triage-conformance-diffs

triage-conformance-diffs is a skill for Claude Code from leifericf/agentic-sdk. It costs 45 tokens per session (901 once invoked), scanned A, original, MIT.

A review process for differences found when two implementations are tested against the same expected behaviour.

In plain words
What is it for?
Use it to classify differential-test failures, record their causes and route fixes.
Why use it?
It separates real bugs from intentional differences and mistakes in the test harness, so issues reach the right owner.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to classify differential-test failures, record their causes and route fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leifericf/agentic-sdk/triage-conformance-diffs
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.

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

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.

agentmods badge for triage-conformance-diffs

README.md
[![agentmods](https://agentmods.dev/badge/skills/leifericf/agentic-sdk/triage-conformance-diffs.svg)](https://agentmods.dev/skills/leifericf/agentic-sdk/triage-conformance-diffs)
Your own site
<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/triage-conformance-diffs"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/triage-conformance-diffs.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 901 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00901
Opus 5 $0.00023 $0.00451
Sonnet 5 $0.00009 $0.00180
Haiku 4.5 $0.00005 $0.00090

Measured 4d ago against content hash 9be632f71cfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

triage-conformance-diffs 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/triage-conformance-diffs/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

triage-conformance-diffs

Classify the divergences a differential conformance probe reported. This is check-conformance applied to diff output instead of source: the finding arrives pre-detected (expected versus actual, byte for byte); the judgment is what the difference is and who owns it. Work one module shard at a time so each verdict lands next to the code that would fix it.

Inputs

The probe's failure verdicts (key, expected from each ground truth, actual), the corpus tuples behind them, the intentional-divergence allowlist, the auto-captured regression files, the ADR store, and any named divergence decisions the project records. Read all of them before classifying anything; most wrong verdicts come from not knowing a divergence was already adjudicated.

The three verdicts

  1. :real-bug. The reference behavior is the contract and the implementation misses it. Includes the quiet variants: a wrong result type that prints differently, an unsupported case passed through silently instead of thrown (a no-fakery violation even when the happy path works), off-by-one realization of lazy input. Route: file one bug entry per root cause (not per tuple; twelve tuples failing on one formatter gap are one bug), mark the tuples pending against it, hand the entry to fix-bug with the auto-captured reproducer. Rank by least surprise: a silent wrong answer outranks a loud error.
  2. :intentional. An ADR or named decision designates the divergence. Route: an allowlist entry whose reason cites the decision (ADR-NN or the decision's name), never a bare "expected". If the divergence is deliberate but no record covers it, it is not intentional yet: invoke record-decision first or downgrade to :real-bug. The allowlist never absorbs open bugs, print noise, or anything you cannot cite.
  3. :artifact. The harness, not the implementation: print-bound mismatch between capture and probe, environment leakage (locale, platform newline) making ground truth machine-relative, a tuple that violated the corpus rules (nondeterminism, ambient effects), two ground truths that disagree with each other. Route: fix the harness or the tuple, then re-capture; never allowlist an artifact, that buries a harness bug in the conformance ledger.

Read the full file on GitHub · 83 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 · 83 lines · 45 tokens per session scan A 9be632f71cfe

Subscribe to this mod's changes

triage-conformance-diffs is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 901 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.

Related

Other skills, from other repositories

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

davila7/claude-code-templates · 45 tokens

experimental-code-coverage-local-debugger

Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.

chromium/chromium · 59 tokens

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens