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-filesgit 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-files)<a href="https://agentmods.dev/skills/mininglamp-oss/octo-cli/octo-files"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-cli/octo-files/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-files"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-cli/octo-files.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 Tool Misuse · line 45 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Data Exfiltration · line 58 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00043 | $0.01648 |
| Opus 5 | $0.00022 | $0.00824 |
| Sonnet 5 | $0.00009 | $0.00330 |
| Haiku 4.5 | $0.00004 | $0.00165 |
Grade A, and why
octo-files scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
octo-cli file download /chat/2026/05/abc123.png --jq '.data.url' | xargs curl -o out.png How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
octo-files — file I/O and bot housekeeping
Two small domains are covered here because they share a base URL ($OCTO_API_BASE_URL/v1/bot/*) and are usually needed together:
file— 4 ops, no bot-kind restrictionsbot— 6 ops, no bot-kind restrictions
1. File operations
octo-cli file upload --file ./report.pdf [--type chat] [--path subdir/]
octo-cli file download <path> --format json > saved.bin # <path> = storage key (no bucket prefix), see note below
octo-cli file credentials --filename report.pdf
octo-cli file presigned --filename report.pdf --fileSize 1048576 # --fileSize (bytes) is REQUIRED
upload — multipart form
Unlike every other command, file upload sends a multipart multipart/form-data body, not JSON. The --file flag is required and names a local path; --type (default chat) and --path become form text fields. Promoted body flags declared in the spec go in as text fields alongside the binary.
The response envelope carries the returned file descriptor under data — use it to build attachment references in message send.
download — returns a presigned URL
file download <path> issues a GET. The backend responds with a 302 redirect to the storage tier. The CLI does not stream raw bytes — instead it returns a JSON envelope containing the presigned URL:
octo-cli file download /chat/2026/05/abc123.png
# → {"ok":true,"data":{"url":"https://s3.../abc123.png?...","status":302,"content_type":"image/png"}}
To actually fetch the file, use the URL from the response:
octo-cli file download /chat/2026/05/abc123.png --jq '.data.url' | xargs curl -o out.png
Direct-to-S3 uploads
For files too large for multipart, ask the backend for a presigned target and upload directly:
size=$(stat -f%z big.zip 2>/dev/null || stat -c%s big.zip) # fileSize in bytes (REQUIRED; no padding)
cred=$(octo-cli file presigned --filename big.zip --fileSize "$size")
url=$(jq -r '.data.uploadUrl' <<<"$cred")
ctype=$(jq -r '.data.contentType' <<<"$cred")
cdisp=$(jq -r '.data.contentDisposition // empty' <<<"$cred")
curl -X PUT -T big.zip -H "Content-Type: $ctype" ${cdisp:+-H "Content-Disposition: $cdisp"} "$url"
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.
- 13d ago First seen · 126 lines · 43 tokens per session scan A ee1350e7affd
octo-files is a skill published in the GitHub repository Mininglamp-OSS/octo-cli (773 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 1,648 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gh-skill
Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.
gh
Patterns for invoking the GitHub CLI (gh) from agents. Covers structured output, pagination, repo targeting, search vs list, gh api fallback.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
printing-press-score
Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side.
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…