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-ai-initgit 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-ai-init)<a href="https://agentmods.dev/skills/isaiascope/ai/iso-ai-init"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-ai-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/isaiascope/ai/iso-ai-init"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-ai-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 | $0.00089 | $0.03777 |
| Opus 5 | $0.00044 | $0.01888 |
| Sonnet 5 | $0.00018 | $0.00755 |
| Haiku 4.5 | $0.00009 | $0.00378 |
Grade B, and why
iso-ai-init 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **1c — Statusline** copy `templates/statusline.sh` → `~/.claude/statusline-command.sh`, then **safely merge** the `statusLine` key into `~/.claude/settings.json` (read-modify-write via node: preserves all other keys, s How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iso-ai-init
Set up IsaiaScope AI defaults. Some steps are global (run anywhere, even outside a git repo); others are repo-scoped (run only inside a git working tree). The manifest-driven runner decides which apply — being outside a repo is not an error, it just skips the repo-scoped steps.
| Scope | Step | Runs |
|---|---|---|
| global | Caveman (ultra + shrink + statusline) | always |
| global | MCP shrink (allowlist) | always |
| global | headroom (context compression) install + Claude/Codex wiring | always |
| global | ponytail (code-minimalism) install + Claude/Codex wiring | always |
| repo | Graphify CLI install + /graphify wiring |
only inside a git repo |
Deterministic orchestration lives in scripts/init-runner.js, driven by steps.json. Each enabled Init step points at an independently owned script in templates/. Resolve paths against the skill base directory (where this SKILL.md lives), referred to below as <skill-base-dir>.
Step 0 — Deterministic Init run
Run the manifest-driven runner first:
node <skill-base-dir>/scripts/init-runner.js
The runner evaluates whether the current directory is a git repo, filters repo-scoped Init steps outside git repos, executes enabled steps in steps.json order, and prints the summary. Add or remove deterministic Init steps by editing steps.json plus the step script, not by rewriting this skill.
After the runner completes, continue to Step 3b only if the runner ran inside a git repo.
Implementation detail — Gate
The old gate remains as human-readable implementation detail and dependency documentation. It does a hard node check (node is required by caveman install, the MCP-shrink script, and the statusline merge — fail fast here, not mid-step), then prints IN_GIT_REPO=true|false on its first line plus a human-readable plan. Do not use it as the primary ordering interface; scripts/init-runner.js and steps.json own deterministic ordering and scope filtering.
What ships with it
15 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.
- README.md 8.5 KB
- scripts/init-runner.js 2.0 KB runs code
- scripts/init-runner.test.js 2.0 KB runs code
- steps.json 650 B
- templates/caveman-config.json 27 B
- templates/caveman-init.sh 4.4 KB runs code
- templates/graphify-init.sh 9.9 KB runs code
- templates/headroom-init.sh 4.4 KB runs code
- templates/headroom-init.test.js 2.7 KB runs code
- templates/ponytail-init.sh 2.8 KB runs code
- templates/ponytail-init.test.js 1.8 KB runs code
- templates/preflight-gate.sh 1.5 KB runs code
- templates/shrink-known-mcps.js 11 KB runs code
- templates/statusline.sh 3.5 KB runs code
- templates/statusline.test.js 2.7 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 · 164 lines · 89 tokens per session scan B 115dee4475d4
iso-ai-init is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 3,777 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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 …