Borrowing it
Nothing to install: this file belongs to osama-raddad/FireCrasher. 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/osama-raddad/FireCrasher/master/.claude/skills/update-abi-baseline/SKILL.mdgit clone --depth 1 https://github.com/osama-raddad/FireCrasherWrote 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/osama-raddad/firecrasher/update-abi-baseline)<a href="https://agentmods.dev/skills/osama-raddad/firecrasher/update-abi-baseline"><img src="https://agentmods.dev/badge/skills/osama-raddad/firecrasher/update-abi-baseline/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/osama-raddad/firecrasher/update-abi-baseline"><img src="https://agentmods.dev/badge/skills/osama-raddad/firecrasher/update-abi-baseline.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 | $0.00056 | $0.00491 |
| Opus 5 | $0.00028 | $0.00246 |
| Sonnet 5 | $0.00011 | $0.00098 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
update-abi-baseline 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 11d 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.
What it actually says
Update the ABI baseline
The library's public binary API is frozen in firecrasher/api/firecrasher.api
by the binary-compatibility-validator plugin. :firecrasher:apiCheck (part of
check, and therefore CI) fails whenever the compiled public surface no longer
matches that file. The baseline exists so public API changes are always
deliberate and reviewed — never accidental.
When to use
apiCheckfailed and the API change was intentional.- You added, removed, renamed, or changed the signature/visibility of any
public/protecteddeclaration infirecrasher/src/main.
If the API change was not intentional, do not run this — you have leaked an
implementation detail into the public surface. Make the declaration internal
or private instead (the library is compiled with explicitApi()).
Steps
- Regenerate the baseline from the current sources:
./gradlew :firecrasher:apiDump - Review the diff — this is the point of the skill. Every line must be a change
you meant to make:
git diff firecrasher/api/firecrasher.api - Confirm the check now passes:
./gradlew :firecrasher:apiCheck - Commit
firecrasher.apiin the same commit as the API change it describes, so the baseline and the code never drift apart.
Notes
- Removing or changing an existing public signature is a breaking change for
consumers — call it out in the PR description and the README "What's new", and
it should drive a version bump (see the
releaseskill). - The validator tasks are wired by hand in
firecrasher/build.gradle(AGP's built-in Kotlin doesn't auto-register them);apiDump/apiCheckare the only entry points you need.
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.
- 11d ago First seen · 50 lines · 56 tokens per session scan A 7c88f6836ceb
update-abi-baseline is a skill published in the GitHub repository osama-raddad/FireCrasher (148 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 491 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
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.
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.
swiftlint
Configure and roll out SwiftLint for an iOS/Swift (or KMP-iOS) fintech app — author .swiftlint.yml (disabledrules / optinrules / onlyrules / analyzerrules / included / excluded / customrules, per-rule severity thresholds, parentconfig / childconfig), wire it via the SwiftLintPlugins SPM build-tool plugin (SimplyDanny)…
solid-expert
Kotlin & Compose Multiplatform SOLID Expert. Applies SOLID principles with a strong preference for composition over inheritance (COI) to build professional, clean, maintainable, and testable mobile/multiplatform applications. Use when: designing architectures, refactoring deep class hierarchies, debugging class…
kotlin-concurrency-expert
Kotlin Coroutines review and remediation for KMP and Android codebases. Use when asked to review concurrency usage, fix coroutine-related bugs, improve thread safety, or resolve scoping issues in any Kotlin code (commonMain, androidMain, iosMain).
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.