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.
npx agentmods add instructions/davevoyles/resume-builder/agents-mdgit clone --depth 1 https://github.com/DaveVoyles/resume-builderWrote 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/instructions/davevoyles/resume-builder/agents-md)<a href="https://agentmods.dev/instructions/davevoyles/resume-builder/agents-md"><img src="https://agentmods.dev/badge/instructions/davevoyles/resume-builder/agents-md.svg" alt="Measured on agentmods" 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 | $0.01314 | $0.01314 |
| Opus 5 | $0.00657 | $0.00657 |
| Sonnet 5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
resume-builder AGENTS.md 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 5d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🤖 Agent instructions
Cursor Cloud: see docs/cursor-cloud.md.
This CLI is agent-operated: you are the primary operator, and the CLI is your deterministic toolbelt for parsing, validating, rendering, and tracking resumes. See ADR 0001 for the design rationale.
Use this repo to help a candidate run an evidence-backed resume workflow. Assume the candidate wants the agent-first path unless they explicitly ask for CLI-only instructions.
🚀 Default workflow
- 📦 Run
npm installif dependencies are missing. - 🧪 Run
npm startso the candidate can see the fictional sample workflow. - 🧭 Follow
docs/playbooks/onboarding.mdfor first-run sequencing — it checks the workspace's actual state (does it exist? has real material been dropped in? has it been ingested? has intake happened?) and greets the candidate at the right step instead of always starting from scratch.
Throughout the lifecycle, not just at first launch:
- 🙋 Ask clarifying questions before making claims that are missing, vague, or high impact.
- 📌 Record unanswered questions in workspace notes or
candidate/outputs/follow-up-questions.md. - ✅ Run
npm run workspace:validate -- --workspace candidatebefore handoff. - 🔒 Run
npm run check:privacybefore committing or sharing anything.
⚠️ Claim rules
- Do not invent experience, metrics, degrees, employers, production usage, or ownership.
- Use
profile.jsonandevidence.jsonlas the source of truth. - If a claim lacks evidence, ask the candidate or record a follow-up question.
- Phrase low-confidence claims cautiously and mark them for candidate review.
- Do not promote a similar role to tracked status until the candidate approves it.
🔒 Privacy rules
- Treat
candidate/as private workspace data. - Do not commit real resumes, private notes, profile files, evidence ledgers, tracked roles, or generated outputs.
- Commit reusable code, docs, templates, schemas, and fictional examples only.
- If a privacy check fails, stop and fix the staged or tracked private file before proceeding.
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.
- 5d ago First seen · 103 lines · 1,314 tokens per session scan A eff06d6a9d82
resume-builder AGENTS.md is an instructions file published in the GitHub repository DaveVoyles/resume-builder (10 stars, last pushed 13d ago), licensed MIT. It adds 1,314 tokens to every session, about $0.0066 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.
Other instructions, from other repositories
vitaecontext AGENTS.md
AGENTS.md instructions for vitaecontext/vitaecontext, covering agents.md, scope, start here, source of truth and brand contract.
vitaecontext copilot-instructions.md
Copilot instructions for vitaecontext/vitaecontext, covering repository instructions for github copilot, repository model, coding and documentation rules and validation.
job-seeker AGENTS.md
Instructions for galiprandi/job-seeker, covering job seeker — rules, gold rules, gold rule 1, gold rule 2 and gold rule 3 — user preferences always up to date.
vitaecontext GEMINI.md
Gemini CLI instructions for vitaecontext/vitaecontext, covering vitaecontext, module map and runtime loading.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
trackly-cli AGENTS.md
AGENTS.md instructions for trackly-app/trackly-cli, covering agents.md - trackly-cli, project overview, architecture, dev commands and no build step — pure js.