Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sergeyizmailov/knowledge-delta-skills --skill google-grey-opsgit clone --depth 1 https://github.com/sergeyizmailov/knowledge-delta-skillsWrote 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/sergeyizmailov/knowledge-delta-skills/google-grey-ops)<a href="https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/google-grey-ops"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/google-grey-ops/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/sergeyizmailov/knowledge-delta-skills/google-grey-ops"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/google-grey-ops.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 | $0.00218 | $0.02721 |
| Opus 5 | $0.00109 | $0.01360 |
| Sonnet 5 | $0.00044 | $0.00544 |
| Haiku 4.5 | $0.00022 | $0.00272 |
Grade A, and why
google-grey-ops 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 8d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Grey Ops
Reviewed 2026-09-02. Baseline: Sonnet 5 / Claude Code subagent / 2026-09-02; 2026-09-03 blind cascade task [A] — payment+email cascade named only when prompted.
Launch/operate via API on your own MCC credentials (googleops, 10) + survive aggressive
verticals without losing accounts, domains, payment identities.
googleops/gmcops are NOT yet live-verified (2026-09-03): offline tests only, no run against
a real customer. A human watches the first live plan → apply; record the result in 10.
Start here
| You are… | Read | Then |
|---|---|---|
In a directory with workspace.json |
references/10-googleops-agent-cli.md |
googleops --workspace . --json …; stop reading |
| Handed a developer token / asked to launch anything via API | references/00-launch-runbook.md |
create a workspace in a project dir outside the skill (scripts/specs/example-workspace.json), doctor, then plan → apply → verify → activate |
| Setting up access (OAuth vs service account, MCC, refresh-token death) | 00 §1, google-ads/10 §Access |
back to 00 |
| Merchant Center: gates, link, products | google-feed-ops/04 + gmcops (10) |
grey cascade rules in 12 |
| Hit an error, a gate, a suspension | 00 § "When a step fails" |
the one file it names |
Agent writes a JSON spec; googleops validates, creates PAUSED, reads back, activates.
Never hand-assemble a MutateOperation or call a mutate outside the CLI. New shape → extend
gads_spec/gads_build/gads_verify and test_googleops.py.
Boundary: "buy well" → google-ads · "don't get killed / source accounts / scale" → here ·
"feed and Merchant Center" → google-feed-ops · "count and sync" → tracker-ops ·
"portfolio and TL decisions" → senior-buyer-ops.
Authority: this skill governs grey-vertical execution; google-ads clean-marketing guardrails govern
compliant accounts. Route by lane; do not merge the two normative stances.
The Google model is not the Facebook model
What ships with it
36 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 93 B
- playbooks/dating-loans-apps.md 7.0 KB
- playbooks/finance-crypto.md 5.7 KB
- playbooks/gambling.md 5.9 KB
- playbooks/nutra-health.md 4.9 KB
- pyproject.toml 1.0 KB
- README.md 3.4 KB
- references/00-launch-runbook.md 9.2 KB
- references/01-account-supply-and-identity.md 9.1 KB
- references/02-payments-and-billing.md 6.4 KB
- references/03-domains-trackers-review.md 6.7 KB
- references/04-failure-forensics.md 14 KB
- references/05-review-layer-and-cloaking.md 34 KB
- references/06-verification-selfie-bov.md 8.2 KB
- references/07-geo-isolation.md 3.7 KB
- references/08-surfaces-and-no-path.md 7.0 KB
- references/09-api-errors-grey-response.md 5.5 KB
- references/10-googleops-agent-cli.md 9.1 KB
- references/11-autolaunch-parity.md 4.9 KB
- references/12-merchant-center-grey-lane.md 4.9 KB
- schemas/result.v1.json 642 B
- schemas/workspace.v1.json 1.8 KB
- scripts/gads_build.py 22 KB runs code
- scripts/gads_client.py 3.8 KB runs code
- scripts/gads_spec.py 19 KB runs code
- scripts/gads_verify.py 16 KB runs code
- scripts/gads_workspace.py 5.3 KB runs code
- scripts/gmcops.py 22 KB runs code
- scripts/googleops.py 46 KB runs code
- scripts/sheetfeed.py 15 KB runs code
- scripts/specs/example-pmax-retail.json 1.7 KB
- scripts/specs/example-search.json 1.6 KB
- scripts/specs/example-shopping.json 1.1 KB
- scripts/specs/example-workspace.json 608 B
- scripts/test_googleops.py 12 KB runs code
- uv.lock 157 KB
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.
- 8d ago Changed · +38 lines · +100 tokens per session 1014b2bcc0a8
- 12d ago First seen · 124 lines · 118 tokens per session scan A f3e19a8967cd
google-grey-ops is a skill published in the GitHub repository sergeyizmailov/knowledge-delta-skills (3 stars, last pushed 4d ago), licensed MIT. It adds 218 tokens to every session and 2,721 once invoked, about $0.0011 per session on Opus 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 2026-08-31.
Other skills, from other repositories
langbot-dev
Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth…
stripe-apps
Use when building, modifying, or reviewing a Stripe App — or when the user describes something that implies one (e.g. "add a panel to the customer page", "customize my Stripe Dashboard", "react to Stripe events from my app", "connect my service to Stripe without sharing API keys"). Covers the full app development…
firebase-auth
Use when setting up auth, managing auth state, implementing email/password or social sign-in, handling auth errors, or managing users.
architecture-feature-first
Use when creating a feature, designing folder structure, adding repositories/services/view models, wiring dependency injection, or deciding which layer owns logic.
testing
Verify a Skyvern deployment is working correctly by smoke-testing the backend API, frontend rendering, browser session provisioning, and workflow execution. Use when the user says 'is Skyvern working', 'test my deployment', 'verify the installation', 'smoke test', or needs to check that a self-hosted or local Skyvern…
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.