experience-record

experience-record is a skill for Claude Code from huskar20/huskar20-plugins. It costs 108 tokens per session (2,947 once invoked), scanned A, original, MIT.

A guided interview and record-keeping skill for building a complete account of one person's working life in a Markdown file. It covers jobs, projects, skills, informal work, and stories across multiple sessions; a Markdown file is a plain-text document with simple formatting.

In plain words
What is it for?
Starting or continuing career interviews, saving the answers to an experience record, and maintaining that record across conversations.
Why use it?
It preserves work experience that people often forget or leave out, especially when their career is non-linear or they tend to undersell themselves. The record can later be used to create a resume.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the resume-forge plugin — 3 skills shipped together

Install

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.

agentmods
npx agentmods add skills/huskar20/huskar20-plugins/experience-record
Any agent
npx skills add huskar20/huskar20-plugins --skill experience-record
Clone the repo
git clone --depth 1 https://github.com/huskar20/huskar20-plugins

Made for: Claude Code.

Or install resume-forge, the plugin that ships this one along with the rest of its 3 skills.

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 experience-record

README.md
[![agentmods](https://agentmods.dev/badge/skills/huskar20/huskar20-plugins/experience-record.svg)](https://agentmods.dev/skills/huskar20/huskar20-plugins/experience-record)
Your own site
<a href="https://agentmods.dev/skills/huskar20/huskar20-plugins/experience-record"><img src="https://agentmods.dev/badge/skills/huskar20/huskar20-plugins/experience-record.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,947 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00108 $0.02947
Opus 5 $0.00054 $0.01473
Sonnet 5 $0.00022 $0.00589
Haiku 4.5 $0.00011 $0.00295

Measured 6d ago against content hash 7462767e110b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

experience-record 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.

plugins/resume-forge/skills/experience-record/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experience Record

Interview one person, patiently, across many sittings, and keep an honest record of their working life in a single markdown file they own.

This is not a resume. It is the truthful, complete record a resume gets built from later. It exists for people who undersell themselves, have non-linear paths, or are early in their careers.

The person is probably not technical. They never edit the file, never paste blocks, never manage anything. They talk; handle the file yourself.

Skill version 1.2.0. Write this into the record's SKILL: header line on every save, so any record can be traced to the version that wrote it.

1. Work out where the record lives — before promising anything

  1. Look for experience-record.md in the working folder and its parents. Found → Mode A, returning session (§4).
  2. Not found → create it from assets/record-template.md, then read it back from the same path. Read succeeds → Mode A, first run (§3).
  3. No working folder, the write fails, or the read-back does not return what you wrote → Mode B. Say once, plainly: their record lives in this conversation, you will hand it back at every save point, and they must keep it to continue later.

Never tell someone their record is saved to a folder unless you have read it back from that folder. When unsure, use Mode B — a file in their hands is recoverable; a file they believe exists and does not is not.

The two modes differ only in how saving works. Everything else is identical.

Read references/record-format.md and references/file-operations.md before your first save — both, not one. In Mode A the second also tells you to snapshot the record before the first write of each session.

Reading the file back proves it is readable, not writable. In some environments those are different paths, and a write can report success while changing nothing. So verify each save as well, per file-operations.md, and never say "Saved." on the strength of a tool's success message alone.

Read the full file on GitHub · 229 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 229 lines · 108 tokens per session scan A 7462767e110b

Subscribe to this mod's changes

experience-record is a skill published in the GitHub repository huskar20/huskar20-plugins (3 stars, last pushed 22d ago), licensed MIT. It adds 108 tokens to every session and 2,947 once invoked, about $0.0005 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.