CONTEXT JAMMING

Field notes from inside the context window.

AGENTIC JOB SEEKER

Job Application
Batch Maker

Turn 15 job targets into a complete application pack — résumé PDFs, cover letters, and a live pipeline dashboard — in one Claude Code run.

Application Cockpit

Live pipeline funnel (Not Applied → Applied → Follow Up → Interview → Offer → Rejected). Per-row status, date-applied, and notes that save in your browser. Search + filter by archetype, fit score, and work mode. Sortable columns. Works offline. CSV/JSON export + restore.

4–7 Archetypes, Not 15 PDFs

The skill builds archetype résumé bases, documents every reuse decision, and spends customization where it counts: cover letters and high-value roles. Every reuse decision is recorded and shown in the dashboard.

No Fabricated Credentials

The skill never invents degrees, titles, or engineering depth. For stretch roles it repositions honestly rather than inflating. Every apply link is verified in-session; unverifiable links are marked clearly.

The Pipeline

10 deterministic steps. One Claude Code session.

Your role list (or "find 15")
       ↓
[Intake & Discover]    Step 1–2
       ↓
[Score Fit · Decide Reuse]    Step 3–4
       ↓
[Build Résumés · Write Covers]    Step 5–6
       ↓
[Generate PDFs]    Step 7
       ↓
[Build Application Cockpit]    Step 8
       ↓
dashboard (index.html) + manifest.csv[Package & Zip]    Step 9
       ↓
<name>-application-pack.zip
APPLICATION COCKPIT — LIVE PREVIEW

The dashboard ships as a self-contained index.html. Open it offline. Update status as you hear back. Export anytime.

Application Cockpit Dashboard Interface showing tracking table and pipeline stages
Own — Perpetual License
$40

Job Application Batch Maker

Drop in 15 target roles and walk away. The skill builds per-role résumé and cover-letter PDFs (with strategic reuse documented), a live pipeline funnel, and a self-contained Application Cockpit — all zipped.

  • Application Cockpit: pipeline funnel + status tracking
  • Strategic résumé reuse — 4–7 archetypes documented
  • Per-role cover letters, company-specific (350–650 w)
  • Python scripts: inject batch → dashboard → zip
  • Works offline; CSV/JSON export + restore
  • Runs on your own Claude tokens; no recurring cost
Own the skill — $40 ↓
Perpetual · single-purchaser license · runs on your own tokens in Claude Code
Pair with the ACRA Dashboard Compiler on /book/skills for a full content + career intelligence stack.
What is an agentic job seeker AI tool?

An agentic job seeker AI tool uses a large language model — like Claude — to autonomously find job postings, score fit, generate tailored résumés and cover letters, and produce a tracking dashboard. The Job Application Batch Maker is a Claude Code skill that does exactly this: give it a target list or let it search, and it builds a complete application pack including résumé PDFs, cover letters, and an Application Cockpit dashboard.

How does the Job Application Batch Maker differ from standard AI resume builders?

Standard AI resume builders produce a single document. The Job Application Batch Maker runs an entire pipeline: it scores fit across 15 roles, makes strategic reuse decisions (4–7 archetype résumés instead of 15 bespoke documents), writes company-specific cover letters, generates PDFs, and builds a self-contained Application Cockpit dashboard with a live pipeline funnel and per-row status tracking. It runs on your own Claude tokens with no recurring cost.

What does "perpetual license" mean for a Claude skill?

A perpetual license means you purchase the skill once for $40 and own it forever. There is no subscription. The skill runs inside Claude Code on your own Anthropic API tokens. You can update the candidate profile and run unlimited batches. It is a single-purchaser license for personal use.

Can I use this skill without Claude Code?

The skill is designed for Claude Code CLI or Claude Desktop (Code tab), which provide the file-creation and script-execution environment the pipeline needs. It cannot run in the standard claude.ai chat interface, which does not support local file creation or Python scripts.

§ · Invoice No. 001 · The Build Ledger

The Ledger.

Filed · contextjamming.com

What a conservative mid-market digital agency would have quoted for the same scope, itemized against what this site actually cost. Agency numbers are the floor — not the premium brand-studio tier.

TIME

12 weeks

2 days

~42× faster

COST

~$150,000

~$300

~500× cheaper

TEAM

5-person agency

1 human + 3 models

Same deliverable

§ Itemized — what a mid-market agency SOW would have billed

Discovery · brand positioning · workshops40–80 hr$10,000
Design system · Figma tokens · 3 rounds60–120 hr$18,000
Wavesurfer audio carousel · single-track context60–100 hr$16,000
Dual lightbox systems · focus trap · keyboard30–50 hr$8,000
LLM product flows · streaming · state machine80–160 hr$26,000
Stripe · checkout · webhooks · env hardening40–80 hr$10,000
Editorial routes · 6 sub-pages · templates60–100 hr$14,000
Accessibility pass · aria · reduced-motion40–80 hr$10,000
QA · cross-browser · mobile matrix60–100 hr$14,000
Cross-publication rebrand · masthead + IA · 2026-04-2820–40 hr$6,000
Subtotal~700 hr$126,000
Project management · 18% overhead$24,000
Agency total — conservative floor~700 hr~$150,000
Actually spent · Claude + Gemini stack~20 hr~$300

Agency figure assumes ~700 billable hours at $200/hr blended, plus ~18% PM overhead — the conservative floor of a mid-market SOW. Premium brand studios would have quoted 2–3× that. Stack: Antigravity (orchestrator), Claude Opus 4.8 (auditor), Codex (adversary), Cloudflare Workers / OpenNext.

§   Colophon

How this site is made.

Vol. 26 · build log

Every page on contextjamming.com is the output of a real-time, three-body Mixture-of-Experts loop. One model orchestrates. Two consult. The human holds the thesis. No single model commits alone.

View Redesign Assessment →

Orchestrator

Antigravity

Google DeepMind

  • Primary author
  • Terminal-native, direct push to Cloudflare
  • Audit trail to GitHub on every commit
  • Adaptive thinking · effort: extra-high

Auditor

Claude Opus 4.8

1M context

  • Editorial critic
  • Code review before merge
  • Backup-of-record
  • Co-signs every commit

Adversary

Codex

Cross-model MoE

  • Factual adjudication
  • Structural dissent
  • Deep Research → semantic triples
  • Caught the Donelan incident

Stack

Next.js
16.2 · App Router
React
19.2
TypeScript
5
Tailwind
v4 · @theme inline
@opennextjs/cloudflare
adapter
wrangler
Pages deploy
framer-motion
transitions
wavesurfer.js
audio waveforms

Typeset in

Fraunces
variable · opsz + SOFT
Playfair Display
debate display
IBM Plex Mono
editorial metadata
Geist Mono
utility mono
Caveat
grease-pencil marginalia
All via
next/font/google
Palette
single @theme block
No dupe tokens
ever

Infrastructure

Deploy
Cloudflare Workers / OpenNext
ISR
30-min revalidate · Cloudflare-served
Repo
github.com/BretKerrAI/founderfile
Branch
main
Analytics
Google Tag Manager
Apex
contextjamming.com
Runtime
Node 24
Build tool
Turbopack
       human intent
            │
            ▼
   ┌────────────────────┐         ┌─────────────────┐
   │    Antigravity     │  ◄────► │ Claude Opus 4.8 │      ← auditor loop
   │    (orchestrator)  │         │     (auditor)   │
   └─────────┬──────────┘         └─────────────────┘
             │  ◄───────────┐
             ▼              │
       ┌──────────┐    ┌────┴───────┐
       │Cloudflare│    │   Codex    │          ← adversarial loop
       │ Workers  │    │            │
       └─────┬────┘    └────────────┘
             │
             ▼
       contextjamming.com
             │
             ▼
       ┌──────────────┐
       │   Git push   │         ← audit trail
       └──────────────┘
Assembled on Mac in Terminal · Filed from Franklin, MAContext Jamming · ACRA Insight LLC · MIT License · FounderFile.ai · RelationalIntelligence.xyz · Commission a Dispatch →