inspect-steps

A tool for checking whether BDD step definitions test the behaviour described by their scenarios. BDD, or behaviour-driven development, uses readable feature files to describe expected software behaviour.

In plain words
What is it for?
It is for reviewing pytest-bdd step definitions, finding weak or missing assertions, tracing steps back to Gherkin scenarios, and optionally flagging vague feature specifications.
Why use it?
A test can technically pass while checking too little—for example, confirming only that a response exists instead of confirming the feature works. This inspector links each step to its scenarios so missing or weak checks are easier to find.

Skill for Claude CodeCodex

Part of the qa-bdd plugin — 4 skills shipped together

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/postindustria-tech/agentic-toolkit/inspect-steps
Any agent
npx skills add postindustria-tech/agentic-toolkit --skill inspect-steps
Clone the repo
git clone --depth 1 https://github.com/postindustria-tech/agentic-toolkit

Made for: Claude Code, Codex.

Or install qa-bdd, the plugin that ships this one along with the rest of its 4 skills.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,170 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 $0.00104 $0.01170
Opus 5 $0.00052 $0.00585
Sonnet 5 $0.00021 $0.00234
Haiku 4.5 $0.00010 $0.00117

Measured 2d ago against content hash b35f0ba6192c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

inspect-steps 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/inspect_bdd_steps.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/qa-bdd/skills/inspect-steps/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BDD Step Assertion Completeness Inspector (v2 -- Context-Aware)

Inspects BDD step functions for semantic completeness by placing each step in the context of the scenario(s) that use it.

Why Context Matters

v1 asked: "Does this function implement what the step text claims?" A helper that checks "response exists" for "validation should result in valid" would PASS (technically correct for the claim).

v2 asks: "Does this function verify what the SCENARIO intends?" If the scenario tests whether a feature WORKS, checking "response exists" proves input acceptance, not behavioral correctness -- FLAG.

Usage

/qa-bdd-inspect-steps                          # Full pipeline (triage + deep trace)
/qa-bdd-inspect-steps --pass1-only             # Fast triage only
/qa-bdd-inspect-steps --gherkin-quality        # Also flag vague Gherkin specs
/qa-bdd-inspect-steps --steps-dir path/to/steps --features-dir path/to/features

Prerequisites

  • Python 3.10+
  • claude CLI available on PATH (used for LLM triage passes)
  • pytest-bdd project with .feature files and step definition files

Pipeline

  1. Pass 0a: AST scan -- extract step functions from step definitions directory
  2. Pass 0b: Gherkin parse -- extract scenarios from features directory
  3. Pass 0c: Link -- match each Then step to its scenario(s) via text matching
  4. Pass 1 (Sonnet): Context-aware triage -- each Then step shown WITH its scenario chain (Given/When/Then + tags + Examples + postconditions)
  5. Pass 2 (Opus): Deep trace -- architectural judgment on flagged steps
  6. Gherkin quality (optional): Flag scenarios where the specification itself is too vague for a meaningful implementation

Configuration

Default paths (override with CLI args):

  • Steps directory: tests/bdd/steps/
  • Features directory: tests/bdd/features/
  • Output: .claude/reports/bdd-step-audit-<timestamp>.md

Running the Script

python ${SKILL_DIR}/scripts/inspect_bdd_steps.py

# Custom paths
python ${SKILL_DIR}/scripts/inspect_bdd_steps.py \
  --steps-dir tests/bdd/steps \
  --features-dir tests/bdd/features \
  --output reports/bdd-audit.md

# Fast triage only (skip deep trace)
python ${SKILL_DIR}/scripts/inspect_bdd_steps.py --pass1-only

# Include Gherkin quality analysis
python ${SKILL_DIR}/scripts/inspect_bdd_steps.py --gherkin-quality

Read the full file on GitHub · 126 lines

Files

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.

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. 2d ago First seen · 126 lines · 104 tokens per session scan A b35f0ba6192c

Subscribe to this mod's changes

inspect-steps is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,170 once invoked, about $0.0005 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