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 agentmods add skills/ivklgn/ai-kit/compatibility-auditnpx skills add ivklgn/ai-kit --skill compatibility-auditgit clone --depth 1 https://github.com/ivklgn/ai-kitWrote 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/ivklgn/ai-kit/compatibility-audit)<a href="https://agentmods.dev/skills/ivklgn/ai-kit/compatibility-audit"><img src="https://agentmods.dev/badge/skills/ivklgn/ai-kit/compatibility-audit.svg" alt="Measured on agentmods" 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 | $0.00231 | $0.02421 |
| Opus 5 | $0.00115 | $0.01210 |
| Sonnet 5 | $0.00046 | $0.00484 |
| Haiku 4.5 | $0.00023 | $0.00242 |
Grade A, and why
compatibility-audit 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 4d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compatibility Audit
Answer one question: is this change safe and clean with respect to everything it touches?
The audited unit can be anything with a boundary — a package, a module, a class, a single function, an endpoint, a schema, a config file. The word "surface" below means whatever that unit exposes.
Compatibility here is not only "does it break the build". Any change sits inside four boundaries, and it is compatible only when it agrees with all four:
| Axis | Boundary | The question |
|---|---|---|
| Contract | What it exposes outward | Does anything that depends on it still work? |
| Integration | The context it lives in | Does it match the conventions and reuse the abstractions of this place? |
| Completeness | The closure of the change | Was the change carried through everywhere it had to be? |
| Environment | What it executes on | Does it survive its runtime, platform, and rollout? |
This works across languages and domains because the axes are fixed while the reference standard is discovered per repository. Never judge against a generic best practice — judge against what this repo already does, and cite it.
This skill assesses; it does not fix. Evidence over intuition: every finding cites a file and line, a diff hunk, or a command result.
Step 0: Resolve the Scope
Run the bundled scope resolver — it handles baseline detection, all change states, and path scoping (paths are relative to this skill's directory):
sh scripts/resolve_scope.sh # current git changes vs merge base
sh scripts/resolve_scope.sh path/to/target # a package, module, file, schema, or config dir
sh scripts/resolve_scope.sh --base v1.4.0 pkg/ # explicit baseline
It prints BASE, MODE, COUNT, the changed files, the manifests that govern them, and the touched directories. Parse that output; do not re-derive it.
The three modes mean different things:
- git-changes / path-scoped-changes — baseline is
BASE, candidate is the working tree. Diff withgit diff <BASE> -- <paths>. - path-snapshot — no pending changes in that path. Audit the code as it stands against its current consumers ("is this thing in good standing?"). Contract findings become "risk in the existing surface" rather than "regression".
- COUNT 0 — nothing to audit. Ask the user what to audit; do not guess.
What ships with it
4 files 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.
- 4d ago First seen · 151 lines · 231 tokens per session scan A afef5021ecd5
compatibility-audit is a skill published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 2d ago), licensed MIT. It adds 231 tokens to every session and 2,421 once invoked, about $0.0012 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
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.