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.
curl -O https://raw.githubusercontent.com/prebid/salesagent/main/.claude/skills/derive-tests/SKILL.mdgit clone --depth 1 https://github.com/prebid/salesagentWrote 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.
[](https://agentmods.dev/skills/prebid/salesagent/derive-tests)<a href="https://agentmods.dev/skills/prebid/salesagent/derive-tests"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/derive-tests/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.
<a href="https://agentmods.dev/skills/prebid/salesagent/derive-tests"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/derive-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.04289 |
| Opus 5.5 | $0.00020 | $0.01716 |
| Sonnet 5.5 | $0.00010 | $0.00858 |
| Haiku 4.5 | $0.00005 | $0.00429 |
Grade A, and why
derive-tests scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
env.mock["post"] # requests.post mock How it starts
The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness-Based Obligation Test Derivation
Write one behavioral test per obligation using the test harness (tests/harness/).
Tests use domain-specific test environments instead of inline @patch decorators,
producing 10-15 line tests instead of 40-50 line tests.
Args
/derive-tests UC-004-MAIN-01 UC-004-MAIN-02
/derive-tests UC-004 --count 10
/derive-tests UC-001-MAIN --count 15
Direct IDs: Space-separated obligation IDs. Prefix mode: Auto-selects uncovered obligations matching the prefix.
Available Harness Environments
| Domain | Env Class | Tests | Production Function |
|---|---|---|---|
| Delivery poll | DeliveryPollEnv |
test_delivery_poll_behavioral.py |
_get_media_buy_delivery_impl |
| Webhook delivery | WebhookEnv |
test_delivery_webhook_behavioral.py |
deliver_webhook_with_retry |
| Circuit breaker | CircuitBreakerEnv |
test_delivery_service_behavioral.py |
WebhookDeliveryService, CircuitBreaker |
| Creative sync | CreativeSyncEnv |
test_creative_sync_behavioral.py |
_sync_creatives_impl |
| Creative list | CreativeListEnv |
test_creative_list_behavioral.py |
_list_creatives_impl |
| Creative formats | CreativeFormatsEnv |
test_creative_formats_behavioral.py |
_list_creative_formats_impl |
Multi-transport support: Creative envs support call_via(transport) dispatch
across IMPL, A2A, and REST transports. See Multi-Transport Pattern.
Protocol
Step 0: Resolve obligation IDs
If args look like a prefix (no trailing -NN sequence number):
python3 -c "
import json
al = json.loads(open('tests/unit/obligation_coverage_allowlist.json').read())
matches = sorted(oid for oid in al if oid.startswith('{prefix}'))
print(' '.join(matches[:N]))
print(f'Total matching: {len(matches)}, selected: {min(N, len(matches))}')
"
Step 1: Harness gate (HARD STOP)
Check if a harness exists for the target domain:
ls tests/harness/*.py
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 · 512 lines · 50 tokens per session scan A 794a44ffdad1
derive-tests is a skill published in the GitHub repository prebid/salesagent (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 4,289 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
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.
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".
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.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.