Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ali-demirbas/claude-lifecycle/plugin install claude-lifecycleWrote 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/ali-demirbas/claude-lifecycle/lifecycle-intake)<a href="https://agentmods.dev/skills/ali-demirbas/claude-lifecycle/lifecycle-intake"><img src="https://agentmods.dev/badge/skills/ali-demirbas/claude-lifecycle/lifecycle-intake.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.02367 |
| Opus 5 | $0.00034 | $0.01184 |
| Sonnet 5 | $0.00014 | $0.00473 |
| Haiku 4.5 | $0.00007 | $0.00237 |
Grade A, and why
lifecycle-intake 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 8d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lifecycle Intake — Structured Gap Filling
Collect ONLY the information that changes the output. Maximum 2 rounds of questions; each round is one message with grouped, numbered questions and pre-filled defaults the user can accept with "defaults ok".
When NOT to use this
- Invoked cold, before any pipeline stage has identified what it actually needs. This skill exists to fill gaps
lifecycle-journeys/lifecycle-copyname, not to front-load a generic questionnaire — asking before a real gap is known risks collecting answers nothing downstream consumes, which the whitelist gate exists specifically to prevent. - A brand config already answers everything a stage needs — there's nothing to ask; proceed straight to the stage that would have triggered intake.
- The user is describing a preference for a single generated artifact (e.g. "bu journey'i daha kısa yap") — that's a direct edit request to the owning skill, not a structured gap to collect.
What may be asked (the whitelist)
Ask a question only if its answer is (a) not derivable from connected data, and (b) actually consumed by a downstream step:
| Topic | Consumed by | Ask when |
|---|---|---|
| Primary goal (growth / retention / revenue / reactivation) | journey prioritization | Always, unless user already stated it |
| Product rhythm — how often a typical user engages/purchases (daily / weekly / occasional-seasonal, with the actual cadence) | every lapse window, dormancy threshold, and cadence | Always on T3 (it is the only way to set winback/reactivation clocks without data); on T1/T2 only if not computable from median gaps |
| Channel inventory + rough audience size per channel | step channel selection | Always on T2/T3; on T1 only if not inferable |
| Existing automations (what already runs) | dedupe — don't generate what exists | Always |
Multi-vertical product lines — does the company run genuinely separate product lines, each with its own funnel and conversion event (not just several features sharing one funnel)? If yes: each vertical's name, its closest knowledge/industries/ fit, and how its events are named (e.g. "do the wallet features' events all start with wallet_?") |
brand config verticals; per-vertical DQS/funnel/pattern-priorities in connect/map/journeys |
When the event inventory shows 2+ event-name clusters with no shared conversion event, or the user volunteers it |
| Brand tone (2–3 adjectives) + formality (sen/siz, formal/informal) | lexicon calibration | Before any copy |
| Incentive policy (may journeys offer discounts? max % + is there a CLV threshold above which value-adds replace discounts — priority support, early access, extended feature trial) | incentive-gated steps: above the CLV bar prefer a value-add (protects margin, doesn't train price expectations); below it a capped discount. Threshold comes from the account's real unit economics, never a guessed round number. If the user doesn't know their CLV: skip the value-add/discount split, default to capped-discount-only, and record the threshold as an open gap — never guess a number to fill it | If sector uses incentives |
| Sector-specific questions | industry playbook "Intake questions" section | On T3, or when playbook flags them |
| Known campaign calendar (dated peak/sale windows) | knowledge/calendar-rules.md — campaign-vs-evergreen conflict review | If the sector runs seasonal campaigns; silence = rules dormant, portfolio notes it |
| One-click unsubscribe implemented in the ESP (header pair, not just a footer link)? | knowledge/deliverability.md floor | If email volume is meaningful (bulk-sender territory) |
| Target language(s) for copy | lifecycle-copy | Before any copy |
| Legal market(s) | compliance defaults | If not obvious from GA4 geo/user context |
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.
- 8d ago First seen · 102 lines · 68 tokens per session scan A d2a49c262653
lifecycle-intake is a skill published in the GitHub repository ali-demirbas/claude-lifecycle (2 stars, last pushed 20d ago), licensed MIT. It adds 68 tokens to every session and 2,367 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
geo-optimization
Use when the user wants to improve their AI visibility (GEO score) across ChatGPT, Gemini, Perplexity, Claude, Grok, DeepSeek, Meta AI, and Copilot. Covers the full optimization playbook, what each sub-score rewards, fix prioritization, and discovery stack requirements.
crm-workflow
Use when the user is working with StudioMeyer CRM and you need to pick the right tool. Covers the Lead → Contact → Deal → Pipeline flow, daily CRM routine, and how to run import/export safely.
memory-import-guide
Use when the user wants to import conversation history from ChatGPT, Claude, Gemini, Microsoft Copilot, or Perplexity into StudioMeyer Memory. Covers export steps per platform, file formats, and how to run the import safely.
memory-workflow
Use when the user is working with StudioMeyer Memory and you need to pick the right tool. Covers when to use search vs entity tools vs learn vs decide, how to structure queries, and how to avoid duplicate writes.
persona-usage
Use when the user wants to pick the right Crew persona for a task, combine multiple personas, or understand how personas differ. Covers when to activate which role, how workflows chain them, and how to avoid persona misuse.
add-vacancy
Use whenever the user wants to ingest one or more job vacancies into Job Search HQ. Triggers: /add-vacancy, "add this vacancy", "add these jobs", pasting one or more job URLs, or pasting an aggregator/search URL and asking to expand it. Handles a single URL, a bulk list, or an aggregator page (DOU / Djinni /…