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 tonyfadel23/skill-inspector --skill build-my-skillgit clone --depth 1 https://github.com/tonyfadel23/skill-inspectorWrote 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/tonyfadel23/skill-inspector/build-my-skill)<a href="https://agentmods.dev/skills/tonyfadel23/skill-inspector/build-my-skill"><img src="https://agentmods.dev/badge/skills/tonyfadel23/skill-inspector/build-my-skill/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/tonyfadel23/skill-inspector/build-my-skill"><img src="https://agentmods.dev/badge/skills/tonyfadel23/skill-inspector/build-my-skill.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 | $0.00082 | $0.01731 |
| Opus 5 | $0.00041 | $0.00865 |
| Sonnet 5 | $0.00016 | $0.00346 |
| Haiku 4.5 | $0.00008 | $0.00173 |
Grade A, and why
build-my-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
build-my-skill — Skill Tree Builder
Step 0 — Setup
Locate Builder
Find where the skill-inspector package is installed:
BUILDER_DIR=$(find "$(pwd)" ~/.agents/skills -path '*/skill-inspector/skill_inspector/builder.py' -type f 2>/dev/null -exec dirname {} \; | head -1)
if [ -z "$BUILDER_DIR" ]; then
BUILDER_DIR=$(find "$(pwd)" -path '*/skill_inspector/builder.py' -type f 2>/dev/null -exec dirname {} \; | head -1)
fi
echo "Builder found at: $BUILDER_DIR"
Ensure Dependencies
python3 -c "import yaml" 2>/dev/null || pip3 install --user "PyYAML>=6.0"
Step 1 — Understand the Goal
Ask the user to describe what they want to build. Gather:
- Goal: What is the end-to-end outcome?
- Inputs: What data, files, or context does it need?
- Outputs: What deliverables should it produce?
- Constraints: Time, quality thresholds, human review points?
- Tools: What external tools or APIs are needed?
If the user is unsure, suggest one of these common patterns:
- Research Pipeline: fetch → analyze → synthesize → deliver
- Goal to Prototype: context → research → evaluate → diverge → converge → refine → deliver
- Quality Audit: scan → check → report → fix → verify
- Content Generation: brief → draft → review → iterate → publish
Step 2 — Design the Tree
Based on the user's goal, design the skill tree using these node types.
Read references/node-types.md for the full reference.
Available Node Types
| Type | Use When |
|---|---|
executor |
Agent takes action — writes files, generates content |
tool |
External tool invocation — WebSearch, APIs, bash commands |
subagent |
Spawn a dedicated sub-agent with its own context and tools |
context_loader |
Dynamically inject context from files or URLs |
signal_gate |
Gate on computed metrics with pass/fail thresholds |
improvement_loop |
RALPH-style iterate until quality threshold met |
diverge |
Fork into parallel branches for multi-angle analysis |
converge |
Synthesize parallel outputs with a merge strategy |
router |
Conditional branching based on computed values |
gate |
Human approval checkpoint |
file_io |
Read or write specific files |
What ships with it
2 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.
- 11d ago First seen · 207 lines · 82 tokens per session scan A af1aa469cc96
build-my-skill is a skill published in the GitHub repository tonyfadel23/skill-inspector (2 stars, last pushed 5mo ago), licensed MIT. It adds 82 tokens to every session and 1,731 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
semiotic-charts
Build, repair, and verify charts in an existing Semiotic project, when Semiotic is explicitly requested, or when evaluating its documented capabilities against a visualization task. Preserve the project's dependency and runtime constraints; routine changes in another charting stack and tasks without a chart do not…
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
experiment-tracking-swanlab
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.
data_analyst
Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.
iflytek-text-proofread
A tool that checks Chinese writing through iFlytek’s official document-proofreading service. It looks for spelling, punctuation, wording, factual, terminology, and sensitive-content problems.