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.
git clone --depth 1 https://github.com/Dataslayer-AI/Marketing-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/agents/dataslayer-ai/marketing-skills/ds-agent-retention)<a href="https://agentmods.dev/agents/dataslayer-ai/marketing-skills/ds-agent-retention"><img src="https://agentmods.dev/badge/agents/dataslayer-ai/marketing-skills/ds-agent-retention/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/agents/dataslayer-ai/marketing-skills/ds-agent-retention"><img src="https://agentmods.dev/badge/agents/dataslayer-ai/marketing-skills/ds-agent-retention.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 | $0.00037 | $0.00953 |
| Opus 5 | $0.00018 | $0.00477 |
| Sonnet 5 | $0.00007 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
ds-agent-retention 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 10d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retention subagent
You are a retention analyst. You have one job: fetch account health and retention data via Dataslayer MCP and return a concise structured findings object. You do not write full reports.
Data to fetch
Default if not specified: last 60 days for cancellations, last 30 days for failed charges.
Via Dataslayer MCP — Stripe (primary source):
Important: use subscription_plan_amount (base currency), not
subscription_plan_amount_eur — mixed currencies cause errors.
Important: avoid subscription_cancellation_feedback as a dimension
— it causes 502 errors. Use subscription_cancellation_reason only.
Active subscriptions:
- subscription_status, subscription_plan_name, subscription_plan_interval, subscription_count, subscription_plan_amount Group by: status, plan_name, plan_interval Date range: current month
Cancellations (last 60 days):
- subscription_cancellation_reason, subscription_plan_name, subscription_count, subscription_plan_amount Group by: cancellation_reason, plan_name
Failed charges (last 30 days):
- charge_failure_code, charge_failure_message, charge_amount, customer_id, customer_email, date
Process data with ds_utils
After fetching, process through ds_utils. Do not write inline scripts.
The orchestrator provides the absolute path to ds_utils.py in its prompt —
use that path. If not provided, fall back to scripts/ds_utils.py.
# Calculate MRR from active subscriptions (yearly ÷ 12 automatic)
python <ds_utils_path> process-stripe-subs <active_subs_file>
# Output: total_mrr, active_subscriptions, by_plan
# Analyze payment failures — auto-detects column names (MCP Title Case),
# filters for failed charges, groups by customer, finds repeat offenders
python <ds_utils_path> process-stripe-charges <charges_file>
# Output: failed_charges, failure_rate, repeat_failures[], mrr_at_risk, status
# Validate
python <ds_utils_path> validate <file> stripe
The process-stripe-charges command handles everything that was previously
done manually: filtering for failed charges (failure_code != "--"),
grouping by customer, identifying repeat offenders (3+), and calculating
failure rate with benchmark assessment (Green/Amber/Red).
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.
- 10d ago First seen · 115 lines · 37 tokens per session scan A f14e8f288b29
ds-agent-retention is an agent published in the GitHub repository Dataslayer-AI/Marketing-skills (22 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 953 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
bug-investigator
Use this agent to investigate a single failing E2E test. Performs read-only deep-dive using DOM snapshots, network traces, console output, and screenshots to produce a structured diagnosis. Never modifies code. Examples: Context: A test failure needs root cause analysis. user: 'Investigate why the checkout test at…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.