What is conformance-walk?

A command that checks the testable parts of a repository against recorded expectations and reports coverage, pass rates, and missing expectations. It automatically chooses the checking method for the detected project type.

Running repository conformance checks and producing a report across source code, delivered artifacts, and live interfaces such as APIs or command-line tools.

It shows both what was tested and what passed, while making newly added testable work fail until it has an expectation.

conformance-walk — Command for Claude Code by terrene-foundation

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.

Clone the repo

git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-py

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/conformance-walk/github.svg)](https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/conformance-walk)

Your own site

<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/conformance-walk"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/conformance-walk/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/conformance-walk"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/conformance-walk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,295 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.01295
Opus 5	$0.00018	$0.00647
Sonnet 5	$0.00007	$0.00259
Haiku 4.5	$0.00004	$0.00129

Measured 7d ago against content hash bfdf3c498f4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

conformance-walk 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 7d 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.

.claude/commands/conformance-walk.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/conformance-walk — Run The Conformance Walk, Adapter Family Auto-Selected

Run a Conformance Walk (CW) over the repo's testable surfaces: enumerate every actionable unit → attach a FROZEN expectation → judge live/static state with a DETERMINISTIC oracle → report coverage HONESTLY (separate from pass-rate) → RATCHET so a new unit without an expectation fails. CW = one cw_core + three oracle families on one delivery axis — Source (SCM) → Delivered (DCM/FCM) → Live (API/CLI/MCP/FE=TOW).

You never choose a tool. This command DETECTS the project flavor at invocation and APPLIES the matching adapter family. The methodology is rules/conformance-walk.md (the four MUST clauses) + skills/conformance-walk/SKILL.md (the model); the per-flavor runbook this command drives is skills/conformance-walk/command-runbook.md.

1. Detect the project flavor (auto — never asked)

Read the repo's manifest files (Cargo.toml, pyproject.toml / setup.py, package.json, Gemfile) and look for kailash markers (a kailash* crate/package dependency, or a shipped conformance-walk/ engine directory). Delegate to stack-detector when the host language is ambiguous. Resolve to exactly one flavor:

kailash-rs — Rust host + kailash markers.
kailash-py — Python host + kailash markers.
other kailash-* — kailash markers, a different host language.
non-kailash — no kailash markers.

Full detection algorithm (signal precedence, tie-breaks, the fail-safe default): skills/conformance-walk/command-runbook.md § Flavor Detection.

2. Select the adapter family (from the detected flavor)

kailash-* (rs / py / other) → the kailash reference adapter FAMILY. Run the CW methodology (the frozen-expectation walk) PLUS the language-specific engine that ships with the kailash SDK: cw_core + the Source, Delivered, and Live adapters. Per flavor: kailash-rs scans crates/** (Source via rustdoc-JSON) + the resolved shipped-feature wheel surface (Delivered) + service-boot (Live); kailash-py scans the package / __all__ / AST surface (Source) + the shipped wheel × binding surface (Delivered) + Live. Where a language lacks a shipped adapter, that surface degrades to core-only rather than failing.
non-kailash → ARTIFACT-ONLY / core-only. Run the CW methodology + cw_core + the consumer's OWN per-surface adapters (each repo authors adapters for the surfaces it exposes, per skills/conformance-walk/SKILL.md § Per-consumer adapter obligation). Surfaces with no applicable adapter degrade gracefully — reported, never faked.

Read the full file on GitHub · 92 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.

7d ago First seen · 92 lines · 37 tokens per session scan A bfdf3c498f4d

Subscribe to this mod's changes

conformance-walk is a command published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 23d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,295 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 2026-09-03.

Testing

prototype

You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.

grainulation/grainulator · 0 tokens

verify

Run repository verification using the verification-loop skill.

cloudnative-co/claude-code-starter-kit · 9 tokens

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

conformance-walk