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-readmegit 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-readme)<a href="https://agentmods.dev/skills/isaiascope/ai/iso-readme"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-readme/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-readme"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-readme.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 | $0.00104 | $0.01320 |
| Opus 5 | $0.00052 | $0.00660 |
| Sonnet 5 | $0.00021 | $0.00264 |
| Haiku 4.5 | $0.00010 | $0.00132 |
Grade A, and why
iso-readme scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Icon realism:** use only a `logo=` slug you've verified. Look up brands at simpleicons.org; if absent, try React Icons `ri:Si<Name>` (e.g. OpenAI → `ri:SiOpenai`); only then fall back to `logo=false` + an emoji in th How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iso-readme
Write a fresh README or refine an existing one to the house look defined in STYLE.md, then commit only the README file(s) and push. Runs in any repo, under Claude Code or Codex.
Read STYLE.md before writing — it is the single source of truth for badges, layout, voice, and writing rules (each rule carries a stable anchor like B4/L1). Before committing, clear every applicable gate in CHECKLIST.md — the Definition of Done.
Input
/iso-readme [path]
- path given — a README file or a directory (use its
README.md). - no arg — target the repo-root
README.md. If the repo is a monorepo, offer to also scan subdirs that carry their own manifest (apps/*,packages/*); do not scan them unprompted.
Step 1: Detect context
Pick the layout (see STYLE.md "Layouts by context"):
| Signal | Context | Layout |
|---|---|---|
A SKILL.md sits in the same dir, or path is skills/<name>/README.md |
skill | skill layout |
| Repo-root README, or an application dir | root / app | centered + badges |
| Manifest declares a published package (name+version, library not app) | lib / pkg | lib layout |
Ambiguous → top-level defaults to root/app; a dir with SKILL.md is a skill; ask only if still unclear.
Step 2: Detect stack (stack-agnostic)
Parse whatever manifest exists to derive badge signals:
| Manifest | Stack |
|---|---|
package.json |
node/TS/JS; frameworks from dependencies (next, react, express…) |
pyproject.toml / setup.py / requirements.txt |
python; framework from deps (django, fastapi…) |
Cargo.toml |
rust |
go.mod |
go |
composer.json |
php |
Gemfile |
ruby |
| none | docs-only → license badge only (if LICENSE exists), or no badges |
Step 3: Write or refine
- README missing → generate fresh from the matching STYLE.md skeleton.
- README exists → refine: preserve all real content (install steps, env vars, credits, commands) — restyle layout + badges only. Never invent features or commands.
- Derive badges from Step 2, curate to 3–6 identity badges (primary lang/runtime · 1–2 defining frameworks · license) using the STYLE.md hex table. Add a missing tech as a new row in STYLE.md.
- Icon realism: use only a
logo=slug you've verified. Look up brands at simpleicons.org; if absent, try React Iconsri:Si<Name>(e.g. OpenAI →ri:SiOpenai); only then fall back tologo=false+ an emoji in the label. A miss renders blank. Don't hand-wave hex-table slugs as "done" — the Step 4 DoD curl-verifies everylogo=badge (gate U1), so a typo or table-rot surfaces regardless. See STYLE.md "Icons". - Pick the structure before writing the content [V11]: a table only holds values that fit on one line. The moment a column would carry a sentence —
Why,Does,Notes— it is a bullet list with a bold lead term, and any short column becomes a leading marker (- 🔒 **\file`** — sentence.`). GitHub sizes columns to their widest cell, so the prose column starves its neighbours and the narrow cell is what visibly breaks. - Format/quality:
.svg(crisp, GitHub-safe),logoColoras bare hex (fff, neverwhite), light brand colors → darkbg hex+ brightlogoColor. Measure real language bytes before picking language badges; don't assume.
What ships with it
3 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.
- 9d ago First seen · 82 lines · 104 tokens per session scan A 40ac85dbd6e6
iso-readme is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed 5d ago), licensed MIT. It adds 104 tokens to every session and 1,320 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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 …