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-create-agentnpx skills add jmagly/aiwg --skill devkit-create-agentgit 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 | $0.00020 | $0.01276 |
| Opus 5 | $0.00010 | $0.00638 |
| Sonnet 5 | $0.00004 | $0.00255 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
devkit-create-agent 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 3d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create AIWG Agent
Create a new agent with AI assistance to define expertise, workflow, and capabilities.
Follows: Agent Design Bible - 10 Golden Rules for production-grade agents.
Research Foundation: REF-001 (Bandara et al.), REF-002 (Roig 2025) failure archetype prevention.
Usage
/devkit-create-agent <name> --to <target> [options]
Arguments
| Argument | Required | Description |
|---|---|---|
| name | Yes | Agent name (kebab-case recommended) |
Required Options
| Option | Description |
|---|---|
| --to | Target addon or framework |
Optional Options
| Option | Description |
|---|---|
| --template | Agent template: simple (default), complex, orchestrator |
| --interactive | Enable interactive mode with guided questions |
Templates
Templates are in ~/.local/share/ai-writing-guide/templates/agent-scaffolding/.
simple (default)
Single-purpose, focused agent with minimal structure (Rule 1: Single Responsibility).
- Best for: Utility agents, single-task specialists
- Model: haiku (efficiency tier)
- Tools: Read, Write (Rule 2: Minimal Tools)
complex
Full reasoning agent with all safeguards including failure archetype prevention.
- Best for: Subject matter experts, reviewers, analysts
- Model: sonnet/opus (based on complexity)
- Tools: Read, Write, Grep (Rule 2: 0-3 tools)
- Includes: Grounding, uncertainty handling, recovery protocol
orchestrator
Multi-agent coordination with workflow patterns and agent assignment tables.
- Best for: Workflow coordinators, phase managers
- Model: opus (Rule 8: reasoning tier for coordination)
- Tools: Task only (Rule 2: single tool for delegation)
validator
Read-only validation agent that doesn't modify state.
- Best for: Quality gates, compliance checks, code review
- Model: haiku/sonnet
- Tools: Read, Grep (read-only)
Interactive Mode
When --interactive is specified, I will ask:
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.
- 3d ago First seen · 178 lines · 20 tokens per session scan A e5608549c571
devkit-create-agent is a skill published in the GitHub repository jmagly/aiwg (205 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 1,276 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
hunt
Compose a guided or automatic shift from the ready catalog, then review it first or run it directly under one time budget. Use when the owner wants to choose jobs or let Nightshift find the highest-value applicable work.
archive
File the finished part of the run state into a dated archive — shipped items, research, opportunities, the rotated journal, and handled snags. The live files stay lean; the facts stay on disk.
doctor
Read-only Nightshift diagnosis — workspace, rules, markers, session, process lease, watchman, deadline, and classified next actions. Use when a shift looks wrong, recovery is unclear, or the owner asks what Nightshift sees. Never repairs by being invoked.
import-issues
Stage explicitly selected GitHub issues onto the drafting table as quoted source. Never searches, never writes back to GitHub, never installs gh.
purge
Permanently delete this project's Nightshift state. Does not uninstall the plugin.
stop
Issue a stop-work order — pause the shift immediately, leaving unfinished items open.