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 IsaiaScope/ai --skill iso-configgit clone --depth 1 https://github.com/IsaiaScope/aiWrote 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/isaiascope/ai/iso-config)<a href="https://agentmods.dev/skills/isaiascope/ai/iso-config"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-config/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/isaiascope/ai/iso-config"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-config.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 | $0.00000 | $0.01781 |
| Opus 5 | $0.00000 | $0.00890 |
| Sonnet 5 | $0.00000 | $0.00356 |
| Haiku 4.5 | $0.00000 | $0.00178 |
Grade B, and why
iso-config scanned grade B 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
iso_pkg_install # -> "brew install" | "sudo apt-get install -y" | "sudo dnf install -y" How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iso-config
Owns the Iso config and the library every other iso-* skill reads it through.
Invocation: /iso-config [init | show | doctor]. Default is show.
| Command | What it does |
|---|---|
init |
Writes ~/.config/iso/iso.json seeded with the defaults. Refuses to overwrite. |
show |
Prints which scope files exist, then the merged document. |
doctor |
Validates the overlay, sweeps prerequisites, checks the skill dirs and the tracker hooks, records the readiness stamp. |
All three run scripts/config.sh. This file describes the surface; it holds no logic.
Scopes
~/.config/iso/iso.json describes you — tracker, terminal, identity, agent
data. docs/iso/config.json in a repository describes that repository, and
may carry branches, paths and test only. Repo wins per key, not per file.
An overlay is meant to be tiny: only the values that differ from the global ones, which for most repositories is a handful.
test.command is the odd one out, and belongs to the repository for a reason a
global value could not serve — it is the shell command that proves this
repository still works. /iso-review runs it between phases and undoes a phase
that turns it red. Unset (the default) means no gate: phases still run, and
nothing checks them.
A key the overlay is not allowed to carry is a hard error naming the key, never a silent fall-through to global. A typo in a five-line file must not behave like a correct file that changed nothing.
Reading config from another skill
Resolve the library relative to your own script, never through $HOME/.claude —
that path is correct under one of the four install topologies and silently
wrong under the rest.
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
. "$HERE/../../iso-config/scripts/lib/sibling.sh"
. "$(iso_sibling iso-config scripts/lib/config.sh)"
development=$(iso_config_get branches.development)
Telling a user how to install something
No iso-* skill names a package manager. config.sh exports the one this
machine actually has, so a hint stays runnable off macOS — brew install jq
handed to a Debian reader is advice they cannot follow, and it read as correct
here for as long as only one machine ever ran these skills.
What ships with it
11 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.
- scripts/config.sh 5.4 KB runs code
- scripts/lib/branch.sh 5.8 KB runs code
- scripts/lib/branch.test.sh 4.6 KB runs code
- scripts/lib/config.sh 6.5 KB runs code
- scripts/lib/config.test.sh 7.6 KB runs code
- scripts/lib/sibling.sh 1.1 KB runs code
- scripts/lib/sibling.test.sh 2.4 KB runs code
- scripts/lib/track.sh 2.1 KB runs code
- scripts/lib/track.test.sh 5.7 KB runs code
- scripts/prereq.sh 2.9 KB runs code
- scripts/prereq.test.sh 2.5 KB runs code
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.
- 9d ago First seen · 147 lines · 0 tokens per session scan B ee5d97b2038a
iso-config is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,781 tokens. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-architecture-planner
Use when designing an autonomous agent, planning agent architecture, building a scheduled automation, or creating a Claude Code agent workflow. Triggers: 'design an agent', 'build an automation', 'agent architecture', 'automate this workflow', 'create a scheduled agent', 'shell script agent'.
remotion-upgrade
Upgrade Remotion, and related packages.
agent-curator
Deep curation of a single agent definition through structured human conversation. Coordinates knowledge research, persona refinement, tooling optimization, and instruction quality improvement. One agent at a time, with due care.
remotion-docs
Search and fetch Remotion documentation pages.
agent-browser
Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…
agent-builder
Build custom AI agents in Claude Code from a user's problem statement. This skill analyzes the user's use case, asks smart clarifying questions, researches the internet for similar agents (GitHub repos, blogs, Claude Code community patterns), and then architects and builds production-ready Claude Code agents …