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/validate-maplenpx skills add OpenSecretCloud/Maple --skill validate-maplegit 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 | $0.00078 | $0.04388 |
| Opus 5 | $0.00039 | $0.02194 |
| Sonnet 5 | $0.00016 | $0.00878 |
| Haiku 4.5 | $0.00008 | $0.00439 |
Grade A, and why
validate-maple 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 — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Maple
Prove the behavior that changed. Treat automated checks, successful builds, and observed runtime behavior as different evidence. Never call a build or unit-test pass an end-to-end test.
Establish scope and identity
- Read
AGENTS.md, the relevant source, nearby tests, and the applicable workflow or script before choosing commands. - Inspect
git status, the diff, and the base commit. Preserve unrelated user changes. - Classify risk by behavior, not file path. Code under
frontend/src/can invoke Tauri commands and require native validation even though PR change detection may classify it as web-only. - Identify every boundary the change crosses: browser, Tauri IPC, Rust, local process, filesystem, keyring, OpenSecret API, configurable billing or feature-flag API endpoint, operating system, or packaged resource.
- Record the untested boundaries before running checks. Add proof as it is obtained.
Use the repository's pinned Nix environments. Do not install substitute global tools merely to make a check pass.
Choose the validation tier
Use the highest tier triggered by the change. Add lower-tier checks rather than replacing them.
Tier 0: documentation and inert metadata
Use for prose, comments, or metadata that cannot affect a build or runtime.
- Review the rendered or consumed result, links, examples, and commands.
- Run
nix flake check --no-update-lock-filewhen changing the flake, GitHub Actions, or release metadata. - Escalate to the owning tier when documentation changes an executable example, environment contract, or generated input.
Tier 1: isolated frontend behavior
Use for pure React, TypeScript, CSS, state, and browser behavior with no native or service boundary.
- Run focused Bun tests while iterating.
- Run the complete frontend CI script before handoff.
- Build the PR-configured web artifact.
- Smoke the changed state in a real browser. Cover loading, empty, success, error, and disabled states when relevant.
- Test keyboard operation, focus, accessible labels, light/dark themes, and narrow/wide layouts when the change can affect them.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 407 lines · 78 tokens per session scan A a266d9635ffc
validate-maple is a skill published in the GitHub repository OpenSecretCloud/Maple (91 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 4,388 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
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
speckit-analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
add-sample
Create a SamplesApp sample page with correct theming and attributes. Use when adding UI samples for controls.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…