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 skills/huskar20/huskar20-plugins/experience-recordnpx skills add huskar20/huskar20-plugins --skill experience-recordgit clone --depth 1 https://github.com/huskar20/huskar20-pluginsWrote 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/skills/huskar20/huskar20-plugins/experience-record)<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>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 | $0.00108 | $0.02947 |
| Opus 5 | $0.00054 | $0.01473 |
| Sonnet 5 | $0.00022 | $0.00589 |
| Haiku 4.5 | $0.00011 | $0.00295 |
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.
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
- Look for
experience-record.mdin the working folder and its parents. Found → Mode A, returning session (§4). - Not found → create it from
assets/record-template.md, then read it back from the same path. Read succeeds → Mode A, first run (§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.
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.
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 · 229 lines · 108 tokens per session scan A 7462767e110b
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.