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 AdamBien/airails --skill bc-carvergit clone --depth 1 https://github.com/AdamBien/airailsWrote 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/adambien/airails/bc-carver)<a href="https://agentmods.dev/skills/adambien/airails/bc-carver"><img src="https://agentmods.dev/badge/skills/adambien/airails/bc-carver/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/adambien/airails/bc-carver"><img src="https://agentmods.dev/badge/skills/adambien/airails/bc-carver.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 | $0.00115 | $0.00781 |
| Opus 5 | $0.00057 | $0.00391 |
| Sonnet 5 | $0.00023 | $0.00156 |
| Haiku 4.5 | $0.00012 | $0.00078 |
Grade A, and why
bc-carver 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BC Carver
Decide the decomposition, don't perform it. Carving and executing are different acts: the carver produces a written, reviewable cut of the system into business components — the diff a human argues about before the first class moves. Candidates, not verdicts.
Inputs
migration/GLOSSARY.md— canonical terms and## Decisions: ground truth, never contradicted.migration/CONCEPTS.md— co-occurrence graph and evidence pointers.
No mining, no new concepts. Vocabulary missing here is an extractor defect — stop and re-run /concept-extractor, don't improvise.
Carving Heuristics
- BCs are the dense clusters in the co-occurrence graph; cut along sparse edges.
- Homonym splits settled by the clarifier are the strongest boundary signals — a word that means two things marks two components.
- Name each BC with one canonical glossary term as a single lowercase token (
contracts,pricing) — this is the future sbce BC name. - Give each BC a one-line responsibility phrased in glossary language. If the line needs "and", reconsider the cut.
- Inter-BC references are directed (
uses); cycles between candidates are a carving error, not a documentation fact.
CARVING.md Format
Write migration/CARVING.md — regenerable, diffable:
# Carving: <system name>
## Components
### <bc-name>
- **Responsibility:** <one line, glossary language>
- **Concepts:** <canonical terms>
- **Uses:** <bc-name>, ...
## Diff
| Current | Target BC | Layer |
|---|---|---|
| com.legacy.contractmgmt | contracts | — |
| com.legacy.common.ContractValidator | contracts | control |
## Unmapped
<technical noise, dead-code candidates, shared utilities — with reasons>
## Open Questions
### Q<n> — <one-line question>
<evidence; candidate assignments>
- Diff granularity: package-level rows by default; class-level rows only where a package splits across BCs — that is where the information matters, and full class listings on large systems are enormous and instantly stale.
- Layer (boundary | control | entity) only where the evidence supports it; leave
—otherwise. - Unmapped is mandatory — silent omission reads as "covered".
- Open Questions continue the shared Q-id space from
CONCEPTS.md: never reuse or renumber ids, continue counting. Ambiguous assignments ("Tariff → contracts or pricing?") are questions, not guesses — resolve via/concept-clarifier.
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.
- 11d ago First seen · 64 lines · 115 tokens per session scan A f7ea2ba02252
bc-carver is a skill published in the GitHub repository AdamBien/airails (50 stars, last pushed 3d ago), licensed MIT. It adds 115 tokens to every session and 781 once invoked, about $0.0006 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
authoring-java-sdk-tasks
Writes Airflow task logic in Java, Kotlin, or any JVM language using the Airflow Java SDK. Use when the user wants to implement Airflow tasks in Java/JVM, asks about @Builder.Dag/@Builder.Task/@Builder.XCom, the Task/BundleBuilder interfaces, reading connections/variables/XComs from Java, the JSON-to-Java type…
configuring-airflow-language-sdks
Configures Airflow to run language SDK tasks (Java, Go, and future native SDKs) — register a coordinator, map a queue to it, ensure the runtime/artifact on workers, and tune coordinator options. Use when the user wants Airflow to route a queue to a native-language coordinator, asks about the [sdk]…
aws-cloudformation-bedrock
Provides AWS CloudFormation patterns for Amazon Bedrock resources including agents, knowledge bases, data sources, guardrails, prompts, flows, and inference profiles. Use when creating Bedrock agents with action groups, implementing RAG with knowledge bases, configuring vector stores, setting up content moderation…
aws-cloudformation-cloudfront
Provides AWS CloudFormation patterns for CloudFront distributions, origins (ALB, S3, Lambda@Edge, VPC Origins), CacheBehaviors, Functions, SecurityHeaders, parameters, Outputs and cross-stack references. Use when creating CloudFront distributions with CloudFormation, configuring multiple origins, implementing caching…
aws-cloudformation-cloudwatch
Provides AWS CloudFormation patterns for CloudWatch monitoring, metrics, alarms, dashboards, logs, and observability. Use when creating CloudWatch metrics, alarms, dashboards, log groups, log subscriptions, anomaly detection, synthesized canaries, Application Signals, and implementing template structure with…
aws-cost-optimization
Provides structured AWS cost optimization guidance using five pillars (right-sizing, elasticity, pricing models, storage optimization, monitoring) and twelve actionable best practices with executable AWS CLI examples. Use when optimizing AWS costs, reviewing AWS spending, finding unused AWS resources, implementing…