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 updategit 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/update)<a href="https://agentmods.dev/skills/jmagly/aiwg/update"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/update/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/update"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 20 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 32 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 42 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 60 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 67 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 138 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00020 | $0.01391 |
| Opus 5.5 | $0.00008 | $0.00556 |
| Sonnet 5.5 | $0.00004 | $0.00278 |
| Haiku 4.5 | $0.00002 | $0.00139 |
Grade A, and why
update 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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIWG Update
You update AIWG through its canonical install-aware command and re-deploy all installed frameworks from the registry.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "refresh frameworks" → run
aiwg update - "redeploy everything" → run
aiwg update --all - "get the latest aiwg" → run
aiwg update - "reinstall my frameworks" → run
aiwg update --skip-check - "what would update change" → run
aiwg update --dry-run
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| Update request | "update aiwg" / "upgrade aiwg" | Run aiwg update |
| Refresh request | "refresh frameworks" | Run aiwg update |
| Full redeploy | "redeploy everything" | Run aiwg update --all |
| Dry run | "what would update change" | Run aiwg update --dry-run |
| Provider-scoped | "update for copilot" | Run aiwg update --provider copilot |
| Skip version check | "just redeploy my frameworks" | Run aiwg update --skip-check |
Behavior
When triggered:
-
Extract intent:
- Should this update everything (
--all) or only the currently installed frameworks (default)? - Is a specific provider mentioned?
- Is this a preview only (
--dry-run) or should changes be applied? - Is the user asking to redeploy without updating the package (
--skip-check)?
- Should this update everything (
-
Run the appropriate command:
# Default: check for updates + re-deploy installed frameworks aiwg update # Re-deploy all frameworks (equivalent to `aiwg use all`) aiwg update --all # Preview what would be updated (no changes) aiwg update --dry-run # Re-deploy to a specific provider aiwg update --provider copilot # Skip version check, only re-deploy aiwg update --skip-check # Combine flags aiwg update --all --provider cursorExecution sequence:
- Detect the active distribution and update safely (unless
--skip-check)- full
aiwgnpm package: preservestable,next, ornightly - lightweight
@aiwg/cli: follow its signed web resource channel without replacing it with the full package - source/dev checkout: print the supported Git/build workflow without overwriting the checkout
- full
- Read
.aiwg/frameworks/registry.jsonto find installed frameworks - Re-deploy each installed framework via
aiwg use <framework> [--provider <name>] - Print update summary with per-framework pass/fail status
- Detect the active distribution and update safely (unless
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.
- 1mo ago First seen · 167 lines · 20 tokens per session scan A 04c96af3c510
update is a skill published in the GitHub repository jmagly/aiwg (224 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,391 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
rally
Orchestrating multi-session parallel execution via Claude Code Agent Teams API and Codex CLI Subagents — launch, manage, coordinate concurrent tasks. Use when parallel work is needed.
void
Verifying YAGNI, cutting scope, and proposing complexity reductions. A 'subtraction' agent questioning the justification for every feature, dependency, doc, and config. Does not write code.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) development methodology with multi-agent orchestration. Use when running a structured spec-to-code workflow or decomposing a feature through the SPARC phases.
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows. Use when piping output between agents/tools as streaming JSON or building a sequential transform pipeline.
hive-mind-advanced
Queen-led collective-intelligence coordination with consensus mechanisms and persistent shared memory. Use when orchestrating a large swarm of agents under a lead coordinator, building consensus across agents, or maintaining durable cross-agent memory.
session-handoff-packager
Packages session work into a local handoff document for continuity. Use for: session summary, handoff, save what we did, continue next time.