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/conformancenpx skills add fold-run/fold --skill conformancegit 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 | $0.00052 | $0.00581 |
| Opus 5 | $0.00026 | $0.00291 |
| Sonnet 5 | $0.00010 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
conformance 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fold conformance suite
make conformance runs the official MCP conformance suite through the
gateway fronting the conformance repo's everything-server in passthrough
mode. CI gates merges on 40/40 checks. Requires go, node/npm/npx, git.
The pin lives in scripts/conformance.sh:
CONFORMANCE_COMMIT— conformance repo commit (server fixture)CONFORMANCE_PKG— npm package version (the checker)
The scheduled drift workflow overrides these to main/@latest to catch
upstream movement early; the pin itself is bumped deliberately.
Debugging a failure
- Reproduce locally:
make conformance. Note which check fails. - First question: did the gateway stop being invisible? Run the same
scenario against the upstream directly (the script starts it on
UPSTREAM_PORT, default 3901; gateway on 3902) and diff the behavior.- Differs through the gateway only → a fold bug. Usual suspects: response buffering/rewriting that federation doesn't require, namespacing applied in passthrough mode (it must not be), SSE stream handling, or a minted error replacing a pass-through error.
- Same failure hitting the upstream directly → the suite or fixture moved; this is a pin/drift issue, not a fold bug.
- Environment failures (ports busy, npx cache, node missing) look like
hangs — check
wait_fortimeouts in the script output before suspecting the gateway.
Bumping the pin (deliberate, never drive-by)
- Test the target first without editing anything:
CONFORMANCE_COMMIT=<sha> CONFORMANCE_PKG=@modelcontextprotocol/conformance@<ver> make conformance - If the check count changed (e.g. new checks beyond 40), read the new checks and decide: does fold pass them, or does a gap need closing first? A gap that stays open belongs in README "Not implemented".
- Edit both pin variables in
scripts/conformance.shtogether, update the 40/40 count in CLAUDE.md/CI docs if it changed, and run the full suite once more on the edited script. - The bump gets its own commit with the reason (drift workflow finding, new spec feature, etc.) — per-step approval before committing.
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 · 47 lines · 52 tokens per session scan A eb2aec452c26
conformance is a skill published in the GitHub repository fold-run/fold (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 581 once invoked, about $0.0003 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
hotplex-release
通过判断 SemVer 影响、整理 CHANGELOG、对账版本面和验证发布输入来准备或发布 HotPlex 版本。不要用于主机二进制更新、运行时诊断或文档巡逻。.
hotplex-docs-patrol
维护 HotPlex 当前文档，将代码、配置、API 或发布变更映射到 BFS 可达文档，只修复已验证的文档漂移。不要用于普通润色、运行时诊断或版本发布。.
hotplex-stt-tts
初始化或修复 HotPlex 本地 STT 和 MOSS TTS 运行时，包括 Python 依赖、官方模型、配置和验收。仅在明确授权主机变更时使用；只读检查请使用 hotplex-cli 或 hotplex-diagnostics。.
hotplex-diagnostics
深入诊断 HotPlex Gateway、Worker、Session、日志或反馈链异常。普通 status/doctor/security/config 只读检查属于 hotplex-cli；安装、更新、重启、配置写入和 Admin 变更属于 hotplex-operator。.
hotplex-cli
使用 HotPlex CLI 处理 Cron、明确请求的 Slack 操作、普通用户聊天命令指引，以及只读 status、doctor、security、config 诊断。不要用于飞书写操作、发布、服务安装、二进制更新或 Admin 变更。.
hotplex-operator
运维或初始化 HotPlex 主机，覆盖首次 onboard、服务安装/启动、二进制更新、主机配置、审计检查和 Admin 变更。仅在明确授权的 operator 上下文中使用。.