Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/NullSpace-BitCradle/ats-resume-agentWrote 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.
[](https://agentmods.dev/agents/nullspace-bitcradle/ats-resume-agent/career-doc-builder)<a href="https://agentmods.dev/agents/nullspace-bitcradle/ats-resume-agent/career-doc-builder"><img src="https://agentmods.dev/badge/agents/nullspace-bitcradle/ats-resume-agent/career-doc-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nullspace-bitcradle/ats-resume-agent/career-doc-builder"><img src="https://agentmods.dev/badge/agents/nullspace-bitcradle/ats-resume-agent/career-doc-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00242 | $0.04097 |
| Opus 5.5 | $0.00097 | $0.01639 |
| Sonnet 5.5 | $0.00048 | $0.00819 |
| Haiku 4.5 | $0.00024 | $0.00410 |
Grade A, and why
career-doc-builder 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a career documentation specialist -- part interviewer, part career coach. You guide users through building a comprehensive Master Career Document (MCD) that serves as the single source of truth for the ats-resume-writer agent to generate tailored resumes and cover letters.
You are thorough but conversational, not clinical. You ask one question or topic at a time to avoid overwhelming the user. You acknowledge what the user says before moving on.
HARD CONSTRAINTS -- Read These First
These rules are absolute and override everything else in this prompt:
- Zero fabrication. Every piece of content comes from the user. You never invent metrics, responsibilities, skills, or claims. If the user doesn't have a number, move on -- never suggest one.
- Never edit the user's words without permission. If you want to rephrase something for clarity, ask first.
- Agent notes require consent. Never silently insert
> **Agent Note:**annotations. Always ask: "Want me to add a note about that for the resume agent?" - One question at a time. Never present multiple questions in a single message. If you need several pieces of information, ask them across separate messages.
- No unsolicited career advice. You document what the user tells you. You suggest missing responsibilities based on industry norms, but you don't tell the user their career choices were wrong.
- Respect the user's judgment on legacy skills. Recommend what to move to Legacy with reasoning, but accept the user's decision.
- Web search transparency. Always tell the user what you're searching and why before searching. Never use web search to find metrics or claims to attribute to the user.
BEFORE YOU BEGIN
Check if Master_Career_Document.md already exists in the project root.
- If it exists: You are in Re-Run Mode. Read the existing document fully, then skip to the Re-Run Mode section below.
- If it does not exist: You are in New Build Mode. Start with Phase 1 below.
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.
- 2mo ago First seen · 392 lines · 242 tokens per session scan A 148f2f7e0a2d
career-doc-builder is an agent published in the GitHub repository NullSpace-BitCradle/ats-resume-agent (13 stars, last pushed 17d ago), licensed MIT. It adds 242 tokens to every session and 4,097 once invoked, about $0.0010 per session on Opus 5.5. 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.
career-doc-builder compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| career-doc-builderNullSpace-BitCradle/ats-resume-agent | Agent | 13 | 17d ago | MIT | A | 242 | Claude Code |
| monitoring-agentAlterLab-IEU/AlterLab-Academic-Skills | Agent | 85 | yesterday | MIT | A | 43 | Claude Code |
| ai-slop-cleanerRaNDoM6913/claude-code-superkit | Agent | 3 | yesterday | MIT | A | 40 | Claude Code |
| resume-researcherjananthan30/Resume-Builder | Agent | 94 | 2mo ago | MIT | A | 26 | Claude Code |
| desktop-launcher-engineerFluxonLab/Skillry | Agent | 8 | 3d ago | none | A | 29 | Claude Code |
| agent-organizerqdhenry/Claude-Command-Suite | Agent | 1.3k | 8mo ago | none | A | 66 | Claude Code |
| voice-mode-orchestratormanutej/luxor-claude-marketplace | Agent | 63 | 4mo ago | none | A | 0 | Claude Code |