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 skills add explyt/spring-plugin --skill coding-guardgit clone --depth 1 https://github.com/explyt/spring-pluginWrote 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/explyt/spring-plugin/coding-guard)<a href="https://agentmods.dev/skills/explyt/spring-plugin/coding-guard"><img src="https://agentmods.dev/badge/skills/explyt/spring-plugin/coding-guard/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/explyt/spring-plugin/coding-guard"><img src="https://agentmods.dev/badge/skills/explyt/spring-plugin/coding-guard.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 | $0.00067 | $0.02924 |
| Opus 5.5 | $0.00027 | $0.01170 |
| Sonnet 5.5 | $0.00013 | $0.00585 |
| Haiku 4.5 | $0.00007 | $0.00292 |
Grade A, and why
coding-guard 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 5d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Guard — explyt/spring-plugin
Rules to follow when writing or modifying code in this repository (Explyt Spring IntelliJ plugin). Grounded in CONTRIBUTING.md, build.gradle.kts, gradle.properties, and existing sources.
0. Before coding (process rules)
These apply before any technical rule below. Bias toward caution over speed; for trivial tasks use judgement.
0.1 Think before coding
- State assumptions explicitly. If uncertain about intent, data shape, or an API contract — ask. Don't guess.
- Surface ambiguity, don't resolve it silently. If the request has multiple reasonable interpretations, list them and let the user choose.
- Push back when warranted. If a simpler approach exists, say so before implementing the requested one.
- Stop and name confusion. Don't patch over unclear behavior with plausible-looking code.
0.2 Simplicity first
- Minimum code that solves the problem. No features beyond what was asked, no abstractions for single-use code, no unrequested configurability.
- No defensive code for scenarios the type system or existing invariants already rule out (null checks on non-nullable Kotlin types, unreachable branches after an exhaustive
whenover a sealed type). Apply this only when an external explicit mechanism rules the case out — not your own "this can't happen" reasoning. - Do not remove platform-mandated guards: PSI
isValidchecks,VirtualFilevalidity checks, read/write-action wrappers,ProgressManager.checkCanceled()calls, and dumb-mode guards are required even if they look defensive. - If you wrote 200 lines where 50 would do — rewrite.
0.3 Surgical changes
- Touch only what's needed. Don't "improve" adjacent code, comments, formatting, or imports outside your change.
- Don't refactor code that isn't broken. If a rule below flags nearby code you are not editing — mention it to the user, don't silently rewrite it.
- Match existing style, even if you'd write it differently.
- Clean up only your own orphans: imports/variables your edit made unused. Flag pre-existing dead code instead of deleting it.
- Traceability test: every changed line should trace directly to the user's request.
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.
- 5d ago Changed · +2 lines 030d98d21bdf
- 6d ago Changed fa677b6dadef
- 1mo ago First seen · 168 lines · 67 tokens per session scan A 3b9394caba9f
coding-guard is a skill published in the GitHub repository explyt/spring-plugin (164 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 2,924 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.
Other skills, from other repositories
create-dataflow-approximation
Model a method's taint propagation as code-based dataflow approximation and refine it against a test project until the sample passes. Use for a dropped method that requires code-based approximation.
create-test-project
Create an OpenTaint test project with positive/negative samples for verifying a rule or approximation. Use when a rule or approximation needs a test project to check against.
debug-rule
Debug a rule or approximation that behaves unexpectedly by tracing where taint is dropped. Use when its samples won't pass after repeated attempts, or it passes tests but is wrong on a real scan.
write-fixture
Write Java/Kotlin tests with Fixture Monkey — enumerate the cases a method can produce, pick the ones worth testing, and build each fixture pinning only the properties that force the expected outcome.
analyze-external-methods
Analyze an OpenTaint scan's dropped external methods and decide which of them are propagators and optionally sinks. Use when a dropped-external-methods.yaml needs classification for dropped method type.
create-rule
Author and verify an OpenTaint rule. Use whenever a rule creation is needed.