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 manishiitg/coding-agent-loop --skill activation-retention-intelligencegit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/activation-retention-intelligence)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/activation-retention-intelligence"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/activation-retention-intelligence/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/manishiitg/coding-agent-loop/activation-retention-intelligence"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/activation-retention-intelligence.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 | $0.00024 | $0.00795 |
| Opus 5.5 | $0.00010 | $0.00318 |
| Sonnet 5.5 | $0.00005 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
activation-retention-intelligence 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 20d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activation and Retention Intelligence
Outcome
Lifecycle Analyst measures day-7 activation and day-30 retention for signup cohorts. Growth Experiment Planner consumes a mature observation and proposes one test. Cohort differences do not prove cause or individual churn.
When to use
Use with authorized signup, usage and subscription records. New Customer to First Value covers one account's result; Funnel and Conversion Intelligence covers signup-to-paid conversion. This route compares mature cohorts or records one baseline. An immature cohort waits.
Discovery and user direction
Builder inspects lifecycle definitions, maturity cutoff, source coverage, identity join, owner and existing Crews. It proposes reuse or creation of distinct Lifecycle Analyst and Growth Experiment Planner Crews, then shows the source and review plan in chat. Selection creates no Crew, customer contact, query, variant or schedule.
Required inputs
Record product and tenant, equal signup-cohort windows, eligible-account definition, activation and day-30 retention predicates with versions, identity and exclusion rules, timezone, maturity date, event and billing sources, minimum coverage, owner, metric, guardrail and approval policy. Feedback is optional and needs authorized access.
Plan and AgentWorks tools
- Bind two Crew IDs and Workflow steps. Lifecycle Analyst saves
cohort-retention-observation/v1with source references and one ofcomparable,baseline_firstorpending_maturity. Runpython3 scripts/validate_handoff.py observation <observation.json>as a blocking step. - Stop if the cohort is immature. Otherwise pass the validated file by checked alias. Growth Experiment Planner preserves exact policy, cohort IDs and observed rates, then saves pending
retention-experiment-plan/v1. Runpython3 scripts/validate_handoff.py plan <observation.json> <plan.json>before reporting. - Review the result and test proposal with the owner. Assignment, power calculation, variant launch, customer action and outcome measurement need separately reviewed routes.
What ships with it
13 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.
- examples/cohort-analysis.json 1.3 KB
- examples/cohort-retention-baseline-first.json 1.7 KB
- examples/cohort-retention-observation.json 2.6 KB
- examples/cohort-retention-pending-maturity.json 1.7 KB
- examples/invalid-retention-experiment-plan.json 1.6 KB
- examples/retention-baseline-first-plan.json 1.7 KB
- examples/retention-experiment-plan.json 1.7 KB
- playbook.json 5.5 KB
- references/lifecycle-intelligence-workflow.md 2.9 KB
- references/team-and-handoffs.md 3.3 KB
- scripts/test_validate_handoff.py 3.6 KB runs code
- scripts/validate_handoff.py 10 KB runs code
- SETUP.json 3.2 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.
- 20d ago Changed · +2 lines · -26 tokens per session f12119d4f952
- 1mo ago First seen · 51 lines · 50 tokens per session scan A ef7271dd4500
activation-retention-intelligence is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 24 tokens to every session and 795 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 2026-09-15.
Other skills, from other repositories
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
node-inspect-debugger
See runtime state a console.log cannot reach — set real breakpoints, step, and dump the scope chain of a paused Node/TypeScript process. Use on "set a breakpoint", "inspect runtime state", "console.log isn't enough", "step through this", "what's in this closure at runtime", "attach a debugger". Not a logging or…
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron apps — navigating, forms, clicks, screenshots, data extraction, testing web apps, UI checks, the dashboard Electron shell, or the user's own logged-in Chrome via the browser relay or Panerelay (SSO/2FA). Triggers: "open…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.