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/vincentlaucsb/experiencer/agents-mdgit clone --depth 1 https://github.com/vincentlaucsb/experiencerWrote 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/vincentlaucsb/experiencer/agents-md)<a href="https://agentmods.dev/instructions/vincentlaucsb/experiencer/agents-md"><img src="https://agentmods.dev/badge/instructions/vincentlaucsb/experiencer/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 5.1 | $0.01028 | $0.01028 |
| Opus 5 | $0.00514 | $0.00514 |
| Sonnet 5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
experiencer 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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Product Scope
- Treat Experiencer OSS as a complete local-first résumé editor. Bug fixes, security, accessibility, compatibility, performance, templates, and regressions are in scope.
- Keep this repository Pro-agnostic. Do not add cloud accounts, billing, entitlements, hosted revision history, custom-template persistence, or Pro terminology.
- Generic extension points are welcome when independently useful to the public editor; private product policy belongs in the consuming Pro repository.
Architecture
- Treat React components as view adapters. Keep workflows, persistence, cross-store coordination, observer policy, and other reusable behavior in framework-neutral stores, services, coordinators, or utilities under
src/shared. - Do not introduce React Context for business state. Keep hooks small: subscribe, bind events, invoke commands, or bridge a platform lifecycle. Effects must remain mechanical.
- Treat
src/app/Resume.tsxas the application composition and mode-routing boundary. Do not add feature workflows, persistence, browser APIs, modal implementations, menus, or asynchronous orchestration there. - Keep handwritten classes and non-obvious invariants concisely documented, especially lifecycle, stale-request, persistence, and rendering boundaries.
Resume Components
- Follow
src/resume/AGENTS.mdfor component-specific editing and event rules. - Register résumé node capabilities through the canonical schema rather than creating parallel type knowledge.
- Preserve semantic node structure, extraction order, and read-only behavior across editor, preview, print, and export surfaces.
Canonical Resume Document Rendering
- Follow
docs/RESUME-DOCUMENT-PIPELINE.mdfor the current rendering contract. - Treat
createResumeDocumentSource→prepareResumeDocument→ a rendering adapter as the only canonical document pipeline. Do not scrape the live editor DOM or reconstruct résumé markup and CSS independently. - Authored CSS must remain standalone and must not contain
#resume. Only the editor adapter scopes selectors to its private#resumehost. The server-owned public-review shell is an infrastructure exception, not authored or persisted CSS. - Standalone targets receive only résumé-owned CSS and requested font stylesheets. Never copy application styles, host theme attributes, editor state, or application DOM into a résumé document.
- Extend the canonical target/root types for every new rendering surface and add contract coverage for markup, stylesheet isolation, page size, fonts, and editor-only element removal.
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.
- 6d ago First seen · 64 lines · 1,028 tokens per session scan A fc0f6991e9de
experiencer AGENTS.md is an instructions file published in the GitHub repository vincentlaucsb/experiencer (90 stars, last pushed 3d ago), licensed MIT. It adds 1,028 tokens to every session, about $0.0051 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 2026-08-30.
Other instructions, from other repositories
resume-ci AGENTS.md
Instructions for gustavo-ferreira03/resume-ci, covering agents.md, project context, yaml rules, star method and evidence standards.
agentic-resume-builder CLAUDE.md
Claude Code instructions for WtotdeD/agentic-resume-builder, covering agentic-resume-builder development guidelines, what this repo is, active technologies, package manager and validation.
resume-parser AGENTS.md
Instructions for dhanushk-offl/resume-parser, covering agents.md — agent configuration for resume parser skill, skill name, description, install and capabilities.
mcp-pandoc AGENTS.md
Instructions for vivekVells/mcp-pandoc, covering agents.md, what this is, where things are, deeper context and commands.
fcp-sheets CLAUDE.md
Instructions for os-tack/fcp-sheets, covering fcp-sheets, project overview, architecture, key patterns and commands.
paperless-ngx-mcp-server CLAUDE.md
Claude Code instructions for cbsmiley/paperless-ngx-mcp-server, covering claude.md, project overview, common commands, architecture and entry points.