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/prime/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/prime)<a href="https://agentmods.dev/skills/prebid/salesagent/prime"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/prime/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/prime"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/prime.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 | $0.00058 | $0.01345 |
| Opus 5.5 | $0.00023 | $0.00538 |
| Sonnet 5.5 | $0.00012 | $0.00269 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
prime 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prime
Produces a falsifiable orientation for the tickets in this worktree, then stops. No plan, no code — the point is to know what is true before proposing anything.
This skill does not restate the rules
CLAUDE.md and tests/CLAUDE.md are already loaded in every session. They own
the architecture patterns, the test-integrity policy, the DRY invariant and the
spec-grounding gate. Do not summarise them here or in your output.
A second copy of a rule drifts from the first, and drifted guidance in this repo has repeatedly sent people at the wrong thing: a stale comment blaming "generic-step shadowing" pointed at a bug fixed weeks earlier and cost about a week; a ledger mis-cited its own graduation three separate times; a memory note asserting a macOS/Linux duplication skew caused a legitimate ratchet improvement to be reverted three times before anyone measured it.
So: rules live in CLAUDE.md. This skill produces only what is
ticket-specific and dynamic — things that change per ticket and can be
checked.
Steps
1. Read the tickets
cat TICKETS
gh issue view <n> --repo prebid/salesagent --comments
Read the comments, not just the body. In this repo the sharpest constraint is
often in a comment — and several issues carry a Measured on: <branch> @ <sha>
header. If it does, grep that tree, not yours. Four issues were once
declared false-premise because someone grepped only the checked-out branch; the
symbols were real, on the branch the author measured. Before writing "X does not
exist", run git log --all -S"X" --oneline.
2. Ground against the pinned AdCP version
Resolve the pin, do not assume it:
grep -n 'adcp==' pyproject.toml
grep -n 'targets AdCP spec' docs/adcp-spec-version.md
Then read the spec at that version — the worktree at ~/projects/adcp is
usually checked out somewhere else, so always go through git show:
cd ~/projects/adcp && git show v<PIN>:dist/schemas/<PIN>/<area>/<file>.json
cd ~/projects/adcp && git show v<PIN>:dist/docs/<PIN>/building/implementation/<tool>.mdx
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 · 134 lines · 58 tokens per session scan A 03aa17da25cc
prime is a skill published in the GitHub repository prebid/salesagent (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 1,345 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 2026-09-04.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.