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 automagik-dev/genie --skill offload-guidancegit clone --depth 1 https://github.com/automagik-dev/genieWrote 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/automagik-dev/genie/offload-guidance)<a href="https://agentmods.dev/skills/automagik-dev/genie/offload-guidance"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/offload-guidance/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/automagik-dev/genie/offload-guidance"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/offload-guidance.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 | $0.00267 | $0.02369 |
| Opus 5.5 | $0.00107 | $0.00948 |
| Sonnet 5.5 | $0.00053 | $0.00474 |
| Haiku 4.5 | $0.00027 | $0.00237 |
Grade A, and why
offload-guidance 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 today.
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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offloading exploration to mikro
The rule
Explore-class question → call mikro_explore-r first. Treat its answer as a
lead, not as a finding. Escalate to your own tools the moment any of the three
triggers below fires.
explore-r is a first-pass explorer. It failed its parity gate —
Round-2 gate: FAIL (docs/parity-explore.md:993), agreeing with round 1's
Gate: FAIL (docs/parity-explore.md:595). It ships anyway because a first
pass does not have to be a verdict: it has to be cheaper than reading the tree
yourself and honest about where it stops. Everything claimed below comes from
that report, at the report's own scoping. Read
docs/parity-explore.md in the mikro repository before quoting any of it; if it
and this file disagree, the report wins.
When to route
Route when all of these hold:
- The question is about a codebase you have not already read into context.
- Answering it inline would mean opening many files — a survey, a "where is X handled", a "how does Y flow through this repo", a "what are all the Z".
- A wrong first answer is recoverable, because you are going to check the citations anyway.
Do not route when:
- You already have the file in context. Reading it is cheaper and exact.
- The question is about a specific known line, a diff you just made, or a test you just ran.
- The answer must be complete — see escalation trigger 3.
- The work is a mutation.
explore-rreads; it does not edit, run your build, or touch git.
How to call it
Tool: mikro_explore-r (namespaced mcp__plugin_mikro_mikro__mikro_explore-r
when it comes from this plugin). It explores the project directory the server
was started with — the plugin passes --dir ${CLAUDE_PROJECT_DIR}, so that is
your project root.
| Argument | Use |
|---|---|
prompt |
The question. Required in practice. |
session_id |
Continue an earlier call on this same tool. Omit to start fresh. |
context |
Optional path to a file or directory to preload, relative to the project root. |
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.
- today First seen · 173 lines · 267 tokens per session scan A 19c92affbc63
offload-guidance is a skill published in the GitHub repository automagik-dev/genie (346 stars, last pushed today), licensed MIT. It adds 267 tokens to every session and 2,369 once invoked, about $0.0011 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 2026-10-16.
Other skills, from other repositories
telegram
Telegram Bot skill for sending and editing Telegram messages via Bot API. Use when Bub needs to: (1) Send a message to a Telegram user/group/channel, (2) Reply to a specific Telegram message with replytomessageid, (3) Edit an existing Telegram message, or (4) Push proactive Telegram notifications. Prefer rich…
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
static
Stash is your personal home for agent work. Everything you create is scoped to your account — it is yours alone, with nothing to pick or set up first. Your Stash has three primary surfaces.
brief
Brief the user on what they saved in a period — the thread running through it, not a list.
resurface
Pick a few old saves worth revisiting now, and say why now.
cleanup
Find duplicates, dead links and untagged items in a saved library and propose what to do about each.