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/verify-spec/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/verify-spec)<a href="https://agentmods.dev/skills/prebid/salesagent/verify-spec"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/verify-spec/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/verify-spec"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/verify-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00057 | $0.01581 |
| Opus 5.5 | $0.00023 | $0.00632 |
| Sonnet 5.5 | $0.00011 | $0.00316 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
verify-spec 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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Verification
Verify that every test in entity surface suites reflects actual protocol behavior as defined by the authoritative sources. Adds traceability links and flags discrepancies before we commit to changing production code.
Args
/verify-spec <entity-name-1> [entity-name-2] ...
Entity names (space-separated). Each must already have a test suite from
/surface. If the suite doesn't exist, the formula STOPS at pre-check.
Why This Step Exists
The pipeline from spec to test has multiple translation layers:
adcp spec repo (JSON schemas, OpenAPI)
↓ interpreted into
adcp-client-python (Pydantic models)
↓ extracted into
docs/test-obligations/ (requirements artifacts)
↓ mapped into
tests/unit/test_{entity}.py (surface tests + stubs)
Each arrow can introduce errors. Before /remediate changes production code
to make tests pass, we must confirm the tests expect the RIGHT behavior.
Sources of Truth (Priority Order)
-
adcontextprotocol/adcp— The protocol spec. JSON schemas atdist/schemas/3.0.0-beta.3/core/, OpenAPI atstatic/openapi/. Local clone:../adcp(commit-pinned). GitHub:https://github.com/adcontextprotocol/adcp -
adcontextprotocol/adcp-client-python— The Python implementation. Pydantic models atadcp/types/generated_poc/. Local clone:../adcp-client-python(upstream remote). GitHub:https://github.com/adcontextprotocol/adcp-client-python -
adcp-req(derivative, NOT authoritative) — Requirements artifacts at../adcp-req/docs/requirements/. Useful as an INDEX with source links back to (1) and (2). Follow those links to confirm faster than researching from scratch. Never treat adcp-req as the source of truth itself.
Entity to Spec File Mapping
| Entity | JSON Schemas (adcp repo) | Python Types (adcp-client-python) | adcp-req Index |
|---|---|---|---|
| creative | creative-manifest.json, creative-asset.json, creative-variant.json, creative-filters.json, creative-assignment.json, creative-policy.json, format.json, format-id.json | media_buy/sync_creatives_, media_buy/list_creatives_ | BR-UC-006/ |
| media-buy | media-buy.json, package.json, pricing-option.json, targeting.json, brand-ref.json | media_buy/create_media_buy_, media_buy/update_media_buy_ | UC-002/, UC-003/ |
| delivery | delivery-metrics.json, reporting-webhook.json, reporting-capabilities.json | media_buy/get_media_buy_delivery_* | UC-004/ |
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 2669955f6545
- 1mo ago First seen · 173 lines · 57 tokens per session scan A b5b78bef2016
verify-spec is a skill published in the GitHub repository prebid/salesagent (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 1,581 once invoked, about $0.0002 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.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.