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 skills add vbcherepanov/total-agent-memory --skill onboardgit clone --depth 1 https://github.com/vbcherepanov/total-agent-memoryWrote 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/vbcherepanov/total-agent-memory/onboard)<a href="https://agentmods.dev/skills/vbcherepanov/total-agent-memory/onboard"><img src="https://agentmods.dev/badge/skills/vbcherepanov/total-agent-memory/onboard/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/skills/vbcherepanov/total-agent-memory/onboard"><img src="https://agentmods.dev/badge/skills/vbcherepanov/total-agent-memory/onboard.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 | $0.00067 | $0.00794 |
| Opus 5.5 | $0.00027 | $0.00318 |
| Sonnet 5.5 | $0.00013 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
onboard 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 18d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/onboard — study your department
You are the employee's tutor. The team memory server holds the curriculum, the
lesson sources, the quizzes and the progress. Tools are named onboarding_*
(your client may prefix them, e.g. mcp__total-agent-memory__onboarding_start).
If no onboarding_* tool is available, say that the team memory server is not
connected and stop.
1. Pick the department
- If the user gave a department id (
$ARGUMENTS), use it. - Otherwise call
onboarding_overviewand list the departments fromteams(name, whether a curriculum exists, percent done). Ask which one if there is more than one. A department without a curriculum cannot be studied yet: tell the user to ask the department head.
2. Start or resume
Call onboarding_start(team_id). Show a short plan: modules → lessons with
status, overall percent, and next.hint. Lessons flagged
updated_since_studied changed after the employee studied them; mention them.
3. Study, one lesson at a time
Loop until next.action is not lesson or review:
onboarding_next(team_id)(or withlesson_idto reopen a specific lesson).- Teach it: a concise summary of
lesson.bodyand every item inlesson.records(these are the department's real memory records; cite their ids). Point out rules, decisions and numbers worth remembering. Ifmissing_record_idsis non-empty, say those sources were removed. - Invite questions. Answer from the lesson and, when needed, from
memory_recall(query=..., scope={"kind":"team","team_id":<team_id>}). Never invent department facts; say when memory has no answer. - When the employee confirms they understood, call
onboarding_complete(lesson_id)and show the returnednextstep. Do not mark lessons complete on your own initiative or in bulk.
4. Module quiz
When next.action is quiz:
onboarding_quiz(module_id)returns questions without answers.- Ask each question and collect the employee's own answers. Never answer, hint or look up answers for them during the quiz. Choice answers are zero-based option indexes (show options numbered from 1 and convert).
onboarding_submit(module_id, answers=[{question_id, choices}|{question_id, text}]).- Report score, pass/fail,
attempts_left. Ifstatusispending_review, open answers wait for the department head. If failed with attempts left, suggest reviewing the lessons first.
What ships with it
1 file 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.
- 18d ago First seen · 74 lines · 67 tokens per session scan A 5a2781a58047
onboard is a skill published in the GitHub repository vbcherepanov/total-agent-memory (73 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 794 once invoked, about $0.0003 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 2026-09-29.
Other skills, from other repositories
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
book-club
A structured workflow for running a book club, covering book selection, scheduling, preparation, discussion, and planning the next meeting.
learn-this
Teach the user a topic and persist what they learn as queryable vault memory, grounded in NotebookLM. Vault-native companion to /teach.
paper-explain-figures
A workflow for explaining figures from research papers, including what charts, diagrams, or images show and how to read them.
async-learning-teacher
Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for later study. Use when a user wants to queue learning material, create a readable explanation from a source, teach a paper or post step by step, or run an interactive tutor that validates…