | mature
-stage: early
-
-# Primary go-to-market motion. Drives default agent suggestions.
-# Options: outbound | inbound | plg | hybrid
-motion: outbound
-
-# Default approval channel for HITL — used when an agent's instance config
-# leaves approval_channel unset.
-# Options: slack | inline | auto
-approval_channel: auto

package/templates/scaffold/projects/_demo/state.md

@@ -1,11 +0,0 @@
----
-last_session: 2026-05-03
-focus: (none — demo project)
----
-
-# Acme Corp — Session State
-
-This file tracks short-term context across Claude Code sessions for this project. Updated via `/save-state` or by the user explicitly. Five lines max.
-
-- Status: demo / illustrative
-- Next task: replace with your real project, or delete `_demo/` entirely

package/templates/scaffold/scripts/archive-project.sh

@@ -1,98 +0,0 @@
-#!/usr/bin/env bash
-# archive-project.sh — moves a project and all its agent instances to _archive/
-# Usage: bash scripts/archive-project.sh <project> [reason]
-
-set -euo pipefail
-
-if [ $# -lt 1 ]; then
-  echo "Usage: $0 <project> [reason]"
-  exit 1
-fi
-
-PROJECT="$1"
-REASON="${2:-}"
-ROOT="$(cd "$(dirname "$0")/.." && pwd)"
-PROJECT_DIR="$ROOT/projects/$PROJECT"
-
-if [ ! -d "$PROJECT_DIR" ]; then
-  echo "ERROR: Project '$PROJECT' not found at $PROJECT_DIR"
-  exit 1
-fi
-
-DATE=$(date +%Y-%m-%d)
-TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
-
-# Find all agent instances for this project
-INSTANCES=()
-while IFS= read -r path; do
-  INSTANCES+=("$path")
-done < <(find "$ROOT" -type d -path "*/projects/$PROJECT" -not -path "*/_template/*" -not -path "*/_archive/*" 2>/dev/null | grep -v "^$ROOT/projects/$PROJECT$" || true)
-
-# Determine archive suffix (handle same-day re-archiving)
-SUFFIX="$DATE"
-COUNTER=2
-while [ -d "$ROOT/_archive/projects/$PROJECT-$SUFFIX" ]; do
-  SUFFIX="$DATE-$COUNTER"
-  COUNTER=$((COUNTER + 1))
-done
-
-echo "Archiving project: $PROJECT (suffix: $SUFFIX)"
-
-# Create archive root
-mkdir -p "$ROOT/_archive/projects"
-
-# Move project root
-mv "$PROJECT_DIR" "$ROOT/_archive/projects/$PROJECT-$SUFFIX"
-echo "  Moved: projects/$PROJECT/  →  _archive/projects/$PROJECT-$SUFFIX/"
-
-# Move each instance
-for inst in "${INSTANCES[@]}"; do
-  REL="${inst#$ROOT/}"
-  PARENT_DIR=$(dirname "$REL")
-  ARCHIVE_PARENT="$ROOT/_archive/$PARENT_DIR"
-  mkdir -p "$ARCHIVE_PARENT"
-  mv "$inst" "$ARCHIVE_PARENT/$PROJECT-$SUFFIX"
-  echo "  Moved: $REL/  →  _archive/$PARENT_DIR/$PROJECT-$SUFFIX/"
-done
-
-# Write ARCHIVED.md
-cat > "$ROOT/_archive/projects/$PROJECT-$SUFFIX/ARCHIVED.md" << EOF
----
-archived_at: $TIMESTAMP
-project: $PROJECT
-archive_suffix: $SUFFIX
-reason: ${REASON:-(not specified)}
----
-
-# Archived: $PROJECT
-
-## Paths archived
-- _archive/projects/$PROJECT-$SUFFIX/  (project root)
-$(for inst in "${INSTANCES[@]}"; do
-  REL="${inst#$ROOT/}"
-  PARENT_DIR=$(dirname "$REL")
-  echo "- _archive/$PARENT_DIR/$PROJECT-$SUFFIX/  (instance)"
-done)
-
-## To restore
-\`\`\`bash
-bash scripts/unarchive-project.sh $PROJECT $SUFFIX
-\`\`\`
-EOF
-
-# Operation log
-LOG_DIR="$ROOT/chief-of-staff/logs/$(date +%Y-%m)"
-mkdir -p "$LOG_DIR"
-LOG_FILE="$LOG_DIR/operations-$(date +%Y-%m-%d).md"
-{
-  echo ""
-  echo "## $TIMESTAMP — archive-project: $PROJECT"
-  echo "Suffix: $SUFFIX"
-  echo "Instances archived: ${#INSTANCES[@]}"
-  [ -n "$REASON" ] && echo "Reason: $REASON"
-} >> "$LOG_FILE"
-
-echo ""
-echo "✓ Archive complete."
-echo "  ARCHIVED.md: $ROOT/_archive/projects/$PROJECT-$SUFFIX/ARCHIVED.md"
-echo "  Operation log: $LOG_FILE"