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 tiktok-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/tiktok-ops)<a href="https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/tiktok-ops"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/tiktok-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/tiktok-ops"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/tiktok-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 | $0.00072 | $0.02450 |
| Opus 5.5 | $0.00029 | $0.00980 |
| Sonnet 5.5 | $0.00014 | $0.00490 |
| Haiku 4.5 | $0.00007 | $0.00245 |
Grade A, and why
tiktok-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 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TikTok Ops
Reviewed 2026-09-14, against TikTok's own docs portal (business-api.tiktok.com/portal/docs).
STATUS.
ttopspasses 102 offline tests and has never been run against a live advertiser. Its offline commands (preflight,audit,budget-check,explain) need no token and are safe to trust; its live commands are a paper guarantee until you prove them. Make the first real run a throwaway campaign at a floor budget, reviewed by a human before anything is enabled.
Start here
| You are… | Read | Then |
|---|---|---|
| Connecting an agent to TikTok Ads for the first time | references/01-mcp-server.md |
official MCP: no app, no API key, browser OAuth |
| About to create anything through MCP | references/00-launch-runbook.md § 5–7 |
ttops preflight → MCP → ttops audit; both offline |
| Handed a token / asked to launch via API | references/00-launch-runbook.md |
create a workspace in a project dir, ttops doctor, then follow the runbook |
In a directory with workspace.json |
references/04-ttops-cli.md |
ttops --json doctor before anything else |
| Hit an error code, a gate, a rejection | references/05-error-catalog.md or ttops explain <code> |
the file it names |
| Asked "can the API even do X" | references/01 § tool surface, then references/03 |
The four facts that cost money if you don't know them
operation_statusdefaults toENABLE. Omit it and your campaign is created live and spending. This is the opposite of Meta. PassDISABLEat campaign, ad group and ad, every time.ttopsforces it and offers no override.- A successful create is not proof the object holds what you sent. TikTok drops unknown keys and fills enum defaults silently. Read every object back and diff it before activating.
- Budget minimums are
base × per-currency ratio, and nine currencies take no decimals. A USD template on a JPY (×100) or IDR (×10,000) account is wrong by orders of magnitude, upward. Runttops budget-check --currency Xbefore writing a spec. - Throttling arrives in the response body, as HTTP 200 with
code40100/40133/40016. Branch on the body code, never on HTTP status — TikTok is not documented to send 429 and handling keyed on status will loop forever without noticing. If a 429 ever does arrive, treat it as throttling too; the rule is "always read the body code", not "429 cannot happen".
What ships with it
24 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.
- pyproject.toml 461 B
- references/00-launch-runbook.md 11 KB
- references/01-mcp-server.md 11 KB
- references/02-api-access-and-tokens.md 7.2 KB
- references/03-api-enums-and-payloads.md 17 KB
- references/04-ttops-cli.md 15 KB
- references/05-error-catalog.md 8.8 KB
- references/06-monitoring-rules-webhooks.md 6.5 KB
- scripts/ttops/__init__.py 96 B runs code
- scripts/ttops/__main__.py 51 B runs code
- scripts/ttops/api.py 10 KB runs code
- scripts/ttops/cli.py 17 KB runs code
- scripts/ttops/currencies.json 2.5 KB
- scripts/ttops/errors.py 15 KB runs code
- scripts/ttops/lifecycle.py 34 KB runs code
- scripts/ttops/mcp.py 21 KB runs code
- scripts/ttops/money.py 6.2 KB runs code
- scripts/ttops/operate.py 11 KB runs code
- scripts/ttops/selftest.py 38 KB runs code
- scripts/ttops/spec.py 28 KB runs code
- scripts/ttops/workspace.py 5.5 KB runs code
- specs/example-traffic-abo.json 1.7 KB
- specs/example-web-conversions-cbo.json 1.7 KB
- specs/example-workspace.json 947 B
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 · 160 lines · 72 tokens per session scan A 1ce2b2931da4
tiktok-ops is a skill published in the GitHub repository sergeyizmailov/knowledge-delta-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 2,450 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 2026-09-15.
Other skills, from other repositories
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
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.
accessibility
Use when working on accessibility, a11y, WCAG, ARIA, screen readers, keyboard nav, focus order, contrast, alt text, captions, reduced motion, or target sizes; not language/culture/device (see inclusive-design).
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
excalidraw-architect
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…
launch-workflow
Launch Nextflow pipeline executions on cloud and HPC clusters via Seqera Platform. Use when the user wants to run/launch/submit a pipeline on a cloud or cluster compute environment, configure a compute environment, push pipeline changes to GitHub before launching, or sign in to Seqera Platform.