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 Mininglamp-OSS/octo-cli --skill octo-drivegit clone --depth 1 https://github.com/Mininglamp-OSS/octo-cliWrote 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/mininglamp-oss/octo-cli/octo-drive)<a href="https://agentmods.dev/skills/mininglamp-oss/octo-cli/octo-drive"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-cli/octo-drive/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/mininglamp-oss/octo-cli/octo-drive"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-cli/octo-drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 200 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 229 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00055 | $0.04645 |
| Opus 5 | $0.00028 | $0.02322 |
| Sonnet 5 | $0.00011 | $0.00929 |
| Haiku 4.5 | $0.00006 | $0.00464 |
Grade A, and why
octo-drive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
octo-drive — network drive operations
45 commands over one backend. Everything is scoped to a drive space: either your personal space or a shared one you are a member of.
1. Credentials — nothing drive-specific
Drive uses the same credential as every other domain. Set one of:
export OCTO_TOKEN=<uk_… | bf_… | app_…> # preferred slot, any token kind
export OCTO_BOT_TOKEN=<bf_… | app_…> # long-standing variable, still fine
OCTO_TOKEN wins when both are set, so you can run one command as a real person without disturbing a bot setup:
OCTO_TOKEN=$UK_KEY octo-cli drive space list
A stored profile (octo-cli auth login) takes precedence over both. Do not create a drive-only profile — there is no such concept.
The token kind decides which identity the backend sees, and the CLI routes the request accordingly:
| token | acts as | mount |
|---|---|---|
uk_… |
the real person who owns the key | /v1/user/drive/* |
bf_… |
the User Bot | /v1/bot/drive/* |
app_… |
the App Bot | /v1/bot/drive/* |
Any other credential fails locally with TOKEN_KIND_NOT_ALLOWED (exit 2) — switch credentials, don't retry.
A bot has no implicit access: to touch a shared space it must be added as a member, exactly like a person. If a bot gets permission_denied, add it with drive member add. An app_… token may also lack a resolvable space entirely; that surfaces as a 401 (exit 3) from the server, and the fix is a bf_… or uk_… credential.
Drive never sends X-Space-Id — the tenant comes from the verified identity.
2. Ids — copy them, never compute with them
| id | shape | produced by | consumed by |
|---|---|---|---|
| drive space id | opaque string, e.g. personal:<octo-space>:<uid> or shared:<uuid> |
space create/list/get/ensure-personal → .data.id |
--space-id, --target-space-id, positional <space-id> |
| drive file id | decimal string | browse, folder create, upload file, doc mount, im-transfer create → .data.id |
<file-id>, --parent-id ("0" = space root) |
doc_id / doc_space_id |
opaque strings | doc candidates, doc list, file get |
document links only |
share_id vs share_token |
opaque strings | share create, share blob-create, share list |
share_id → share revoke; the token is embedded in share_url |
invite_id vs invite_token |
opaque strings | invite create, invite list |
invite_id → invite revoke; invite_token → invite accept |
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.
- 12d ago First seen · 258 lines · 55 tokens per session scan A 8004cbd9dafc
octo-drive is a skill published in the GitHub repository Mininglamp-OSS/octo-cli (773 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 4,645 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
xberg
Extract text, tables, metadata, and images from 97+ document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg CLI.
haypile
Search the user's local documents (PDF, docx, pptx, markdown, text, HTML, mbox email) through Haypile, a local search daemon. Use when the user asks what their files say, wants passages from contracts, papers, or notes, or wants a folder indexed for search. Every result carries a file and page citation. Runs entirely…
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…
gws-sheets
Google Sheets: Read and write spreadsheets.
pptx
Create/edit/inspect/verify slide decks and PPTX presentations.