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 richfrem/agent-plugins-skills --skill hf-initgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/hf-init)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/hf-init"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/hf-init/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/richfrem/agent-plugins-skills/hf-init"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/hf-init.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 | $0.00024 | $0.00493 |
| Opus 5.5 | $0.00010 | $0.00197 |
| Sonnet 5.5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
hf-init 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 17d 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.
What it actually says
HuggingFace Initialization (hf-init)
Sets up credentials, connectivity, and dataset repository structure for HuggingFace persistence.
Contents
Critical Constraints
- Secret Hygiene: Tokens must be stored in shell profile (
~/.zshrc), NEVER committed to.envor Git. - Repository Structure: Enforces standard folder structure (
lineage/,data/,metadata/).
Quick start
Validate HuggingFace configuration without modifying remote repositories:
python3 scripts/hf_init.py --validate-only
Required Environment Variables
| Variable | Required | Description |
|---|---|---|
HUGGING_FACE_USERNAME |
Yes | HuggingFace account username |
HUGGING_FACE_TOKEN |
Yes | Hub API token (in shell profile) |
HUGGING_FACE_REPO |
Yes | Model repository name |
HUGGING_FACE_DATASET_PATH |
Yes | Dataset repository name |
HUGGING_FACE_TAGS |
No | Comma-separated discovery tags |
HUGGING_FACE_PROJECT_NAME |
No | Display name for dataset card |
Workflow
- Credential Validation: Verify presence of required environment variables.
- Connectivity Test: Run API probe to confirm read/write token privileges.
- Repository Setup: Initialize standard directory structure (
lineage/,data/,metadata/) on remote dataset. - Readiness Report: Output connection status and configured paths.
Verification
Confirm configuration and authentication validity:
python3 scripts/hf_config.py
References
- acceptance-criteria.md — Acceptance criteria and security validation for HuggingFace initialization.
- fallback-tree.md — Fallback protocol when credentials or variables are missing.
What ships with it
7 files 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.
- 17d ago Changed · -23 lines · -17 tokens per session 640b235b1ced
- 1mo ago First seen · 87 lines · 41 tokens per session scan A 91bfd80b5f28
hf-init is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 493 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
factory-handoff
Hand one exact agent-ready ticket to the central Factory runtime over the configured SSH forced-command boundary. Use when an operator asks to hand off an existing ticket or a prose request instead of implementing it in the current session.
ticket-spec
Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
review-my-team
Review a connected Paperclip team's agents, tasks, blockers and pending approvals when the user asks for a team summary or what needs attention.
ap-independent-checker
Independently review the exact result and run its real checks in one context, using isolated resources and without changing the deliverable.