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/opensecretcloud/maple/develop-maple-proxynpx skills add OpenSecretCloud/Maple --skill develop-maple-proxygit clone --depth 1 https://github.com/OpenSecretCloud/MapleWhat 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 | $0.00083 | $0.01327 |
| Opus 5 | $0.00042 | $0.00664 |
| Sonnet 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 2d 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.
- 2d 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 (91 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 1,327 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…