A process for turning unfinished database-dependent unit tests into integration tests, which check several parts working together with a real database.

Use it to derive integration tests from existing test stubs, fix failing implementation, and reconcile the results.

It makes expected behavior testable across the full system instead of leaving important paths as placeholders.

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/integrate/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/integrate/github.svg)](https://agentmods.dev/skills/prebid/salesagent/integrate)

Your own site

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

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,510 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00084	$0.01510
Opus 5.5	$0.00034	$0.00604
Sonnet 5.5	$0.00017	$0.00302
Haiku 4.5	$0.00008	$0.00151

Measured 1mo ago against content hash adf14bfa23b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

integrate 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/integrate/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integration Tests from Stubs

Derive integration tests from existing unit test xfails (Bucket A: "requires real DB") and UNSPECIFIED stubs that exercise DB-dependent paths. Each stub's expected behavior is absolute truth — if the integration test fails, fix production code, never adjust the expected behavior.

Args

/integrate <entity-name-1> [entity-name-2] ...

Entity names (space-separated): creative, media-buy, delivery. Each must already have a unit test suite from /surface.

Hard Gate: Pre-Check

The catalog atom checks if tests/unit/test_{entity}.py exists. If not:

┌──────────────────────────────────────────────────────────┐
│  STOP: No entity test suite for {entity}.                │
│                                                          │
│  Run `/surface {entity}` first to create the             │
│  test surface map with obligations and stubs.            │
│                                                          │
│  Integration tests derive from the surface — no surface, │
│  nothing to derive from.                                 │
└──────────────────────────────────────────────────────────┘

Protocol

Step 1: Cook the molecule

python3 .claude/scripts/cook_formula.py \
  --formula .claude/formulas/integration-from-stub.yaml \
  --var "ENTITY_NAMES={all_args}" \
  --epic-title "Integrate: {all_args}"

Dry run first (recommended):

python3 .claude/scripts/cook_formula.py \
  --formula .claude/formulas/integration-from-stub.yaml \
  --var "ENTITY_NAMES={all_args}" \
  --epic-title "Integrate: {all_args}" \
  --dry-run

Step 2: Walk the molecule

bd ready → bd show <atom-id> → read description → execute → bd close <atom-id> → repeat

Each entity goes through 9 atoms:

catalog → review → triage → architect → write-integration → fix-green → reconcile-xfail → verify → commit

Barrier serialization: Entities execute in parallel within each atom phase, but write-integration waits for ALL entities' commit from the previous barrier (if any) to complete. This prevents merge conflicts.

Read the full file on GitHub · 154 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 Changed adf14bfa23b4
1mo ago First seen · 154 lines · 84 tokens per session scan A fed3307f2572

Subscribe to this mod's changes

integrate is a skill published in the GitHub repository prebid/salesagent (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 1,510 once invoked, about $0.0003 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 2026-09-01.

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