What is author-bdd-steps?

A guide for adding BDD step definitions to automated tests. BDD, or behaviour-driven development, describes expected behaviour as readable scenarios and connects each scenario line to code that runs it.

Use it to add or connect scenario steps, verify them against the specification, and prove they work across the supported transports.

It helps new steps follow the project's pinned specification and test harness instead of using incompatible, hand-written request or error handling.

How prebid/salesagent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to prebid/salesagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/prebid/salesagent/main/.claude/skills/author-bdd-steps/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/prebid/salesagent

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/skills/prebid/salesagent/author-bdd-steps/github.svg)](https://agentmods.dev/skills/prebid/salesagent/author-bdd-steps)

Your own site

<a href="https://agentmods.dev/skills/prebid/salesagent/author-bdd-steps"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/author-bdd-steps/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/skills/prebid/salesagent/author-bdd-steps"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/author-bdd-steps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,646 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	$0.00098	$0.02646
Opus 5.5	$0.00039	$0.01058
Sonnet 5.5	$0.00020	$0.00529
Haiku 4.5	$0.00010	$0.00265

Measured 1mo ago against content hash 939d8f03b142, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

author-bdd-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 1mo 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/skills/author-bdd-steps/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring BDD Steps

Normative rules live in tests/CLAUDE.md §"BDD authoring discipline (the five rules)" and §"Error Verification Policy" — read those first; this skill is the wiring guide for applying them while writing a step, not a restatement. tests/bdd/CLAUDE.md has the quick-reference helper table.

Do not follow the generic qa-bdd:step-development plugin skill for this project. Its When-step template is except Exception as exc: ctx["error"] = exc — the exact hand-stash antipattern rule 2 forbids. It predates this repo's harness and doesn't know dispatch_request or the wire-envelope helpers exist.

1. Authority gate

Locate the scenario in its generated tests/bdd/features/BR-UC-*.feature — that file (mirroring the pinned schema + storyboard) is the authority, not the step body and not a docs/test-obligations/ bootstrap artifact. Spec-cite before writing code:

uv run python -c "import adcp; print(adcp.get_adcp_spec_version())"   # confirm the pin, docs/adcp-spec-version.md
git -C ~/projects/adcp show v3.1.1:dist/schemas/3.1.1/core/<schema>.json

If the scenario's wording diverges from what the schema actually requires, fix the scenario (generated features can be edited locally — mirror the diff upstream) rather than coding to a wrong scenario. Cite the divergence with the spec version + path.

2. Wireability gate (HARD STOP)

Before writing a When, confirm the domain env this scenario needs can reach the wire:

Which env class serves this scenario? (tests/CLAUDE.md's environment table, or tests/harness/*.py.)
Does dispatch_request (tests/bdd/steps/generic/_dispatch.py) already route this tool/domain through call_via? If yes, use it — it's the ONE writer of ctx["result"] / ctx["wire_response"] / ctx["wire_error_envelope"].
If the env or route doesn't exist yet: wire it first (add the env method, or extend _dispatch.py's routing), or single-transport-tag + xfail-route the scenario with an explicit wiring-gap reason. Do this instead of reaching for a shortcut.

Read the full file on GitHub · 196 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.

1mo ago First seen · 196 lines · 98 tokens per session scan A 939d8f03b142

Subscribe to this mod's changes

author-bdd-steps is a skill published in the GitHub repository prebid/salesagent (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 98 tokens to every session and 2,646 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-19.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

salesagent: Skill for Claude Code