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 onboard-reportgit 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-report)<a href="https://agentmods.dev/skills/vbcherepanov/total-agent-memory/onboard-report"><img src="https://agentmods.dev/badge/skills/vbcherepanov/total-agent-memory/onboard-report/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-report"><img src="https://agentmods.dev/badge/skills/vbcherepanov/total-agent-memory/onboard-report.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 | $0.00065 | $0.00670 |
| Opus 5.5 | $0.00026 | $0.00268 |
| Sonnet 5.5 | $0.00013 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade B, and why
onboard-report scanned grade B with 1 finding 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 29d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
For each item in `grading_queue`, show prompt, rubric and answer, ask the head How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/onboard-report — onboarding results and curriculum
Tools are named onboarding_* (possibly client-prefixed). The server enforces
access: department heads (team role manager) see and manage their own
department; company_viewer and superadmin see every department; superadmin
may also manage. A Forbidden error means the user lacks that role — say so.
1. Pick the department
Use $ARGUMENTS if given. Otherwise call onboarding_overview and choose from
viewable_teams (report) or manageable_teams (editing).
2. Report
Call onboarding_team_report(team_id) and present:
- a table: employee × module with status (not started / in progress / quiz available / awaiting review / passed / failed), lessons done, best quiz score, and the relevant date (started, finished, passed);
- who is stuck (failed with no attempts left, or no activity) and lessons
flagged as updated since people studied them (
summary.updated_lessons); - the latest entries of
login plain language.
For one person's detail: onboarding_progress(team_id, user_id).
3. Grade open answers (department head)
For each item in grading_queue, show prompt, rubric and answer, ask the head
for points (0..points) and an optional comment, then call
onboarding_grade(attempt_id, question_id, score, comment). Grading the last
open answer finalizes the attempt. Never grade without the head's decision.
4. Build or edit the curriculum (department head)
onboarding_curriculum_get(team_id)→ current curriculum andrevision.- For a first version,
onboarding_curriculum_draft(team_id)groups the department's memory into modules/lessons (LLM-polished only if the server has one). Review it with the head: reorder, rename, remove, add lesson text. - Save with
onboarding_curriculum_set(team_id, expected_revision, curriculum). Keep existingids so employees keep their progress; omitted items are archived. - Quizzes per module:
onboarding_quiz_draft(module_id)(needs a server LLM; drafts are checked against lesson quotes) or write questions with the head, thenonboarding_quiz_set(module_id, expected_revision, questions). Question types:single,multiple(zero-basedcorrectindexes),open(needsrubric). Setpass_thresholdandmax_attemptsper module in the curriculum.
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.
- 29d ago First seen · 59 lines · 65 tokens per session scan B 07a4c4fd88d0
onboard-report is a skill published in the GitHub repository vbcherepanov/total-agent-memory (73 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 670 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). 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.
memoh-help
You are Memoh, so when a user asks about Memoh they are asking about you. Use when the user asks what Memoh can do, how to set something up, where a setting is, how bots, workspaces, channels, memory, skills, Supermarket, connectors, schedules, hooks, MCP, ACP agents, access, the desktop app, or self-hosting work…
paper-explain-figures
A workflow for explaining figures from research papers, including what charts, diagrams, or images show and how to read them.