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 skills/fold-run/fold/depsnpx skills add fold-run/fold --skill depsgit clone --depth 1 https://github.com/fold-run/foldWrote 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/fold-run/fold/deps)<a href="https://agentmods.dev/skills/fold-run/fold/deps"><img src="https://agentmods.dev/badge/skills/fold-run/fold/deps.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 | $0.00072 | $0.01067 |
| Opus 5 | $0.00036 | $0.00534 |
| Sonnet 5 | $0.00014 | $0.00213 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade A, and why
deps 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependencies and vulnerabilities
fold has 13 direct dependencies and runs at a trust boundary, so the supply chain is part of the threat model rather than housekeeping. Four separate mechanisms watch it, and knowing which one is talking saves the whole investigation.
| Mechanism | Watches | Produces |
|---|---|---|
CI vuln job / make vuln |
Go advisories against this tree | A red merge gate |
| dependabot (weekly ×3) | gomod, github-actions, docker base images | PRs |
drift.yml (Mondays 06:00 UTC) |
the latest MCP SDK and conformance suite | An issue |
console-sync.yml (on demand; bumped at release) |
the vendored console | A PR — see /console-sync |
A red govulncheck often has no commit behind it
Check this first, before reading the diff. make vuln runs
govulncheck@latest against the live advisory database, so a run that
was green yesterday goes red today because an advisory was published — not
because anything changed here.
go version # the toolchain in use
grep '^go ' go.mod # the version this module requires
make vuln # read WHICH module and WHICH advisory
If the finding is in the standard library, the fix is a Go patch
version, not a dependency bump: raise the go line in go.mod and let the
toolchain download it. That has happened here before — six standard-library
advisories at once, fixed by moving to a Go patch release.
If the finding is in a dependency, bump that dependency alone. Do not run a
blanket go get -u; a vulnerability fix and a feature bump should not
arrive in one commit.
Either way the image builder base may also need repinning — it sets
GOTOOLCHAIN=local, so an image whose base is below what go.mod requires
cannot fix it at build time and fails the build. That skew once sat on
main through two green merges and failed after the tag was pushed. CI's
image job now catches it per-PR; check deploy/docker/*.Dockerfile when
you move the Go line.
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 Changed f659a61f6780
- 3d ago First seen · 101 lines · 72 tokens per session scan A f6e42fc3257e
deps is a skill published in the GitHub repository fold-run/fold (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,067 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 skills, from other repositories
release-notes
Draft concise release notes.
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
jwx-guide-v4
Guide for developing Go applications with github.com/lestrrat-go/jwx v4 — parse/sign JWTs, work with JWS/JWE/JWK, pick algorithms, and avoid the common footguns. For developers using jwx, not for developing the library itself.
jwx-companion-bulk
Apply bulk operations across all jwx companion modules. Args.
readme-generate
從原始碼分析自動生成雙語 README。當使用者請求為專案建立 README、需要從程式碼庫生成 README.md（英文）和 README.zh.md（中文）、或希望為其函式庫/套件建立一致的多語言文件時使用。.
extension-upload
Package a script tool under /.config/agenvoy/tools/script/ into a tar.gz and publish to pkg.agenvoy.com registry. Keyword picker, dep/key detection, config-stored email (ask + lowercase + persist), ask version, email verification gate, multipart upload with downgrade/unique guards.