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 simplifiergit 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/simplifier)<a href="https://agentmods.dev/skills/adambien/airails/simplifier"><img src="https://agentmods.dev/badge/skills/adambien/airails/simplifier/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/simplifier"><img src="https://agentmods.dev/badge/skills/adambien/airails/simplifier.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 | $0.00146 | $0.00840 |
| Opus 5.5 | $0.00058 | $0.00336 |
| Sonnet 5.5 | $0.00029 | $0.00168 |
| Haiku 4.5 | $0.00015 | $0.00084 |
Grade A, and why
simplifier 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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simplifier
The middle mode between rehost and rearchitect: the system keeps its structure, loses its noise. Every pass is semantics-preserving — and proven so, not assumed: the characterization suite is the green bar every pass must hold. This skill owns the pass discipline; what to transform and what replaces a dependency comes from the composed stack ecosystem.
Preconditions
- The system runs on the target platform (1:1 lift completed).
- Characterization recordings exist and replay green. No green bar, no simplification — run
/characterization-testsfirst.
Pass Loop
- Pick one pass: a single transformation over a bounded scope, or a single dependency removal. Never batch.
- Apply it.
- Verify with the stack's own build/check loop, then replay the characterization suite.
- Green → commit the pass. Diff → reconcile (an accepted behavior change is a human decision, per characterization-tests) or revert the pass entirely.
- Log the pass in
migration/SIMPLIFICATION.md— one line: date, pass, result. - Repeat until the catalog finds no high-impact transformation and the dependency list is settled.
Code Passes
The transformation catalog and its impact-to-risk ordering come from the composed stack ecosystem:
- Java — java-distiller: modern syntax, API upgrades, pattern adoption, dead-code removal.
- Web frontend — web-conventions + web-components: semantic HTML, modern CSS over framework classes, custom elements over framework widgets, standards-based routing and state.
Constraint on top, any stack: preserve the public surface and the structure — packages, components, routes stay where they are. Internals may simplify, dead code may go; moves, splits, and merges are carving, and carving is /bc-carver + /sbce territory.
Dependency Passes
One dependency per pass. The ladder shape is stack-neutral — platform first, then copied source, then keep with justification; the rungs are the stack's:
| Stack | Ladder | Manifest |
|---|---|---|
| Java | Java SE → MicroProfile/Jakarta EE → copied source (zjson pattern) | pom.xml |
| Web frontend | Web platform, Baseline (fetch, querySelector, custom elements, modern CSS) → vendored source |
package.json, script tags |
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.
- 2d ago Changed · +1 lines · +146 tokens per session 536c2b367986
- 1mo ago First seen · 52 lines · 0 tokens per session scan A 484377132812
simplifier is a skill published in the GitHub repository AdamBien/airails (58 stars, last pushed 3d ago), licensed MIT. It adds 146 tokens to every session and 840 once invoked, about $0.0006 per session on Opus 5.5. 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
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
resolve-repro-audit
Audit a recovered repro patch, assertions, and behavioral baseline before authoring or reviewing.
testing-dags
Complex DAG testing workflows with debugging and fixing cycles. Use for multi-step testing requests like "test this dag and fix it if it fails", "test and debug", "run the pipeline and troubleshoot issues". For simple test requests ("test dag", "run dag"), the airflow entrypoint skill handles it directly. This skill…
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.