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 elie222/atom-eve --skill revenue-pulsegit clone --depth 1 https://github.com/elie222/atom-eveWrote 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/elie222/atom-eve/revenue-pulse)<a href="https://agentmods.dev/skills/elie222/atom-eve/revenue-pulse"><img src="https://agentmods.dev/badge/skills/elie222/atom-eve/revenue-pulse/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/elie222/atom-eve/revenue-pulse"><img src="https://agentmods.dev/badge/skills/elie222/atom-eve/revenue-pulse.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 | $0.00033 | $0.00880 |
| Opus 5.5 | $0.00013 | $0.00352 |
| Sonnet 5.5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
revenue-pulse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revenue & churn pulse workflow
You produce a grounded weekly revenue & churn pulse. All numbers come from CLIs
you run in the sandbox with bash. Never invent a figure.
0. Window
Compute the lookback window in Unix seconds. Default 7 days:
UNTIL=$(date +%s); SINCE=$(( UNTIL - 7*86400 ))
1. Stripe facts (stripe CLI)
Auth comes from STRIPE_API_KEY (a restricted, read-only key) in the env.
Every command returns JSON — pipe through jq. Add --live for live data
(default is test mode). Use --limit and paginate with --starting-after.
- New / active subscriptions in the window:
stripe subscriptions list --status active --created "gte=$SINCE" --limit 100 - Cancellations (churn) in the window — read the events, not just current state:
stripe events list --type "customer.subscription.deleted" --created "gte=$SINCE" --limit 100 - Failed payments / dunning risk:
stripe invoices list --status open --created "gte=$SINCE" --limit 100 stripe events list --type "invoice.payment_failed" --created "gte=$SINCE" --limit 100 - At-risk subscriptions (set to cancel, or past_due):
stripe subscriptions list --status past_due --limit 100 stripe get /v1/subscriptions -d "status=active" -d "limit=100" \ | jq '.data[] | select(.cancel_at_period_end == true)'
MRR: derive it from the subscription items' recurring prices
(items.data[].price.unit_amount * quantity, normalized to monthly). Sum across
active subscriptions; do not guess. Compare against the prior window the same way.
stripe get / stripe post give raw API access for anything a resource
sub-command doesn't surface directly.
2. Engagement cross-reference (posthog-cli)
For each at-risk customer, check product engagement. Auth via
POSTHOG_CLI_API_KEY and POSTHOG_CLI_PROJECT_ID.
Use the posthog-cli api workflow. Do not guess tool names or schemas:
posthog-cli api search query
posthog-cli api info <tool>
posthog-cli api call read-data-schema '<json>'
posthog-cli api call <tool> '<json>'
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.
- 2mo ago First seen · 101 lines · 33 tokens per session scan A 4892177cc033
revenue-pulse is a skill published in the GitHub repository elie222/atom-eve (53 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 880 once invoked, about $0.0001 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 2026-08-30.
revenue-pulse compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| revenue-pulseelie222/atom-eve | Skill | 53 | 4mo ago | MIT | A | 33 | Claude Code, Codex |
| cost-efficiency-analyzerawslabs/agentcore-samples | Skill | 3.5k | yesterday | Apache-2.0 | A | 98 | Claude Code, Codex |
| tinker-training-costsynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 55 | Claude Code, Codex |
| check-deckginlix-ai/LangAlpha | Skill | 2.2k | yesterday | Apache-2.0 | A | 63 | Claude Code, Codex |
| check-modelginlix-ai/LangAlpha | Skill | 2.2k | yesterday | Apache-2.0 | A | 72 | Claude Code, Codex |
| chart-annotationginlix-ai/LangAlpha | Skill | 2.2k | yesterday | Apache-2.0 | A | 43 | Claude Code, Codex |
| omh-spend-gaterlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 110 | Claude Code, Codex |