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 tracker-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/tracker-ops)<a href="https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/tracker-ops"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/tracker-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/tracker-ops"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/tracker-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 | $0.00067 | $0.00821 |
| Opus 5.5 | $0.00027 | $0.00328 |
| Sonnet 5.5 | $0.00013 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
tracker-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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracker Ops
Count money correctly and automate tracker work. Keitaro + Binom specifics below; the metric rules and daily sync port to any tracker. Baseline 2026-09-03 (Sonnet 5 blind, CPL cohort task): [R] — click-date cohort and pinned attribution window already known; do not expand that section.
Metric rule (NEVER violate)
- "conversions" (Keitaro) can exceed your payout-lead count, but that is
INTEGRATION-SPECIFIC, not an inherent 3.5-4x: the same subid+status
OVERWRITES; extra records come only from distinct
tids or a genuine multi-step funnel. Never do CPL math on "conversions" — the payout metric is ONE event/status; get it from the TL in writing. (Any "3.5-4x" is one setup's ratio, not a law.) - Metric names aren't portable: Keitaro "leads" = status Lead (first event); Binom "leads" ≈ all conversions. Verify semantics per tracker per setup.
- Cross-check: platform-reported lead count ≈ tracker lead count. A big divergence = wrong metric or broken tracking; stop and reconcile before reporting. The "±20%" tolerance is an account-specific baseline you set from a reconciled day, not a universal constant.
- Compute daily CPL in the AD ACCOUNT timezone for both spend and leads. Google's account timezone is permanent (senior-buyer-ops contract #5) — reconcile in the tracker, never by eye.
- Rows with unsubstituted
{{...}}macros: exclude from performance analysis, then classify the cause — bots/crawlers, yes, but also a broken URL template, an unsupported/misspelled macro, or manual/direct traffic. Fix the template if it's yours before blaming traffic.
Route references
| Need | Reference |
|---|---|
| Keitaro: key, report/build, measures, update_costs, postback/S2S, postback drill, gotchas | references/01-keitaro.md |
| Binom: legacy URL-param + v2 REST, reports, cost, postback/S2S | references/02-binom.md |
| CPL math, funnel + anti-fraud metrics, cohort nowcasting, backend optimization contract (status→CAPI event), TMA/bot CAPI without pixel, multi-tracker sync + conversion ledger, ATT asymmetry, mapping, daily routine | references/03-metrics-and-math.md |
Google lane: gclid/gbraid/wbraid, ValueTrack chains, Keitaro/RedTrack Google config, OCI windows + dedup, the 2026-06-15 cutoff, Data Manager events:ingest for new tokens |
references/04-google-lane.md |
What ships with it
4 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.
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 · -1 lines df41b5a694ee
- 1mo ago First seen · 52 lines · 67 tokens per session scan A 499987ed855c
tracker-ops is a skill published in the GitHub repository sergeyizmailov/knowledge-delta-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 821 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 2026-08-31.
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.