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.
git 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/commands/thisissadeghi/kmpilot/audit-spec)<a href="https://agentmods.dev/commands/thisissadeghi/kmpilot/audit-spec"><img src="https://agentmods.dev/badge/commands/thisissadeghi/kmpilot/audit-spec/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/commands/thisissadeghi/kmpilot/audit-spec"><img src="https://agentmods.dev/badge/commands/thisissadeghi/kmpilot/audit-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00012 | $0.00754 |
| Opus 5.5 | $0.00005 | $0.00302 |
| Sonnet 5.5 | $0.00002 | $0.00151 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
audit-spec scanned grade A with 1 finding 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/docs/{featurename}/prd.md Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Feature Specification
Audit, generate, or compare specifications for existing features.
Architecture Reference: @../skills/_shared/patterns.md Spec Template: @../skills/_shared/spec-template.md
Usage
/audit-spec {featurename} # Generate spec from code
/audit-spec {featurename} --compare # Detect spec drift
When to Use
| Scenario | Use? |
|---|---|
| Legacy feature without spec | Yes |
| Check spec-code consistency | Yes (--compare) |
| New feature creation | No → /create-feature |
| Modifying existing feature | No → /modify-feature |
Mode 1: Generate Spec (Default)
Process
-
Validate:
ls feature/{featurename}/src/commonMain/kotlin/ -
Discover Package:
grep "namespace" feature/{featurename}/build.gradle.kts -
Analyze Implementation:
data/model/*.kt- Data modelsdata/datasource/*.kt- DataSource interface + impldata/repository/*.kt- Repository interface + implpresentation/*ViewModel.kt- State managementpresentation/ui/*Screen.kt- UI compositionpresentation/navigation/*.kt- Routes and callbacksdi/*Modules.kt- DI bindings
-
Check for PRD (preserve WHY):
cat .claude/docs/{featurename}/prd.mdCopy: Goals, Non-Goals, Background & Rationale, Design Decisions
-
Generate: Create
.claude/docs/{featurename}/spec.mdusing @../skills/_shared/spec-template.md -
Report — emit the blockquote as the very last line of output:
## Specification Generated **Feature:** {featurename} **Output:** .claude/docs/{featurename}/spec.md --- > **Next step —** review `.claude/docs/{featurename}/spec.md` and fill any TODO sections, then run `/clear` to free the context window, followed by `/review-feature {featurename}` to validate the implementation against it.
Mode 2: Compare/Drift Detection (--compare)
Process
- Load existing spec:
.claude/docs/{featurename}/spec.md - Analyze current implementation (same as Mode 1)
- Compare and generate drift report:
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 · 95 lines · 12 tokens per session scan A 5b79b6c8b3d4
audit-spec is a command published in the GitHub repository ThisIsSadeghi/KMPilot (55 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 754 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
feature-learn
View and manage patterns learned from feature builds. Shows extracted instincts, confidence scores, and feature completeness history.
feature-build
Build a complete mobile feature from description to running code with E2E tests. Orchestrates 6 phases - planning, implementation, testing, build-fix, quality gate, and verification. Auto-detects platform.
feature-plan
Plan a mobile feature with architecture decisions, file breakdown, dependency analysis, and test strategy. Produces a structured plan document reviewed by an architecture agent.
feature-quality-gate
Run quality reviews on an implemented feature - code review, security audit, and performance review. Collect findings and apply fixes.
feature-build-fix
Compile the feature, run all tests, and iteratively fix compilation errors and test failures until everything passes. Max 5 iterations.
feature-implement
Implement a planned mobile feature using parallel specialized agents for network, data, architecture, UI, and wiring layers. Requires an approved feature plan.