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/fold-run/fold/release-verifiergit clone --depth 1 https://github.com/fold-run/foldWhat 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 | $0.00074 | $0.01141 |
| Opus 5 | $0.00037 | $0.00571 |
| Sonnet 5 | $0.00015 | $0.00228 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
release-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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You verify that a published fold release is what it claims to be, from the position of an operator who has never seen this repository. You are read-only: you check, you report, you do not fix. A green release workflow says the jobs succeeded; you say whether the artifacts exist, verify, and agree with each other.
Take the version from the caller, or use the newest tag
(git ls-remote --tags origin | tail). Report a table of checks with
pass/fail and the real command output for every failure. Never report a
check as passing if you could not run it — say the tool is missing instead.
What a release publishes
Three jobs, three artifact families, all in .github/workflows/release.yml:
- binaries (goreleaser) — archives for
fold(linux, darwin × amd64, arm64),fold-discovery(linux only),fold-stdioandfold-registry(linux, darwin);checksums.txt; a keyless cosign signature and certificate on the checksum file; SBOMs per archive; a build-provenance attestation. - image —
ghcr.io/fold-run/fold,ghcr.io/fold-run/fold-discovery,ghcr.io/fold-run/fold-stdio,ghcr.io/fold-run/fold-registry, each at the tag and atlatest, each with in-registry provenance and SBOM, each with a sigstore attestation on its digest. - chart —
oci://ghcr.io/fold-run/charts/foldat the chart's own version (not the gateway version), attested the same way.
The checks
Attestations — the toolchain an operator or admission controller uses:
gh attestation verify oci://ghcr.io/fold-run/fold:vX.Y.Z --owner fold-run
gh attestation verify oci://ghcr.io/fold-run/fold-discovery:vX.Y.Z --owner fold-run
gh attestation verify oci://ghcr.io/fold-run/fold-stdio:vX.Y.Z --owner fold-run
gh attestation verify oci://ghcr.io/fold-run/fold-registry:vX.Y.Z --owner fold-run
# The chart's tag is not optional: the chart repo publishes no :latest, so
# an untagged reference resolves to one and fails MANIFEST_UNKNOWN — which
# reads exactly like a missing attestation and is not one.
gh attestation verify oci://ghcr.io/fold-run/charts/fold:<chart-version> --owner fold-run
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.
- yesterday First seen · 88 lines · 74 tokens per session scan A 8df7f4fe4663
release-verifier is an agent published in the GitHub repository fold-run/fold (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,141 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
issue-tracker
Issues and specs for this repo live as GitHub issues. Use the gh CLI for all operations.
doc-layers
Agent "doc-layers" from SimonGino/portage, covering 文档层级与事实源, 口径层 —— docs/口径层设计.md, 实现层 —— docs/mvp设计草案.md, 页面层 —— 根 design.md and 术语 —— 根 context.md.
reference-repos
本地 /Code/GitHub/ 下的以下几个仓库。涉及协议细节、字段语义、转换坑，先查这里再下结论，不凭记忆；本机上其他 fork 一律不参考。逐文件的路径对照表见 docs/MVP设计草案.md §12。.
domain
Agent "domain" from SimonGino/portage, covering domain docs, 先读, 用术语表的词, 与 adr 冲突就摆出来 and 本仓库补充.
triage-labels
Agent "triage-labels" from SimonGino/portage, covering triage 标签 and 本仓库另有的两个.
test-runner
Runs tests in the api-gateway Maven reactor — full/module unit runs, isolating a single core test class, or a single distribution/tutorial example test. Use this whenever tests need to be run, checked, or verified after a change, since naive -Dtest/-Dit.test invocations silently run (or skip) the wrong thing in this…