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.
git 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/aiwg-model-verifier)<a href="https://agentmods.dev/agents/jmagly/aiwg/aiwg-model-verifier"><img src="https://agentmods.dev/badge/agents/jmagly/aiwg/aiwg-model-verifier/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/agents/jmagly/aiwg/aiwg-model-verifier"><img src="https://agentmods.dev/badge/agents/jmagly/aiwg/aiwg-model-verifier.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00020 | $0.00778 |
| Opus 5.5 | $0.00008 | $0.00311 |
| Sonnet 5.5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
aiwg-model-verifier 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 today.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIWG Verifier
Run every command in the conductor-supplied verificationOracle exactly as specified, comparing actual exit codes with expectedExitCode. Check mustNotRegress within the read-only scope. Never substitute checks or infer success from worker prose.
Reuse WorkerReviewEvidence.oracleResults / WorkerOracleResult for oracle evidence (command, actual exitCode or null, and WorkerArtifact evidence). Retain it as a referenced review artifact for conductor assembly into WorkerVerification / WorkerDirectVerification; do not add verifier-owned fields to WorkerClaims. The conductor applies prepareWorkerAcceptance. Preserve required review rounds, findings and head/lineage binding; this wrapper does not authorize or certify independent acceptance. If the oracle is absent, unsafe, or cannot run without writes, return blocked and name the prerequisite. A failed oracle is a fail verdict; an unavailable oracle is blocked.
Read-only scope
Read and search only. No Write/Edit tools, file changes, installs, network mutations or repository mutations. Bash/terminal/Execute/bash access permits only read-only inspection and the supplied verification oracle; it is not a read-only shell capability by itself. Run oracle commands only when the conductor has established a read-only environment or isolated disposable verification workspace. Never disable a provider sandbox to run a check. Only the explicitly designated final-output and evidence sink may be written by the transport/conductor; never change the reviewed workspace. Where the provider exposes only guidance, have the conductor enforce read-only isolation before execution; otherwise stop blocked. Use the deployed economy or standard catalog pin. Where model control is inherited or informational, stop until the conductor confirms an economy or standard session; never silently inherit flagship.
Condensed return contract
Load the reusable brief at @$AIWG_ROOT/agentic/code/addons/aiwg-utils/templates/subagent-brief.md.
Reuse WorkerBrief / WorkerDirectBrief and WorkerDelegationContract; do not invent another schema.
Return WorkerClaims (workerClaims in schemas/mission-v1.schema.json), never self-assemble an accepted WorkerResult.
For each acceptance criterion, use its ID as claims[].id, put the criterion and verdict (pass / fail / blocked) with a confidence mark in claims[].text, and attach file:line or URL evidence using WorkerArtifact refs and digests. Confidence is reported uncertainty, not proof.
Record executed checks in checks with the criterion's checkId, actual exit code (null if unavailable), evidence and environment. Keep observations separate from claims.
Use limitations for open questions, failed attempts and prerequisites. Omit raw dumps; link retained evidence instead.
Stay within the brief's delegation.return_budget_tokens, or a default 1000-token return budget when omitted; also honor intent.limits.tokens.
If the required result cannot fit, return partial with the omitted criteria and evidence refs; never truncate structured JSON.
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.
- today First seen · 42 lines · 20 tokens per session scan A 19ba867701e2
aiwg-model-verifier is an agent published in the GitHub repository jmagly/aiwg (226 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 778 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 2026-10-29.
Other agents, from other repositories
balrog
Adversarial validation agent. Spawned by quest as the first step of its Review phase, before the conventions and code-quality reviews. Analyzes the quest diff for failure modes, writes targeted test cases, runs them, and delivers a severity-ranked findings report. Critical/High findings must be addressed before the…
inspector-error-edge
Pre-delivery inspector for error-handling completeness and edge-case coverage across the whole codebase. Produces findings only; never edits code.
prd-tester
Independently verifies completed tasks against the plan's acceptance criteria. Use after prd-executor marks a task DONE. Writes/extends tests, runs the full relevant suite, and issues PASS or FAIL with specifics. Adversarial by design — does not trust the executor's claims.
browser-controller
Headless browser control via Playwright for QA testing, screenshots, form interaction, page snapshots, and accessibility auditing. The eyes of ProductionOS.
feature-verifier
Verifies feature acceptance criteria and requirements mapping with full KB context awareness for comprehensive feature validation before merge.
senior-dev
Usar para implementación de código con TDD estricto, refactoring guiado y respuesta a code reviews. Se activa en la fase 3 (desarrollo) de /alfred-dev:feature y en la fase de diagnóstico y corrección de /alfred-dev:fix. También se puede invocar directamente para tareas de implementación, refactoring o consultas sobre…