agentmods.dev

external-references

external-references is a skill for Claude Code, Codex from i9wa4/dotfiles. It costs 69 tokens per session (461 once invoked), scanned A, original, MIT.

Routing guidance for consulting inactive reference packs about services such as AWS, Azure, Google Cloud, Terraform, Databricks, dbt, and Obsidian.

In plain words
What is it for?
Use it to inspect local reference files, look up provider syntax, answer promotion questions, and decide whether a reference pack should become active.
Why use it?
It helps find provider-specific instructions without loading broad collections of material into the active setup or enabling them by accident.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

not rated 12repo changed 1mo ago A scan 69 tokens original MIT

Good fit Use it to inspect local reference files, look up provider syntax, answer promotion questions, and decide whether a reference pack should become active.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/i9wa4/dotfiles/external-references
View source ↗ i9wa4/dotfiles
Install

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.

Any agent
npx skills add i9wa4/dotfiles --skill external-references
Clone the repo
git clone --depth 1 https://github.com/i9wa4/dotfiles

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for external-references

README.md
[![agentmods](https://agentmods.dev/badge/skills/i9wa4/dotfiles/external-references/github.svg)](https://agentmods.dev/skills/i9wa4/dotfiles/external-references)
Your own site
<a href="https://agentmods.dev/skills/i9wa4/dotfiles/external-references"><img src="https://agentmods.dev/badge/skills/i9wa4/dotfiles/external-references/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.

agentmods 80×15 button for external-references

Your own site · 80×15
<a href="https://agentmods.dev/skills/i9wa4/dotfiles/external-references"><img src="https://agentmods.dev/badge/skills/i9wa4/dotfiles/external-references.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 461 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00461
Opus 5.5 $0.00028 $0.00184
Sonnet 5.5 $0.00014 $0.00092
Haiku 4.5 $0.00007 $0.00046

Measured 1mo ago against content hash 04e982618ac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

skills/external-references/SKILL.md · 48 lines

What it actually says

External References

Dormant provider-pack references live under ~/.local/share/skills. Direct reads from ~/.local/share/skills/<skill-name>/* need no promotion; promote only when the user asks to make a pack active/invokable.

1. Workflow

  1. Read matching bodies under ~/.local/share/skills/<skill-name>.
  2. Enumerate available reference skill names from ~/.local/share/skills/.i9wa4-agent-skills-reference-only.manifest when the generated name is unclear.
  3. Use nix/home-manager/agents/shared/agent-skills.nix referenceOnlySources only when the generated tree is missing or source verification is needed.
  4. Prefer local owner skills for guardrails: data-platform, programming, or dotfiles.
  5. Promote only on an explicit active-provider-pack request.

2. Dormant Packs

cloudflare-skills, databricks-official, dbt, azure, google, aws, hashicorp-terraform, googleworkspace-cli, and streamlit. Use active security-audit for Cloudflare security audits.

3. Direct Read Example

For Terraform, read ~/.local/share/skills/terraform-style-guide/SKILL.md and use the manifest for related Terraform names. hashicorp-terraform is an inventory group, not necessarily a directory.

4. Promotion Rules

For Claude, add a source through i9wa4.agentSkills.extraSources or an explicit repo decision. For Codex, also update codexMinimalSourceNames and codexMinimalAllowlist.

Files

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.

Changes

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.

  1. 1mo ago Changed · -2 lines · -14 tokens per session 04e982618ac6
  2. 1mo ago Changed · +6 lines · -21 tokens per session 7916cc10ce4b
  3. 1mo ago Changed · +1 lines · +6 tokens per session c04c5d46b767
  4. 2mo ago First seen · 43 lines · 98 tokens per session scan A c97e20ad8860

Subscribe to this mod's changes

external-references is a skill published in the GitHub repository i9wa4/dotfiles (12 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 461 once invoked, about $0.0003 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 2026-08-30.

dotfiles
Related

Other skills, from other repositories

merge-pr

Merge a pull request with status checks, squash merge, and branch cleanup. Handles worktree contexts.

joshukraine/dotfiles · 23 tokens

bootstrap-prd

Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.

joshukraine/dotfiles · 25 tokens

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, read exact RGBA via NSBitmapImageRep, and synthesize keystrokes, chords, clicks and drags with CGEventPost. Use for…

natsukium/dotfiles · 113 tokens

audit

Repo audits, one mode or all (codebase, docs, process, perf, tests, threat-model, motion, SEO, debt). Triggers "audit the codebase", "full audit", "perf audit", "audit the tests", "threat model", "motion audit", "seo audit", "debt ledger".

darkroomengineering/cc-settings · 69 tokens

self-review

Deliberate end-to-end review pass over a completed change, applying the laziness ladder. Invoke when the user asks for a review, or when orchestrating one. Not a routine step after every edit.

fredrikaverpil/dotfiles · 45 tokens

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…

sebastienrousseau/dotfiles · 137 tokens