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 agentmods add skills/jmagly/aiwg/devkit-validatenpx skills add jmagly/aiwg --skill devkit-validategit clone --depth 1 https://github.com/jmagly/aiwgWhat 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 | $0.00015 | $0.01018 |
| Opus 5 | $0.00008 | $0.00509 |
| Sonnet 5 | $0.00003 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
devkit-validate 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 2d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate AIWG Package
Validate the structure and manifest of an addon, framework, or extension.
Usage
/devkit-validate <path> [options]
Arguments
| Argument | Required | Description |
|---|---|---|
| path | Yes | Path to addon, framework, or extension |
Options
| Option | Description |
|---|---|
| --fix | Attempt to auto-fix common issues |
| --verbose | Show detailed validation output |
What It Validates
Manifest Validation
-
manifest.jsonexists - Required fields present: id, type, name, version, description
- Type is valid: addon, framework, or extension
- For extensions:
requiresfield specifies valid parent framework - All referenced agents exist in agents/ directory
- All referenced commands exist in commands/ directory
- All referenced skills exist in skills/ directory
- All referenced templates exist in templates/ directory
Structure Validation
- Directory structure matches type expectations
- README.md exists
- Entry directories exist if specified
- No orphaned files (files not in manifest)
Content Validation
- Agent files have valid frontmatter (name, description, model, tools)
- Command files have valid frontmatter (name, description, args)
- Skill directories have SKILL.md with required fields
Extension-Specific Validation
- Parent framework exists
- Extension is in parent's extensions/ directory
-
requiresfield matches parent location
Examples
# Validate addon
/devkit-validate agentic/code/addons/aiwg-utils
# Validate framework
/devkit-validate agentic/code/frameworks/sdlc-complete
# Validate extension
/devkit-validate agentic/code/frameworks/sdlc-complete/extensions/gdpr
# Validate with auto-fix
/devkit-validate agentic/code/addons/my-addon --fix
# Verbose output
/devkit-validate . --verbose
Output Format
Success
✓ Validating: agentic/code/addons/aiwg-utils
Type: addon
Version: 1.1.0
✓ Manifest: Valid
- id: aiwg-utils
- agents: 1 (1 found)
- commands: 10 (10 found)
- skills: 2 (2 found)
✓ Structure: Valid
- agents/: OK
- commands/: OK
- skills/: OK
✓ Content: Valid
- Agent frontmatter: OK
- Command frontmatter: OK
- Skill definitions: OK
═══════════════════════════════
VALIDATION PASSED
═══════════════════════════════
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.
- 2d ago First seen · 163 lines · 15 tokens per session scan A 8a391eaf7446
devkit-validate is a skill published in the GitHub repository jmagly/aiwg (205 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 1,018 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
nightshift
Run an accountable autonomous shift — work a punch list to completion, evolve a product from research, park decisions instead of asking, and leave receipts. Use when the user wants to work through a todo list autonomously, spend remaining agent usage, run overnight, polish or improve a product, research competitors…
role-dev
Use when exactly one approved work package (WORK card) should be implemented — including as a DEV subagent in autonomous-loop. Not for scope decisions, reviews, or when no approved card exists.
autopilot
Full autonomous execution from idea to working code.
graph
Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
deep-interview
Socratic deep interview with mathematical ambiguity gating before explicit execution approval.