santifer · gauravlochab · May 17, 2026 · May 17, 2026 · May 17, 2026 · May 17, 2026
diff --git a/.claude/skills/career-ops/SKILL.md b/.claude/skills/career-ops/SKILL.md
diff --git a/.claude/skills/career-ops/SKILL.md b/.claude/skills/career-ops/SKILL.md
@@ -0,0 +1 @@
+../../../.agents/skills/career-ops/SKILL.md
diff --git a/.github/FUNDING.yml b/.github/FUNDING.yml
@@ -0,0 +1 @@
+github: santifer
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -14,6 +14,6 @@ jobs:
           node-version: '20'
       - uses: actions/setup-go@v6
         with:
-          go-version: '1.22'
+          go-version: '1.26'
       - run: npm install
       - run: node test-all.mjs --quick
diff --git a/AGENTS.md b/AGENTS.md
diff --git a/CLAUDE.md b/CLAUDE.md
diff --git a/DATA_CONTRACT.md b/DATA_CONTRACT.md
@@ -18,7 +18,7 @@ These files contain your personal data, customizations, and work product. Update
 | `data/pipeline.md` | Your URL inbox |
 | `data/scan-history.tsv` | Your scan history |
 | `data/follow-ups.md` | Your follow-up history |
-| `writing-samples/*` | Your personal writing samples for style calibration |
+| `writing-samples/*` | Your personal writing samples for style calibration (except `writing-samples/README.md`, which is system-owned documentation delivered by updates) |
 | `reports/*` | Your evaluation reports |
 | `output/*` | Your generated PDFs |
 | `jds/*` | Your saved job descriptions |
@@ -62,6 +62,7 @@ These files contain system logic, scripts, templates, and instructions that impr
 | `docs/*` | Documentation |
 | `VERSION` | Current version number |
 | `DATA_CONTRACT.md` | This file |
+| `writing-samples/README.md` | System-owned onboarding documentation for the writing-samples directory |
 
 ## The Rule
 

diff --git a/GEMINI.md b/GEMINI.md
@@ -1,118 +1,2 @@
-# Career-Ops — AI Job Search Pipeline (Gemini CLI)
-
-> This file is auto-loaded by the Gemini CLI as persistent context.
-> It is the Gemini equivalent of CLAUDE.md.
-> All slash commands are defined in `.gemini/commands/`.
-
-## What is career-ops
-
-AI-powered job search automation: pipeline tracking, offer evaluation, CV generation, portal scanning, batch processing. Originally built on Claude Code, now fully supported on Gemini CLI and OpenCode.
-
-## Data Contract (CRITICAL)
-
-**User Layer (NEVER auto-updated — your personalizations live here):**
-- `cv.md`, `config/profile.yml`, `modes/_profile.md`, `article-digest.md`, `portals.yml`
-- `data/*`, `reports/*`, `output/*`, `interview-prep/*`
-
-**System Layer (auto-updatable — do NOT put user data here):**
-- `modes/_shared.md`, `modes/oferta.md`, all other modes
-- `GEMINI.md`, `CLAUDE.md`, `*.mjs` scripts, `templates/*`, `batch/*`
-
-**THE RULE:** When the user asks to customize anything (archetypes, narrative, negotiation scripts, proof points, location policy, comp targets), ALWAYS write to `modes/_profile.md` or `config/profile.yml`. NEVER edit `modes/_shared.md` for user-specific content.
-
-## Update Check
-
-On the first message of each session, run the update checker silently:
-
-```bash
-node update-system.mjs check
-```
-
-Parse the JSON output:
-- `{"status": "update-available", ...}` → tell the user an update is available and ask if they want to apply it (`node update-system.mjs apply`)
-- `{"status": "up-to-date"}` → say nothing
-- `{"status": "dismissed"}` or `{"status": "offline"}` → say nothing
-
-## Gemini CLI Commands
-
-When using [Gemini CLI](https://github.com/google-gemini/gemini-cli), the following slash commands are available (defined in `.gemini/commands/`):
-
-| Command | Claude Code Equivalent | Description |
-|---------|------------------------|-------------|
-| `/career-ops` | `/career-ops` | Show menu or evaluate JD |
-| `/career-ops-pipeline` | `/career-ops pipeline` | Process pending URLs from inbox |
-| `/career-ops-evaluate` | `/career-ops oferta` | Evaluate job offer (A-G scoring) |
-| `/career-ops-compare` | `/career-ops ofertas` | Compare and rank multiple offers |
-| `/career-ops-contact` | `/career-ops contacto` | LinkedIn outreach |
-| `/career-ops-deep` | `/career-ops deep` | Deep company research |
-| `/career-ops-pdf` | `/career-ops pdf` | Generate ATS-optimized CV |
-| `/career-ops-training` | `/career-ops training` | Evaluate course/cert |
-| `/career-ops-project` | `/career-ops project` | Evaluate portfolio project |
-| `/career-ops-tracker` | `/career-ops tracker` | Application status overview |
-| `/career-ops-apply` | `/career-ops apply` | Live application assistant |
-| `/career-ops-scan` | `/career-ops scan` | Scan portals for new offers |
-| `/career-ops-batch` | `/career-ops batch` | Batch processing |
-| `/career-ops-patterns` | `/career-ops patterns` | Analyze rejection patterns |
-| `/career-ops-followup` | `/career-ops followup` | Follow-up cadence tracker |
-
-**All commands share the same evaluation logic** in `modes/*.md`. The `modes/` files are shared between Claude Code, OpenCode, and Gemini CLI.
-
-## First Run — Onboarding
-
-**Before doing anything else, check if the system is set up.** Run silently every session:
-
-1. Does `cv.md` exist?
-2. Does `config/profile.yml` exist (not just profile.example.yml)?
-3. Does `modes/_profile.md` exist (not just _profile.template.md)?
-4. Does `portals.yml` exist (not just templates/portals.example.yml)?
-
-If `modes/_profile.md` is missing, copy from `modes/_profile.template.md` silently.
-
-**If ANY of these is missing, enter onboarding mode.** Guide the user step by step — ask for their CV, fill the profile, set up the tracker. See `CLAUDE.md` for the full onboarding script (identical logic applies here).
-
-## Skill Modes
-
-| If the user... | Mode to load |
-|----------------|-------------|
-| Pastes JD or URL | auto-pipeline → read `modes/_shared.md` + `modes/auto-pipeline.md` |
-| Asks to evaluate offer | read `modes/_shared.md` + `modes/oferta.md` |
-| Asks to compare offers | read `modes/_shared.md` + `modes/ofertas.md` |
-| Wants LinkedIn outreach | read `modes/_shared.md` + `modes/contacto.md` |
-| Asks for company research | read `modes/deep.md` |
-| Preps for interview | read `modes/interview-prep.md` |
-| Wants to generate CV/PDF | read `modes/_shared.md` + `modes/pdf.md` |
-| Evaluates a course/cert | read `modes/training.md` |
-| Evaluates portfolio project | read `modes/project.md` |
-| Asks about application status | read `modes/tracker.md` |
-| Fills out application form | read `modes/_shared.md` + `modes/apply.md` |
-| Searches for new offers | read `modes/_shared.md` + `modes/scan.md` |
-| Processes pending URLs | read `modes/_shared.md` + `modes/pipeline.md` |
-| Batch processes offers | read `modes/_shared.md` + `modes/batch.md` |
-| Asks about rejection patterns | read `modes/patterns.md` |
-| Asks about follow-ups | read `modes/followup.md` |
-
-## Main Files
-
-| File | Function |
-|------|----------|
-| `data/applications.md` | Application tracker |
-| `data/pipeline.md` | Inbox of pending URLs |
-| `portals.yml` | Query and company config |
-| `templates/cv-template.html` | HTML template for CVs |
-| `generate-pdf.mjs` | Playwright: HTML to PDF |
-| `article-digest.md` | Proof points from portfolio (optional) |
-| `interview-prep/story-bank.md` | Accumulated STAR+R stories |
-| `gemini-eval.mjs` | Standalone Gemini API evaluator (no CLI required) |
-
-## Ethical Use — CRITICAL
-
-- **NEVER submit an application without the user reviewing it first.** Fill forms, draft answers, generate PDFs — but always STOP before clicking Submit. The user makes the final call.
-- **Strongly discourage low-fit applications.** If a score is below 4.0/5, explicitly recommend against applying.
-- **Quality over speed.** A well-targeted application to 5 companies beats a generic blast to 50.
-
-## Pipeline Integrity
-
-1. **NEVER edit applications.md to ADD new entries** — Write TSV in `batch/tracker-additions/` and `node merge-tracker.mjs` handles the merge.
-2. Run `node verify-pipeline.mjs` to check health.
-3. All reports MUST include `**URL:**` and `**Legitimacy:**` in the header.
-4. All statuses MUST be canonical (see `templates/states.yml`).
+@./AGENTS.md
+<!-- Add anything Gemini specific that other agents don't need -->
-@./AGENTS.md
-<!-- Add anything Gemini specific that other agents don't need -->
+# Gemini
+
+@./AGENTS.md
+<!-- Add anything Gemini specific that other agents don't need -->
-@./AGENTS.md
-<!-- Add anything Gemini specific that other agents don't need -->
+# Gemini
+
+@./AGENTS.md
+<!-- Add anything Gemini specific that other agents don't need -->
diff --git a/README.md b/README.md
@@ -157,7 +157,7 @@ node gemini-eval.mjs --file ./jds/my-job.txt
 npm run gemini:eval -- "JD text here"
 ```
 
-> **Free tier:** Both options work without billing. Native CLI uses Google OAuth; the API script uses `gemini-2.0-flash` (15 RPM, 1M tokens/day free).
+> **Free tier:** Both options work without billing. Native CLI uses Google OAuth; the API script uses `gemini-2.5-flash` (15 RPM, 1M tokens/day free).
 
 ## Usage
 
@@ -233,7 +233,8 @@ Features: 6 filter tabs, 4 sort modes, grouped/flat view, lazy-loaded previews,
 
 ```
 career-ops/
-├── CLAUDE.md                    # Agent instructions
+├── AGENTS.md                    # Canonical agent instructions (all CLIs)
+├── CLAUDE.md                    # Claude Code wrapper (imports AGENTS.md)
 ├── cv.md                        # Your CV (create this)
 ├── article-digest.md            # Your proof points (optional)
 ├── config/

diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-1.6.0
+1.8.0
diff --git a/batch/batch-prompt.md b/batch/batch-prompt.md
@@ -15,6 +15,8 @@ Eres un worker de evaluación de ofertas de empleo for the candidate (read name
 | Archivo | Ruta absoluta | Cuándo |
 |---------|---------------|--------|
 | cv.md | `cv.md (project root)` | SIEMPRE |
+| _profile.md | `modes/_profile.md (if exists)` | SIEMPRE (user customizations: archetypes, role_shape, location policy, comp targets) |
+| profile.yml | `config/profile.yml (if exists)` | SIEMPRE (candidate identity, comp range, role_shape rules) |
 | llms.txt | `llms.txt (if exists)` | SIEMPRE |
 | article-digest.md | `article-digest.md (project root)` | SIEMPRE (proof points) |
 | i18n.ts | `i18n.ts (if exists, optional)` | Solo entrevistas/deep |
@@ -24,6 +26,20 @@ Eres un worker de evaluación de ofertas de empleo for the candidate (read name
 **REGLA: NUNCA escribir en cv.md ni i18n.ts.** Son read-only.
 **REGLA: NUNCA hardcodear métricas.** Leerlas de cv.md + article-digest.md en el momento.
 **REGLA: Para métricas de artículos, article-digest.md prevalece sobre cv.md.** cv.md puede tener números más antiguos — es normal.
+**REGLA: Antes de evaluar, cargar `modes/_profile.md` y `config/profile.yml` si existen.** Contienen las preferencias del candidato Y reglas concretas de scoring que **sobrescriben** los defaults del sistema.
+
+Tipos de patrones que estos archivos pueden incluir:
+- **Caps de bloque** — ej: "cap Block A at 3.0/5 if title contains 'Lead'/'Head'/'Principal'"
+- **Overrides de recomendación** — ej: "force SKIP if comp ceiling below $120K" o "force SKIP if role_shape signals broad ownership"
+- **Scoring por dimensión** — ej: "Remote: full credit on remote-first; score 2.0 on full on-site outside [region]"
+- **Framing adaptativo por archetype** — mappings entre arquetipos detectados y proof points a priorizar
+
+Aplicación durante la evaluación A-G:
+- **Bloque A:** aplicar caps de role-shape ANTES de calcular el score del bloque
+- **Bloques B-D:** aplicar adaptive framing por archetype y reglas de dimension scoring (location, comp, etc.)
+- **Bloque F:** aplicar recommendation overrides (SKIP forzado, etc.) — `_profile.md` puede convertir un score técnicamente alto en un SKIP por shape o por comp
+
+**En conflicto, las reglas de `_profile.md` ganan sobre los defaults de `_shared.md`.** Esto es intencional: `_profile.md` es la capa de personalización del usuario.
 
 ---
 

diff --git a/batch/batch-runner.sh b/batch/batch-runner.sh
@@ -4,6 +4,11 @@ set -euo pipefail
 # career-ops batch runner — standalone orchestrator for claude -p workers
 # Reads batch-input.tsv, delegates each offer to a claude -p worker,
 # tracks state in batch-state.tsv for resumability.
+#
+# NOTE: This script is Claude Code-specific. It uses claude -p with
+# --dangerously-skip-permissions and --append-system-prompt-file flags
+# that are not available in other CLIs. Multi-CLI support is out of scope
+# for now — contributions welcome.
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 PROJECT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
@@ -28,6 +33,7 @@ RETRY_FAILED=false
 START_FROM=0
 MAX_RETRIES=2
 MIN_SCORE=0
+MODEL=""  # empty = let claude -p use the Claude Max default
 
 usage() {
   cat <<'USAGE'
@@ -43,6 +49,9 @@ Options:
   --start-from N       Start from offer ID N (skip earlier IDs)
   --max-retries N      Max retry attempts per offer (default: 2)
   --min-score N        Skip PDF/tracker for offers scoring below N (default: 0 = off)
+  --model NAME         Claude model passed to `claude -p --model` (default:
+                       unset = Claude Max default). Use a cheaper model for
+                       large batches, e.g. `--model claude-sonnet-4-6`.
   -h, --help           Show this help
 
 Files:
@@ -76,6 +85,7 @@ while [[ $# -gt 0 ]]; do
     --start-from) START_FROM="$2"; shift 2 ;;
     --max-retries) MAX_RETRIES="$2"; shift 2 ;;
     --min-score) MIN_SCORE="$2"; shift 2 ;;
+    --model) MODEL="$2"; shift 2 ;;
     -h|--help) usage; exit 0 ;;
     *) echo "Unknown option: $1"; usage; exit 1 ;;
   esac
@@ -350,13 +360,17 @@ process_offer() {
     -e "s|{{ID}}|${esc_id}|g" \
     "$PROMPT_FILE" > "$resolved_prompt"
 
-  # Launch claude -p worker (uses default model from Claude Max subscription)
+  # Launch claude -p worker.
+  # Model defaults to the Claude Max subscription default unless --model was
+  # passed. Building the command in an array keeps quoting safe regardless.
+  local -a claude_args=(-p --dangerously-skip-permissions)
+  if [[ -n "$MODEL" ]]; then
+    claude_args+=(--model "$MODEL")
+  fi
+  claude_args+=(--append-system-prompt-file "$resolved_prompt" "$prompt")
+
   local exit_code=0
-  claude -p \
-    --dangerously-skip-permissions \
-    --append-system-prompt-file "$resolved_prompt" \
-    "$prompt" \
-    > "$log_file" 2>&1 || exit_code=$?
+  claude "${claude_args[@]}" > "$log_file" 2>&1 || exit_code=$?
 
   # Cleanup resolved prompt
   rm -f "$resolved_prompt"

diff --git a/dashboard/go.mod b/dashboard/go.mod
@@ -5,13 +5,13 @@ go 1.24.2
 require (
 	github.com/charmbracelet/bubbletea v1.3.10
 	github.com/charmbracelet/lipgloss v1.1.0
+	github.com/charmbracelet/x/ansi v0.11.5
 	github.com/muesli/termenv v0.16.0
 )
 
 require (
 	github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
 	github.com/charmbracelet/colorprofile v0.4.1 // indirect
-	github.com/charmbracelet/x/ansi v0.11.5 // indirect
 	github.com/charmbracelet/x/cellbuf v0.0.15 // indirect
 	github.com/charmbracelet/x/term v0.2.2 // indirect
 	github.com/clipperhouse/displaywidth v0.9.0 // indirect