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 agentmods add skills/i9wa4/dotfiles/external-referencesnpx skills add i9wa4/dotfiles --skill external-referencesgit clone --depth 1 https://github.com/i9wa4/dotfilesWrote 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/i9wa4/dotfiles/external-references)<a href="https://agentmods.dev/skills/i9wa4/dotfiles/external-references"><img src="https://agentmods.dev/badge/skills/i9wa4/dotfiles/external-references.svg" alt="Measured on agentmods" 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 | $0.00104 | $0.00467 |
| Opus 5 | $0.00052 | $0.00234 |
| Sonnet 5 | $0.00021 | $0.00093 |
| Haiku 4.5 | $0.00010 | $0.00047 |
Grade A, and why
external-references 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.
What it actually says
External References
Route external provider-pack requests to dormant references without activating
the broad packs by default. The generated reference tree is
~/.local/share/skills.
1. Workflow
- Inspect
nix/home-manager/agents/shared/agent-skills.nix. - Inspect matching skill bodies under
~/.local/share/skills/<skill-name>. - Use
referenceOnlySourcesas the dormant provider-pack inventory when the generated tree is missing or needs source-level verification. - Prefer local owner skills for guardrails:
data-platform,programming, ordotfiles. - For provider syntax not covered locally, inspect the pinned source or upstream docs without adding it to loader paths.
- Promote only on an explicit active-provider-pack request.
2. Dormant Packs
databricks-official: Databricks.dbt: dbt, dbt Labs.azure: Azure, Microsoft Foundry, Entra.google: Google Cloud, GCP, BigQuery, GKE, AlloyDB.aws: AWS, Amazon Web Services.hashicorp-terraform: Terraform, HashiCorp.obsidian: Obsidian, Bases, Canvas, Markdown vault workflows.streamlit: Streamlit apps.
3. Promotion Rules
For Claude, add a source through i9wa4.agentSkills.extraSources or make an
explicit repo decision to move it active. For Codex, also update both
codexMinimalSourceNames and codexMinimalAllowlist.
What ships with it
4 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.
- today Changed · +1 lines · +6 tokens per session c04c5d46b767
- 4d ago First seen · 43 lines · 98 tokens per session scan A c97e20ad8860
external-references is a skill published in the GitHub repository i9wa4/dotfiles (11 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 467 once invoked, about $0.0005 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
merge-pr
Merge a pull request with status checks, squash merge, and branch cleanup. Handles worktree contexts.
po-translate
Orchestrate English→Japanese translation of po/ja.po — classify, delegate translation/review to subagents, iterate until clean.
gui-debug
Verify a rendering or window-chrome change in any macOS GUI app unattended — find its CGWindowID via JXA, capture that window alone (with per-pixel alpha) using screencapture -l, and read exact RGBA via NSBitmapImageRep. Use for blur/opacity/corner-radius/glyph/color rendering bugs where a screenshot or pixel value is…
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
taskgo
Maintains a private Git-backed personal project and task control repository using concise current Markdown, derived Git history, ADRs, and status synchronization. Use when tracking tasks, updating project status (STATUS.md), managing ADRs, synchronizing tracker state, delegating tasks to external agents, or generating…