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-testnpx skills add jmagly/aiwg --skill devkit-testgit 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 | $0.00010 | $0.01227 |
| Opus 5 | $0.00005 | $0.00613 |
| Sonnet 5 | $0.00002 | $0.00245 |
| Haiku 4.5 | $0.00001 | $0.00123 |
Grade A, and why
devkit-test 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test AIWG Package
Run comprehensive tests on an AIWG package to verify structure, functionality, and deployment readiness.
Process
1. Locate and Identify Package
Resolve the package path from $ARGUMENTS:
- If relative path, resolve from current directory
- If package name, look in addons/ and frameworks/
Identify package type from manifest.json:
"type": "addon"→ Addon tests"type": "framework"→ Framework tests"type": "extension"→ Extension tests
2. Run Structure Tests
Manifest Validation:
- manifest.json exists and is valid JSON
- Required fields present: id, type, name, version, description
- Entry paths exist and match actual directories
- Component arrays match actual files
Directory Structure:
- Expected directories exist (agents/, commands/, etc.)
- No orphaned files outside expected structure
- README.md exists and is non-empty
Component Files:
- All agents listed in manifest exist as .md files
- All commands listed in manifest exist as .md files
- All skills listed in manifest have SKILL.md
- All templates listed in manifest exist
3. Run Content Tests
Agent Validation: For each agent file:
- Valid YAML frontmatter with name, description, model, tools
- Model is valid (sonnet, opus, haiku)
- Tools list contains valid tool names
- Content sections present (Domain Expertise, Responsibilities, etc.)
Command Validation: For each command file:
- Valid YAML frontmatter with name, description
- Args defined with name and description
- Process section present
- No broken internal references
Skill Validation: For each skill:
- SKILL.md has valid frontmatter
- Trigger phrases defined
- Execution process documented
- References directory exists (if referenced)
4. Run Type-Specific Tests
Addon Tests:
- No
requiresfield (addons are standalone) - Can be deployed independently
Extension Tests:
-
requiresfield present and valid - Parent framework exists
- Located in correct extensions/ subdirectory
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 · 192 lines · 10 tokens per session scan A bbe182ccb6ca
devkit-test is a skill published in the GitHub repository jmagly/aiwg (205 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 1,227 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…
campaign-conductor
Run a project as an orchestrated campaign: Claude as conductor (Fable, or Opus when Fable is unavailable) dispatching a mixed fleet of workers, Claude Opus agents for UI/UX and design judgment, OpenAI Codex CLI workers for implementation and everything else. Use whenever the user says "start a campaign", "campaign…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
massgen-develops-massgen
Guide for using MassGen to develop and improve itself. This skill should be used when agents need to run MassGen experiments programmatically (using automation mode) OR analyze terminal UI/UX quality (using visual evaluation tools). These are mutually exclusive workflows for different improvement goals.
archon
Use when: User wants to run Archon workflows, CREATE workflows or commands, set up Archon, or manage Archon configuration. Triggers (run): "use archon to", "run archon", "archon workflow", "use archon for", "have archon", "let archon", "ask archon to". Triggers (create): "create a workflow", "write a workflow", "make…
massgen
Invoke MassGen's multi-agent system. Use when the user wants multiple AI agents on a task: writing, code, review, planning, specs, research, design, or any task where parallel iteration beats working alone.