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 jmagly/aiwg --skill configgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/config)<a href="https://agentmods.dev/skills/jmagly/aiwg/config"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/config/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/jmagly/aiwg/config"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.01368 |
| Opus 5 | $0.00008 | $0.00684 |
| Sonnet 5 | $0.00003 | $0.00274 |
| Haiku 4.5 | $0.00002 | $0.00137 |
Grade A, and why
config 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 9d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Config
You manage the user-level AIWG configuration file. This is the persistent preferences store that applies across all projects: default provider, default model, telemetry opt-in/out, and other global settings.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "what's my default provider" → get subcommand for
provider - "turn off telemetry" → set subcommand for
telemetry - "where is the aiwg config file" → path subcommand
- "reset aiwg to defaults" → reset subcommand
- "open config in my editor" → edit subcommand
- "is my config valid" → validate subcommand
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| List all settings | "show my aiwg config" | Run aiwg config list |
| Read a value | "what's my default model?" | Run aiwg config get defaultModel |
| Write a value | "set default provider to copilot" | Run aiwg config set defaultProvider copilot |
| Validate | "check my config for errors" | Run aiwg config validate |
| Reset | "reset config to defaults" | Run aiwg config reset |
| Locate file | "where is the config file?" | Run aiwg config path |
| Open editor | "edit config" | Run aiwg config edit |
Behavior
When triggered:
-
Extract intent:
- Which subcommand:
list,get,set,validate,reset,path, oredit? - For
get/set: what is the key? Forset: what is the new value? - Is a custom config directory specified via
--config-dir?
- Which subcommand:
-
Resolve config directory (in order):
AIWG_CONFIGenvironment variable--config-dir <path>flag~/.aiwg/config.json~/.config/aiwg/config.json
-
Run the appropriate command:
# Show all configuration values aiwg config list # Read a specific key aiwg config get <key> # Write a value aiwg config set <key> <value> # Validate the config file aiwg config validate # Reset to factory defaults aiwg config reset # Show resolved config file path aiwg config path # Open in $EDITOR aiwg config edit # Use a custom config directory aiwg config list --config-dir /path/to/config
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.
- 9d ago First seen · 199 lines · 16 tokens per session scan A de2862ddc34b
config is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 1,368 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 2026-09-03.
Other skills, from other repositories
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
dos-dispatch
Plan and ship the next batch on one lane: run dos-next-up, acquire a lease with dos arbitrate, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with collision safety.
dos-class-cycle
Run one DOS plan-class lifecycle tick from the workspace [lifecycle] table: evaluate declared transitions, have a judge approve/defer them, write gated plan-meta edits, and log the cycle. Use when gardening plan lifecycle classes automatically.
pace-bridge
Use to bridge a confirmed Superpowers/native plan into PACEflow CHG/HOTFIX artifacts, create artifact-writer prompts, and mark the specific plan as synced.
task-copilot
Use when work should be tracked with tc, including creating PRDs, tasks, handoffs, logs, and work products, or when preserving detailed outputs outside the chat context.