check-conformance

check-conformance is a skill for Claude Code, Codex from leifericf/agentic-sdk. It costs 31 tokens per session (986 once invoked), scanned A, original, MIT.

A code-review check for differences between the implementation and the project’s specifications, architecture decision records (written design decisions), and programming-language rules.

In plain words
What is it for?
Reviewing one module or part of a codebase for mismatches involving null values, empty collections, evaluation timing, function arguments, numbers, ordering, and error behavior.
Why use it?
It finds code that may work in normal cases but quietly breaks an agreed design or language behavior. It also requires superseded design decisions to be explained where the code differs.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/leifericf/agentic-sdk/check-conformance
Any agent
npx skills add leifericf/agentic-sdk --skill check-conformance
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for check-conformance

README.md
[![agentmods](https://agentmods.dev/badge/skills/leifericf/agentic-sdk/check-conformance.svg)](https://agentmods.dev/skills/leifericf/agentic-sdk/check-conformance)
Your own site
<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/check-conformance"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/check-conformance.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 986 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00986
Opus 5 $0.00015 $0.00493
Sonnet 5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00099

Measured 4d ago against content hash 8e7d7ee3503b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check-conformance 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.

skills/check-conformance/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

check-conformance

Role: review the shard for divergence from the canonical sources of truth.

Failure model: the code works on the happy path but diverges, without comment, from what the spec promises, what an ADR decided, or what the language standard guarantees.

Three layers apply, in this order.

  1. The spec (the design docs under docs/, the dossier the descriptor names, the public API docs) is the design contract. Behavior the code exhibits that the spec specifies differently is a finding; behavior the spec does not address is not.
  2. The ADRs (the :adr :store directory) are dated decisions. Code that violates an ADR is a :high finding citing ADR-NN. Code that follows a different path than an ADR because the ADR was superseded must cite the supersedence at the call site; an unstated supersedence is a finding.
  3. The language standard is the spec for the language surface. The pure core must match the host language's observable behavior for nil and null handling, empty collections, laziness and strictness boundaries, arity and signature errors, numeric tower promotion, ordering guarantees on sorted versus hash collections, integer overflow semantics, and error-propagation shapes (Result, error union, exception). The native wrappers follow the edge contract in skills/shared/references/architecture.md exactly; a mismatch between the calling-language signature and the contract is a finding.

Look for

  1. Semantic drift. Edges where the implementation's behavior would differ from the spec or the language standard: null where a docstring promises a value, empty-collection return where the spec specifies an error, laziness where the spec specifies eagerness, overflow where the spec specifies wrapping.
  2. Undocumented deviations. Behavior that differs on purpose from the spec but has no deviation comment at the implementation site. The idiom is a comment naming what the spec says and what the code does instead.
  3. Edge contract drift. A native call whose signature disagrees with the contract on argument types, return types, or handle ownership. The contract is normative; the handle catalog is the spec.
  4. Error-shape mismatches. An exception thrown where the spec specifies a returned error value (or vice versa); an error code not in the spec's diagnostic catalog; a diagnostic that hides the failing function or signature.
  5. Docstring and comment lies. Docstrings that promise behavior the implementation does not deliver, or that describe an older shape of the API.

Read the full file on GitHub · 104 lines

Changes

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.

  1. 4d ago First seen · 104 lines · 31 tokens per session scan A 8e7d7ee3503b

Subscribe to this mod's changes

check-conformance is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 986 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens