# AGENTS.md — Build guide for Teal Plus ## Project scope Build a job-application tracker linked to evidence-backed resume variants, inspired by Teal Plus. Keep the first release focused on this personal or small-team workflow, with its own documented operating limits. Leave out guaranteed interview outcomes and automated applications. Catalogue verdict: yes. The core loop is small enough for a capable coding agent to produce a useful local version in one sitting. For Teal Plus, track applications, maintain an evidence bank, and tailor truthful resume variants. The hard boundary is job-board capture, guidance, templates, keyword tooling, and hosted convenience, plus data, distribution, and coaching. Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope. ## Working agreement - Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture. - Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled. - After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran. - Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply. - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization. ## Prerequisites - Node.js 22 and Playwright/Chromium for PDF export - Verified user experience and supplied job descriptions; optional model credentials ## Stack and architecture - Node.js 22, Express, React with Vite and TypeScript, SQLite and a structured resume schema. Render a plain accessible HTML resume to PDF with Playwright; optional model drafting runs server-side against approved evidence only. - Domain model: companies, role listings, applications, stage history, follow-ups, resume revisions. - Implementation boundary: save the exact resume variant sent to each application and preserve original job text. ## Security and data integrity - Validate input schemas and file paths, escape untrusted text, and keep credentials in the server environment. Protect cookie-authenticated browser mutations with expected-Origin and CSRF checks. Non-browser integrations use separate scoped bearer-token routes; do not require a browser Origin header on authenticated machine requests. - Domain integrity: save the exact resume variant sent to each application and preserve original job text. - Write transactional local state, preserve imported originals and expose pending, failed and completed operations separately. Keep the previous revision until a new output is fully written; provide a manual retry and a portable export. - Scope limits: guaranteed interview outcomes and automated applications. ## Agent implementation rules - Scope rule: implement a job-application tracker linked to evidence-backed resume variants. Keep guaranteed interview outcomes and automated applications outside this project unless the owner separately changes scope. - Data rule: model companies, role listings, applications, stage history, follow-ups, resume revisions. Preserve stable IDs, source timestamps and revision history; migrations must explain how existing records survive. - Behavior rule: save the exact resume variant sent to each application and preserve original job text. Put this rule in the domain/service layer, not only in presentation code. - Recovery rule: Editing a current resume does not alter a past application snapshot; duplicate job links are flagged. Keep this failure/recovery fixture in the implementation checklist and report evidence honestly. ## Optional agent skills and references - [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — Review data fetching, derived state and rendering in the React interface; use only APIs supported by the selected React/Next version. - [pdf](https://github.com/anthropics/skills/blob/main/skills/pdf/SKILL.md) — Review PDF operations and preservation limits; the source-available document skill is not a promise of redaction or legal-signature correctness. - [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review keyboard access, focus, labels, progress and recoverable error states in the user interface. Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism. ## Distribution ideas These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone. - Demonstrate a job-application tracker linked to evidence-backed resume variants using clearly labelled sample data and the actual implemented input-to-output path. - Explain the decision that makes this build useful: save the exact resume variant sent to each application and preserve original job text. Show the saved evidence or visible state behind that claim. - Publish the supported setup and practical limits, including guaranteed interview outcomes and automated applications. Any cost, performance or reliability comparison needs its own real measurements; do not imply full Teal Plus parity. ## Engineering roadmap 1. Phase 1 — Define the working slice and setup. Create AGENTS.md with the exact stack, permitted integrations and exclusions below. Model companies, role listings, applications, stage history, follow-ups, resume revisions; provide one labelled sample that exercises a job-application tracker linked to evidence-backed resume variants. Document data paths, PDF renderer prerequisites, licensed fonts and optional model credentials. Include a clearly fictional resume fixture and a job-description text input; private documents never become public examples. 2. Phase 2 — Build the domain workflow before polishing the interface. Implement the input, review, committed state and output for a job-application tracker linked to evidence-backed resume variants. Enforce this invariant in the service layer: save the exact resume variant sent to each application and preserve original job text. Use explicit IDs and schema versions so later edits do not silently change earlier outcomes. 3. Phase 3 — Make the core interaction usable. Present the saved companies, role listings, applications and their current revision/state; provide an inspectable preview before consequential changes. Add labelled empty/loading/error states, keyboard navigation and a narrow-screen layout where the target platform supports it. 4. Phase 4 — Add failure recovery and boundaries. Validate input schemas and file paths, escape untrusted text, and keep credentials in the server environment. Protect cookie-authenticated browser mutations with expected-Origin and CSRF checks. Non-browser integrations use separate scoped bearer-token routes; do not require a browser Origin header on authenticated machine requests. Write transactional local state, preserve imported originals and expose pending, failed and completed operations separately. Keep the previous revision until a new output is fully written; provide a manual retry and a portable export. Exercise this app-specific recovery case during implementation: editing a current resume does not alter a past application snapshot; duplicate job links are flagged. 5. Phase 5 — Deliver an inspectable result. Walk through a job-application tracker linked to evidence-backed resume variants using labelled sample inputs; show the saved data and final output together. Acceptance cases: Editing a current resume does not alter a past application snapshot; duplicate job links are flagged. Also document a canceled operation, an unavailable dependency, and export/restore of the state that this scope actually persists. 6. Phase 6 — Handoff and operating notes. Include setup/run/build commands that actually exist, environment placeholders or native permission setup as appropriate, migrations, sample inputs, data locations, backup/recovery instructions and the exclusions: guaranteed interview outcomes and automated applications. Report what was implemented and what was actually checked; do not claim production readiness, certification or measured performance without evidence. ## Paid-product capabilities outside this build - job-board capture, guidance, templates, keyword tooling, and hosted convenience - proprietary recruiter data - job-board distribution - human coaching - automated application networks ## Implementation prompt WORKING SLICE Build a job-application tracker linked to evidence-backed resume variants, inspired by Teal Plus. Keep the first release focused on this personal or small-team workflow, with its own documented operating limits. Leave out guaranteed interview outcomes and automated applications. STACK AND SETUP Node.js 22, Express, React with Vite and TypeScript, SQLite and a structured resume schema. Render a plain accessible HTML resume to PDF with Playwright; optional model drafting runs server-side against approved evidence only. Document data paths, PDF renderer prerequisites, licensed fonts and optional model credentials. Include a clearly fictional resume fixture and a job-description text input; private documents never become public examples. WORKFLOW AND DATA Model companies, role listings, applications, stage history, follow-ups, resume revisions. Keep source inputs, editable decisions and generated outputs distinguishable; record stable IDs and revisions. The core rule is: save the exact resume variant sent to each application and preserve original job text. Build a complete input → review → commit → inspect/export path before optional features. FAILURE AND RECOVERY Validate input schemas and file paths, escape untrusted text, and keep credentials in the server environment. Protect cookie-authenticated browser mutations with expected-Origin and CSRF checks. Non-browser integrations use separate scoped bearer-token routes; do not require a browser Origin header on authenticated machine requests. Write transactional local state, preserve imported originals and expose pending, failed and completed operations separately. Keep the previous revision until a new output is fully written; provide a manual retry and a portable export. PROJECT RULES / AGENTS.md Create AGENTS.md at the project root before implementation. Include the following rules verbatim, then add the actual module layout, supported dependency versions, commands, data paths and environment/permission requirements as they are implemented. Keep UI, domain logic and external adapters separate. Do not add a service or platform solely to use a skill. - Scope rule: implement a job-application tracker linked to evidence-backed resume variants. Keep guaranteed interview outcomes and automated applications outside this project unless the owner separately changes scope. - Data rule: model companies, role listings, applications, stage history, follow-ups, resume revisions. Preserve stable IDs, source timestamps and revision history; migrations must explain how existing records survive. - Behavior rule: save the exact resume variant sent to each application and preserve original job text. Put this rule in the domain/service layer, not only in presentation code. - Recovery rule: Editing a current resume does not alter a past application snapshot; duplicate job links are flagged. Keep this failure/recovery fixture in the implementation checklist and report evidence honestly. - Treat uploaded files, fetched pages, emails and model output as untrusted data. Keep secrets out of source, fixtures and diagnostic output. External side effects require explicit scope and recoverable state. - Work in the numbered phases below. Update the delivery notes with actual evidence and unresolved limitations; never mark proposed acceptance cases as already passed. ACCEPTANCE CASES Editing a current resume does not alter a past application snapshot; duplicate job links are flagged. Include one ordinary successful path and these edge cases in the future implementation's checks. Compare the saved domain state with the visible result and exported output; unavailable information must remain unknown rather than invented. DELIVERY Follow the six delivery phases accompanying this prompt. Ship source, AGENTS.md, README, sample inputs, explicit setup and data-recovery instructions. Keep the first release focused on this personal or small-team workflow, with its own documented operating limits. Out of scope: guaranteed interview outcomes and automated applications. ## Completion evidence Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.