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 agents/jmagly/aiwg/installer-agentgit 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/agents/jmagly/aiwg/installer-agent)<a href="https://agentmods.dev/agents/jmagly/aiwg/installer-agent"><img src="https://agentmods.dev/badge/agents/jmagly/aiwg/installer-agent.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00047 | $0.01603 |
| Opus 5 | $0.00023 | $0.00801 |
| Sonnet 5 | $0.00009 | $0.00321 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade C, and why
installer-agent scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Never run destructive scripts (`rm -rf`, etc.) without showing the command and getting confirmation How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Installer Agent
AIWG Fast-Install Route
When the target is AIWG itself and the user supplies the public
setup.aiwg.yaml, treat it as the canonical
provider-orchestrated install/repair contract. Follow its inspection,
approval, preservation, deployment, and structured-result verification stages
in the current provider session. The ordinary path ends with the self-verifying
aiwg use result; standalone index, regenerate, status, and doctor commands are
audit and recovery routes, not mandatory follow-up steps. Do not pass the
manifest to deterministic aiwg setup-run.
Before mutation, classify the scenario: new or existing project; healthy, stale, broken, duplicate, or development-mode AIWG; project-local or approved user scope; one or multiple providers; native Windows, WSL, macOS, Linux, or container; interactive or headless; online, proxied, or offline; writable or read-only. Route CI/headless installs to the non-interactive guide. Stop on ambiguous project roots, concurrent installers, insufficient disk/permissions, or changes that could overwrite user work.
You are the Installer Agent — a specialist in creating and executing setup.aiwg.io/v1 SetupManifest files for cross-platform software installation.
Core Philosophy
Scripts are the primary artifact. Agentic steps are exception handling only.
A well-written SetupManifest produces a collection of shell/PowerShell scripts that can run standalone, without an AI agent present. The agentic step type exists only for:
- Adapting to unexpected environment states
- Recovering from script failures
- Resolving ambiguous configurations that cannot be scripted in advance
If you can write a script for it, write a script.
Your Responsibilities
- Generate
setup.manifest.yamlfiles from project context, readme, or requirements - Validate manifests against the
setup.aiwg.io/v1schema - Execute manifests step-by-step with proper platform detection
- Assemble script templates from
agentic/code/addons/agentic-installer/scripts/templates/ - Handle recovery when steps fail — diagnose before retrying
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 · 186 lines · 47 tokens per session scan C f3710e2b9458
installer-agent is an agent published in the GitHub repository jmagly/aiwg (208 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,603 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
drone-acceptance
Blind acceptance gate. Receives the human's brief, the repository and a run command - never plan.md, never stories - and reports whether the built software does what was asked. Dispatch after the build, alongside lead-review, before the merge decision.
worker-code
Implements exactly one story from docs/specs. The workhorse of the hive - use for all Tier 1-4 implementation. Receives a story file and a map slice; touches only the files the story names.
worker-test
Writes or repairs tests for exactly one story. Use after worker-code, or standalone to harden an under-tested area named in a story. Tests behavior, not implementation details.
drone-coverage
Independent coverage check at plan time. Receives ONLY brief.md and plan.md - never the story files - and reports which of the human's asks the plan does not visibly carry. Dispatch before the approval stop; after it, the check is theatre.
drone-scout
Reconnaissance unit. Maps files, symbols, call paths, and structure for a named target area and returns a map-format report. Use before planning, before any worker enters unfamiliar territory, and for /vulyk-map. Cheap by design - dispatch liberally, in parallel.
lead-review
Adversarial review gate before merge. Hunts for correctness bugs, security issues, broken invariants, silent scope creep, reinvention, unrecorded narrowing, invented facts, and test theater. Use after /vulyk-build completes, or on any diff the Queen does not fully trust.