Borrowing it
Nothing to install: this file belongs to aoreshkov/kotlin-lib-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aoreshkov/kotlin-lib-mcp/main/.claude/skills/review-currency/SKILL.mdgit clone --depth 1 https://github.com/aoreshkov/kotlin-lib-mcpWrote 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/aoreshkov/kotlin-lib-mcp/review-currency)<a href="https://agentmods.dev/skills/aoreshkov/kotlin-lib-mcp/review-currency"><img src="https://agentmods.dev/badge/skills/aoreshkov/kotlin-lib-mcp/review-currency/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/aoreshkov/kotlin-lib-mcp/review-currency"><img src="https://agentmods.dev/badge/skills/aoreshkov/kotlin-lib-mcp/review-currency.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 | $0.00095 | $0.00914 |
| Opus 5 | $0.00048 | $0.00457 |
| Sonnet 5 | $0.00019 | $0.00183 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
review-currency 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- review-currency — 94% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project currency review — expert panel
Run a currency review of this repository: how far its toolchain, dependencies, and practices have drifted from the latest official releases and recommendations as of today's date. Never judge currency from memory — every claim about "latest" must be verified by the expert subagents against official sources on the web today.
Workflow
1. Snapshot project state
Read these files and collect the facts the experts will need (versions, pins, action refs, base images). Note today's date — all research anchors to it.
gradle/libs.versions.toml— every version pin and its comments (comments mark deliberate pins)gradle/wrapper/gradle-wrapper.properties— Gradle version.github/workflows/ci.yml,.github/workflows/codeql.yml,.github/workflows/release.ymlDockerfileandserver.jsonCLAUDE.md— project conventions and gotchas the experts must honor.claude/— agents, skills, hooks,settings.json(the Claude Code setup itself)
2. Select the panel
The panel is six dedicated currency subagents (defined in .claude/agents/):
kotlin-currency, mcp-currency, deps-currency, ci-currency, security-currency,
claude-code-currency. Each agent carries its own persona, inspection list, official
sources, project gotchas, and output contract — they are the single source of truth.
(references/experts.md is the human-readable copy of those briefs, kept in sync for
reviewers.)
If $ARGUMENTS is non-empty, launch only the experts whose keys it names (kotlin, mcp,
deps, ci, security, claude-code → the matching *-currency agent); otherwise launch
all six.
3. Launch the experts in parallel
Launch one subagent per selected expert, all in a single message, using the matching
*-currency agent type. Each agent already knows its brief and output contract, so the
prompt only needs to supply:
- The relevant snapshot facts from step 1 (versions, pins, action refs, base images).
- The absolute repo path and today's date.
- A reminder to return the standard findings table (Area | Current in repo | Latest official | Severity | Recommendation | Source URL) followed by ≤5 sentences of practice-level commentary — the agent's own definition spells this out in full.
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.
- 12d ago First seen · 72 lines · 95 tokens per session scan A 60d819466622
review-currency is a skill published in the GitHub repository aoreshkov/kotlin-lib-mcp (8 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 914 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
shepherd
Use when asked to shepherd, babysit, monitor, or poll open pull requests or merge requests, including triaging review feedback, CI failures, and routine follow-up.
kotlin-api-design
Use when designing or reviewing Kotlin function ownership, member or extension functions, factories, single-field domain types, value classes, data classes, Kotlin Multiplatform expect/actual declarations, or platform service boundaries.
kotlin-concurrency-and-flow
Use when writing or reviewing Kotlin coroutine scope ownership, raw Thread or Executor work, init launches, non-suspending launch APIs, runBlocking, cancellation, StateFlow, SharedFlow, Channel, stateIn, SharingStarted, state updates, or one-shot events.
pr-fix-loop
Manage multiple GitHub Pull Requests in parallel. In a single loop pass, for every PR: check CI status, auto-classify each failing check (transient infra / lint / binary-compat / build / test) and delegate to the matching fix-ci- skill, then handle unresolved review comments end to end (fetch → fix → commit → push →…
exploratory-pr-verification
Operational rules for exploratory PR verification driven by multiple parallel subagents in a Kotlin project (Android / JVM / KMP / Compose / server-side Kotlin). Covers PDCA / MCP-driven dynamic checks / ticket bookkeeping / PR comment etiquette / build isolation / time budgeting / loop termination /…
to-plan
Use when one ready GitHub issue or an in-chat task needs a repository-aware implementation plan for a later implementation workflow.