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 ThisIsSadeghi/KMPilot --skill modify-featuregit clone --depth 1 https://github.com/ThisIsSadeghi/KMPilotWrote 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/thisissadeghi/kmpilot/modify-feature)<a href="https://agentmods.dev/skills/thisissadeghi/kmpilot/modify-feature"><img src="https://agentmods.dev/badge/skills/thisissadeghi/kmpilot/modify-feature/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/thisissadeghi/kmpilot/modify-feature"><img src="https://agentmods.dev/badge/skills/thisissadeghi/kmpilot/modify-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 3 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 20 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 143 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00016 | $0.04992 |
| Opus 5.5 | $0.00006 | $0.01997 |
| Sonnet 5.5 | $0.00003 | $0.00998 |
| Haiku 4.5 | $0.00002 | $0.00499 |
Grade A, and why
modify-feature 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 1mo 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modify Feature
Apply changes to existing features using spec-first workflow.
Architecture Reference: @../_shared/patterns.md
Hook Marker (Required)
Before editing any feature files, activate the skill marker so the PreToolUse hook allows edits:
touch /tmp/.claude-kmpilot-skill-active
After completion (or on any early exit), remove it:
rm -f /tmp/.claude-kmpilot-skill-active
Workflow
Parse → Spec Check → Design Artifact Detection → Understand → Plan → Draft Spec → [USER APPROVES] → Activate marker → Implement → Validate → Update Spec → Remove marker → Done
Step 1: Parse Feature Name
Extract from request: "add sorting to productlist" → productlist
Validate: ls feature/{featurename}/src/commonMain/kotlin/
Step 2: Spec Check
Load .claude/docs/{featurename}/spec.md
If missing, stop and instruct the user:
No spec found for '{featurename}'. Please run /audit-spec {featurename} first
to generate one, then re-invoke /modify-feature.
Do NOT auto-invoke /audit-spec — skills do not call each other; the user controls the pipeline.
Step 3: Design Artifact Detection
Check for a Stitch design blueprint:
- Check blueprint exists:
.claude/docs/{featurename}/designs/{featurename}_blueprint.md - Check stitch-project.json:
.claude/docs/_project/stitch-project.json— readfeatures[featurename].blueprintConsumed - Determine mode:
| Blueprint exists? | blueprintConsumed |
Mode |
|---|---|---|
| Yes | false |
Design-aware mode — blueprint drives UI implementation |
| Yes | true |
Normal mode — blueprint already consumed |
| No | N/A | Normal mode — no design artifact |
If entering design-aware mode, log:
Design artifact detected: .claude/docs/{featurename}/designs/{featurename}_blueprint.md
Entering design-aware mode. Blueprint will drive UI implementation.
Step 4: Understand Current Implementation
Read spec sections: Requirements, Architecture, State Management, Navigation
What ships with it
2 files 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.
- 1mo ago First seen · 225 lines · 16 tokens per session scan A 02a51455231e
modify-feature is a skill published in the GitHub repository ThisIsSadeghi/KMPilot (55 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 4,992 once invoked, about $0.0001 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
kotlin-android
Use when building or fixing a native Android app in Kotlin and Jetpack Compose on the UDF layered architecture — ViewModel/StateFlow, Hilt, Room, Retrofit, coroutines, type-safe Navigation, and the Gradle/AGP surface. NOT shared Android and iOS UI from one Kotlin codebase (that is compose-multiplatform).
compose-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.
compose-focus-navigation
Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.
kmp-lsp
Kotlin/Java/Swift LSP server for code navigation in Android and iOS codebases. Use when navigating Kotlin, Java, or Swift source files: finding class definitions, listing symbols, jumping to implementations, finding all usages, checking type signatures, or switching workspace between projects. Triggers for: "find this…
kotlin-expert
Expert-level Kotlin development, Android, coroutines, and multiplatform. Use when the user mentions Android, coroutines, multiplatform, or JVM, or when the task involves Kotlin Fundamentals, Android Development, Kotlin Multiplatform, or Kotlin Style.