Borrowing it
Nothing to install: this file belongs to OpenSecretCloud/Maple. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OpenSecretCloud/Maple/master/.agents/skills/develop-maple-proxy/SKILL.mdgit clone --depth 1 https://github.com/OpenSecretCloud/MapleWrote 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/opensecretcloud/maple/develop-maple-proxy)<a href="https://agentmods.dev/skills/opensecretcloud/maple/develop-maple-proxy"><img src="https://agentmods.dev/badge/skills/opensecretcloud/maple/develop-maple-proxy/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/skills/opensecretcloud/maple/develop-maple-proxy"><img src="https://agentmods.dev/badge/skills/opensecretcloud/maple/develop-maple-proxy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00083 | $0.01327 |
| Opus 5.5 | $0.00033 | $0.00531 |
| Sonnet 5.5 | $0.00017 | $0.00265 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
develop-maple-proxy 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop Maple Proxy
Work from the OpenSecretCloud/Maple repository root; the component source is
under proxy/. Read the repository-root AGENTS.md, proxy/README.md,
affected source and tests, and the root
.github/workflows/proxy-*.yml files relevant to the change.
The source is part of Maple but keeps distinct public package and runtime boundaries:
proxy/builds themaple-proxycrate and binary.proxy/Cargo.tomlconsumes the in-tree OpenSecret Rust SDK at../sdk/rustwith a registry version retained for Cargo publishing.- desktop Maple consumes
../../proxyand../../sdk/rustfromfrontend/src-tauri/Cargo.toml; iOS and Android do not compile the proxy. frontend/src-tauri/src/proxy.rsowns Maple's account-scoped listener, configuration, key storage, and lifecycle around the library. Do not move that application behavior into the reusable crate incidentally.
Do not commit, push, open a PR, publish, tag, release, or change live infrastructure unless the user authorizes that action.
Keep validation and routing aligned
Run the credential-free proxy checks through its pinned shell:
nix develop --no-update-lock-file ./proxy -c bash -lc '
cd proxy
cargo fmt --all -- --check
cargo clippy --locked --all-targets --all-features -- -D warnings
cargo test --locked --all-features
RUSTDOCFLAGS="-D warnings" cargo doc --locked --no-deps --all-features
cargo machete
'
For Rust SDK or dependency-wiring changes, also prove the application resolves one local SDK and one local proxy:
nix develop --no-update-lock-file .#ci -c \
./scripts/ci/verify-local-rust-deps.sh
Root workflows own proxy Rust, daily supply-chain, non-publishing container,
and native-release rehearsal checks. proxy/src/**, proxy/Cargo.toml, and
unknown proxy build inputs are desktop application inputs; tests, examples,
docs, the standalone lockfile, and container-only files do not by themselves
route expensive Maple app builds. sdk/rust runtime changes affect both proxy
checks and desktop Maple. When a new input changes either graph, update
scripts/ci/change_detection.py, its table-driven tests, and workflow paths in
the same change.
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.
- 2mo ago First seen · 124 lines · 83 tokens per session scan A 002bb92171ad
develop-maple-proxy is a skill published in the GitHub repository OpenSecretCloud/Maple (92 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 1,327 once invoked, about $0.0003 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 2026-08-30.
develop-maple-proxy compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| develop-maple-proxyOpenSecretCloud/Maple | Skill | 92 | 2mo ago | MIT | A | 83 | Claude Code, Codex |
| rust-engineerJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 120 | Claude Code |
| azure-eventhub-rustmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 58 | Claude Code |
| apollo-router-plugin-creatorclidey/whodb | Skill | 5.0k | yesterday | Apache-2.0 | A | 116 | Claude Code |
| azure-eventhub-rustbenjaminasterA/antigravity-awesome-skills | Skill | 461 | yesterday | MIT | A | 0 | Claude Code, Codex |
| rust-gatewayBerriAI/litellm | Skill | 63k | yesterday | none | A | 70 | Claude Code, Codex |
| axumTerminalSkills/skills | Skill | 192 | yesterday | Apache-2.0 | A | 94 | Claude Code, Codex |