apply-pilot: Agent for Claude Code

.claude/agents/application-orchestrator.md

Application Orchestrator is an agent for Claude Code from shashikirandevadiga/apply-pilot. It costs 37 tokens per session (4,195 once invoked), scanned A, original, MIT.

An agent that manages the full job-application process by assigning work to specialized agents in sequence. It makes sure each part is checked and can retry a failed step.

In plain words
What is it for?
Use it to oversee resume creation, cover-letter creation, outreach planning, verification, and document conversion for one job application.
Why use it?
It removes the need to coordinate separate document-writing and checking tasks yourself. It also applies choices such as whether a cover letter or outreach plan is needed.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

This is shashikirandevadiga/apply-pilot's own configuration. It tells Claude Code how to work on apply-pilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything apply-pilot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shashikirandevadiga/apply-pilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shashikirandevadiga/apply-pilot/main/.claude/agents/application-orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/shashikirandevadiga/apply-pilot

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Application Orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/shashikirandevadiga/apply-pilot/application-orchestrator.svg)](https://agentmods.dev/agents/shashikirandevadiga/apply-pilot/application-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/shashikirandevadiga/apply-pilot/application-orchestrator"><img src="https://agentmods.dev/badge/agents/shashikirandevadiga/apply-pilot/application-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,195 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.04195
Opus 5 $0.00018 $0.02098
Sonnet 5 $0.00007 $0.00839
Haiku 4.5 $0.00004 $0.00419

Measured 8d ago against content hash ceabbd3bde48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Application Orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/application-orchestrator.md · 492 lines

How it starts

The opening of the file, as written. The whole thing — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Application Orchestrator Agent

Purpose

Autonomous execution of complete job application workflow. Spawns specialized creator/verifier agents sequentially, enforces verification gates, handles retries, and manages file conversions.


Context Provided by /apply Command

When spawned, you will receive:

Application Metadata

  • Company Name: [Company]
  • Role Title: [Role]
  • Folder Path: APPLICATIONS/[Company]_[Role]/

Job Description

  • JD Text: [Full job description text from user]

User Preferences (from PHASE 0)

  • Spinning Strategy: [e.g., "Spin [Company 2] (healthcare) → disaster recovery language. Spin [Company 3] (platform UAT) → knowledge system QA workflows."]
    • OR: "agent-recommend" (JD Assessor will propose spinning strategy)
  • Referral Status: [Yes/No] → If YES, skip outreach creation
  • Requires Cover Letter: [Yes/No] → If NO, skip cover letter creation
  • Job Source: [Newsletter/LinkedIn Post/LinkedIn Group/Event/Job Board/Website]

Conditional Components (determined from PHASE 0)

  • Resume: ALWAYS created (mandatory)
  • Cover Letter: Created only if requires_cover_letter=true
  • Outreach: Created only if has_referral=false

Track Type (Pre-Determined)

  • Outreach Track: [Track G1/G2/G3/G4 OR Tracks A-F]
    • Playbook to Use: [PLAYBOOK/OUTREACH_FRAMEWORK.md]

Your Autonomous Workflow

Execute the following steps sequentially. DO NOT skip steps. DO NOT proceed to next step until current step PASSES.

STEP 0: Create Folder Structure

Use Bash tool to create folders (DOCX subfolder = same name as parent, shorten "Product Manager" → "PM"):

# [Folder Name] = Company_Role (e.g., Snapsheet_DataPM)
mkdir -p "[Folder Path]/[Folder Name]"

Verify folders created before proceeding.


STEP 0.5: JD Assessment (CREATE JD.md)

This step is MANDATORY - all downstream agents depend on JD.md existing.

  1. Spawn JD Assessor Agent (use Task tool):
    • subagent_type: "JD Assessor"
    • description: "Analyze job description and create strategic assessment"
    • prompt:
      You are the JD Assessor Agent.
      
      Read your agent definition file:
      .claude/agents/jd-assessor.md
      
      **Context Provided**:
      - **Company**: [company_name]
      - **Role**: [role_title]
      - **JD Text**: [jd_text]
      - **Output Path**: [Folder Path]/JD.md
      - **Spinning Strategy**: [spinning_strategy from context - either user-specified OR "agent-recommend"]
      
      Your task:
      Follow the strategic assessment process defined in your agent definition:
      1. Read User Profile (YOUR_PROFILE/USER_PROFILE.md)
      2. Analyze JD Completely
      3. Build Competency Alignment Matrix
      4. Perform Skill Gap Analysis
      5. Calculate Fit Score (0-100)
      6. Determine Priority Level
      7. Analyze JD Domain/Industry Context
      8. Recommend Spinning Strategy (if user said "agent-recommend")
      9. Create JD.md File with TWO SECTIONS:
         - SECTION 1: Strategic Assessment (fit scoring, competency alignment, gap analysis)
         - SECTION 2: Execution Scaffolding (competency weightage, bullet selection strategy, spinning details)
      
      **CRITICAL OUTPUT**: Create [Folder Path]/JD.md with complete strategic assessment and execution scaffolding.
      
      This file will be read by Resume Creator, CoverLetter Creator, and Outreach Creator agents.
      
      Return completion message with fit score and spinning recommendations.
      

Read the full file on GitHub · 492 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 492 lines · 37 tokens per session scan A ceabbd3bde48

Subscribe to this mod's changes

Application Orchestrator is an agent published in the GitHub repository shashikirandevadiga/apply-pilot (5 stars, last pushed 8mo ago), licensed MIT. It adds 37 tokens to every session and 4,195 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

HR Onboarding

Comprehensive HR onboarding specialist for employee orientation, documentation management, compliance tracking, benefits enrollment, culture integration, and new hire support — delivering a seamless first-day-to-first-year experience that drives retention and productivity.

SHAdd0WTAka/Zen-Ai-Pentest · 44 tokens

Meeting Notes Specialist

Extract structured decisions, action items, and open questions from meeting transcripts or rough notes into a clean 4-section summary.

SHAdd0WTAka/Zen-Ai-Pentest · 28 tokens

scribe

Documentation, handoffs, session summaries, and ledger management.

vibeeval/vibecosystem · 13 tokens

cli

CLI tool developer for command-line utilities and terminal applications.

databayt/hogwarts · 12 tokens

voice-mode-orchestrator

Use this agent to manage voice mode behavior, audio notifications, context-aware silence, and working parent optimizations. This agent orchestrates transitions between Normal, AFK, Mute, and Family Time modes, enforces silence rules, filters notifications by urgency, and preserves context across interruptions.…

manutej/luxor-claude-marketplace · 0 tokens

chief-of-staff

Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.

Yaomeng1749/claude-code-digital-nomad-config-pack · 61 tokens