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 shane9coy/Agent-Skill-Architecture-Guide --skill new-skill-buildergit clone --depth 1 https://github.com/shane9coy/Agent-Skill-Architecture-GuideWrote 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/shane9coy/agent-skill-architecture-guide/new-skill-builder)<a href="https://agentmods.dev/skills/shane9coy/agent-skill-architecture-guide/new-skill-builder"><img src="https://agentmods.dev/badge/skills/shane9coy/agent-skill-architecture-guide/new-skill-builder/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/shane9coy/agent-skill-architecture-guide/new-skill-builder"><img src="https://agentmods.dev/badge/skills/shane9coy/agent-skill-architecture-guide/new-skill-builder.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 | $0.00080 | $0.02599 |
| Opus 5 | $0.00040 | $0.01300 |
| Sonnet 5 | $0.00016 | $0.00520 |
| Haiku 4.5 | $0.00008 | $0.00260 |
Grade D, and why
new-skill scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
find .codex/skills .agents/skills skills -name "SKILL.md" 2>/dev/null || echo "No skills directory found" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "/tmp/${SKILL_NAME}-clone" How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Skill Installer & Scaffolder
Overview
This skill helps you install, create, and manage skills in your Codex-first .codex/skills/ or .agents/skills/ directory. It handles the full lifecycle: scaffolding new skills from scratch, installing skills from external sources, validating skill structure, and troubleshooting registration issues.
Workflow 1: Create a New Skill From Scratch
When the user wants to create a brand new skill:
-
Ask for details (if not provided):
- Skill name (lowercase, hyphenated, e.g.
api-tester) - What it should do (purpose)
- When it should trigger (contexts)
- Whether it needs scripts, references, or assets
- Skill name (lowercase, hyphenated, e.g.
-
Scaffold the folder structure:
SKILL_NAME="the-skill-name"
PROJECT_DIR="$(pwd)"
SKILL_DIR="${PROJECT_DIR}/.codex/skills/${SKILL_NAME}"
mkdir -p "${SKILL_DIR}"
mkdir -p "${SKILL_DIR}/scripts"
mkdir -p "${SKILL_DIR}/references"
mkdir -p "${SKILL_DIR}/assets"
- Generate the SKILL.md with proper frontmatter:
---
name: {skill-name}
description: "{What it does}. Use when {trigger conditions}. Handles {capabilities}."
---
# {Skill Title}
## Overview
{One paragraph purpose statement}
## Instructions
1. {Step-by-step instructions}
## Examples
### Example 1
**Input:** "{example user request}"
**Action:** {what the skill does}
**Output:** {expected result}
## Error Handling
- {How to handle failures}
## Notes
- {Caveats and edge cases}
-
Validate the skill (run Workflow 4 below)
-
Report back with the file tree and confirmation it's registered.
Workflow 2: Install a Skill From External Source
When the user provides a URL, GitHub repo, zip file, or raw markdown:
From a GitHub Repository URL
REPO_URL="$1"
SKILL_NAME="$2" # Extract from repo name if not given
SKILL_DIR=".codex/skills/${SKILL_NAME}"
# Clone just the skill content
git clone --depth 1 "${REPO_URL}" "/tmp/${SKILL_NAME}-clone"
# Find the SKILL.md
SKILL_FILE=$(find "/tmp/${SKILL_NAME}-clone" -name "SKILL.md" -type f | head -1)
if [ -z "$SKILL_FILE" ]; then
echo "ERROR: No SKILL.md found in repository."
echo "This repo may not be a valid AgentSkills package."
exit 1
fi
# Get the skill's parent directory (contains SKILL.md + siblings)
SKILL_SRC=$(dirname "$SKILL_FILE")
# Copy to .codex/skills/
mkdir -p "${SKILL_DIR}"
cp -r "${SKILL_SRC}/"* "${SKILL_DIR}/"
# Cleanup
rm -rf "/tmp/${SKILL_NAME}-clone"
echo "Installed ${SKILL_NAME} to ${SKILL_DIR}"
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.
- 10d ago First seen · 322 lines · 80 tokens per session scan D 14f976187187
new-skill is a skill published in the GitHub repository shane9coy/Agent-Skill-Architecture-Guide (17 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 2,599 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.