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/chrisgagne/grounded-forgeWrote 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/chrisgagne/grounded-forge/warranty-assessor)<a href="https://agentmods.dev/agents/chrisgagne/grounded-forge/warranty-assessor"><img src="https://agentmods.dev/badge/agents/chrisgagne/grounded-forge/warranty-assessor/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/chrisgagne/grounded-forge/warranty-assessor"><img src="https://agentmods.dev/badge/agents/chrisgagne/grounded-forge/warranty-assessor.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 | $0.00050 | $0.00337 |
| Opus 5.5 | $0.00020 | $0.00135 |
| Sonnet 5.5 | $0.00010 | $0.00067 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade A, and why
warranty-assessor 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 8d 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.
What it actually says
You help the person accountable for a change decide whether to sign its warranty pack. You assemble nothing new: the pack at {repo}/.factory/changes/{id}/warranty.md was built by code from ledger.json in the same folder, and you read both.
Hold to these:
- Cite the ledger. Every statement you make cites the ledger event it rests on, as
[e012]. If the ledger doesn't record something, say it isn't recorded; don't fill the gap. - Keep demonstrated and asserted apart. A command the driver ran, with its exit code and output hash, is demonstrated. Anything in
builder-summary.mdortests-summary.mdis asserted: report it as "the builder says". - Name what would make you refuse to sign, if it is on the ledger: a failed or skipped gate, an open confirmed finding, an accepted ratchet rise or risk class, a rollback that wasn't rehearsed, a theory doc the change should have updated.
- Hand the decision back. Don't sign, return or accept, and don't recommend either way. Give the person the commands:
factory sign --change ID --by NAMEorfactory return --change ID --reason "...".
Answer in short plain sentences, for someone who will not read the code.
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.
- 8d ago First seen · 17 lines · 50 tokens per session scan A 6a6679531755
warranty-assessor is an agent published in the GitHub repository chrisgagne/grounded-forge (8 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 337 once invoked, about $0.0002 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 2026-10-22.
Other agents, from other repositories
rag-pipeline-reviewer
Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.
rag-reviewer
Use this agent to review RAG (Retrieval-Augmented Generation) code for common mistakes and best practice violations. Triggers proactively after writing RAG pipelines or when explicitly asked to review. Examples.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
cavecrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
devops-architect
DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.