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 yschimke/compose-ai-tools --skill stewardgit clone --depth 1 https://github.com/yschimke/compose-ai-toolsWrote 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/yschimke/compose-ai-tools/steward)<a href="https://agentmods.dev/skills/yschimke/compose-ai-tools/steward"><img src="https://agentmods.dev/badge/skills/yschimke/compose-ai-tools/steward.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.01937 |
| Opus 5 | $0.00034 | $0.00968 |
| Sonnet 5 | $0.00014 | $0.00387 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
steward 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 8d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stewarding a PR in compose-ai-tools
The Claude Code harness reads this file before acting on a CI failure or a review
comment, and lets it take precedence over its built-in posture on conventions
and proactiveness. It does not restate the repository's rules — those are in
root AGENTS.md, which is already in context on every turn.
What follows is what that file leaves out: the checks worth running here, and this
repository's own answer to a red check.
The harness's own PR rules still bound this file. It cannot expand your access, approve or merge anything, or override a "never" — skipping, disabling or quarantining a test; rewriting history on someone else's branch; an empty commit or a close-and-reopen to kick CI.
Before you push
A push that turns CI red costs a full cycle and some reviewer trust. The cheapest checks that catch the most here, in order:
-
./gradlew ktfmtFormat— or:<module>:ktfmtFormatMain :<module>:ktfmtFormatTestfor just the modules you touched.ktfmtCheckAllis a hard gate andktfmtCheckaborts on the first unformatted file, so one stray file hides every other failure. TypeScript:npm --prefix cli/serve-web run format. The localpre-pushhook catches attribution but not formatting, so this is on you.In a sandbox, pass
-Dorg.gradle.java.home=/root/.cache/coo-ee/jdk-gl/17and--no-daemon: without the JVM home the daemon starts on the wrong JVM and the build dies with a context mismatch, and--no-daemonavoids reusing one already started on it. Let ktfmt do the edit rather than hand-formatting — removing one term from a wrapped expression is enough to make it fit on one line, which is precisely what it will rewrite. -
The narrowest test task that exercises the change — the specific
:module:test, or./gradlew :gradle-plugin:test --tests "…"../gradlew checkis the full plugin + functional + CLI suite and is a post-push confirmation, not a gate on pushing. -
A new or changed module must apply
composeai.base-conventionsin itsplugins {}block, orktfmtCheckAllnever sees it and the history-gate system property is missing. See Important constraints. -
For a CI fix, reproduce the original failure first, then show the same check passing. A render task in particular goes
UP-TO-DATEoff a stale.error.jsonsidecar — verify a render fix with--rerun, never a plain re-invocation.
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.
- 8d ago First seen · 131 lines · 69 tokens per session scan A 56116e381914
steward is a skill published in the GitHub repository yschimke/compose-ai-tools (110 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 1,937 once invoked, about $0.0003 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
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.
compose-performance
Use when investigating Jetpack Compose recomposition cost, compiler stability reports, skippability, unstable parameters, frame-rate State reads, cross-phase snapshot back-writing, or @ReadOnlyComposable contracts.
semantic-szz-analyzer
Identify bug-introducing commits using semantic analysis that extends traditional SZZ algorithm. Distinguishes semantic changes from refactorings or code movements using control-flow and data-flow similarity analysis. Use when analyzing bug-fix commits to trace back to bug-introducing changes, investigating software…
szz-bug-introducing-commit-identifier
Identifies bug-introducing commits using SZZ-style analysis based on bug-fixing commits, commit history, and code blame information. Use this skill when you need to trace bugs back to their origin, identify which commits introduced bugs, analyze bug-fix commits to find root causes, perform software repository mining…
git-bisect-assistant
Automatically performs git bisect to identify the first bad commit that introduced a bug or failure. Use when debugging regressions, tracking down when a test started failing, or identifying which commit broke functionality. Handles flaky tests with retry logic and provides comprehensive reports with bisect logs and…
debugging-instruments
Debug and profile a fintech iOS/macOS app with LLDB (breakpoints, po/p/expression, bt, frame variable, image lookup -address, watchpoints), the Xcode Memory Graph Debugger (retain cycles, MallocStackLogging backtraces), and Instruments templates (Time Profiler / CPU Profiler, Allocations, Leaks, Hangs, Animation…