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-map)<a href="https://agentmods.dev/skills/ali-demirbas/claude-lifecycle/lifecycle-map"><img src="https://agentmods.dev/badge/skills/ali-demirbas/claude-lifecycle/lifecycle-map.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 | $0.00066 | $0.01390 |
| Opus 5 | $0.00033 | $0.00695 |
| Sonnet 5 | $0.00013 | $0.00278 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
lifecycle-map 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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lifecycle Map — Event → Stage Mapping
Turn the event inventory from lifecycle-connect into a stage map and funnel skeleton. This is what makes journey eligibility computable.
When NOT to use this
- No DQS or event inventory exists yet — there is nothing to map; run
lifecycle-connectfirst. - The question is whether a specific automation should be kept, changed, or killed — that's
lifecycle-audit(structural review) orlifecycle-results(outcome-based), not this skill. - The need is an audience query for an already-designed journey — that's
lifecycle-audience. This skill produces the stage map and funnel skeleton, never a runnable query.
Procedure
- If
knowledge/brands/<brand>.mdhasverticalsset: tag every event to a vertical viaevent_prefixmatch first — mechanical name-prefix matching, done before any stage classification. This determines which industry playbook's funnel table and "Event expectations" apply to that event in step 1. An event matching no vertical's prefix falls back to the primary industry, flaggedunclassified-vertical— batch it into the same question as unmappable events (step 3). - First, check for a prior pass: if
output/<project>/event-analysis.jsonexists (written whenlifecycle-connectspawnedevent-analystfor a 50+ event inventory earlier in this same run), its Mapped/Assumed/Unmapped classification is a draft, not a discard-and-redo — confirm or override it below rather than reclassifying every event from zero. Two independent classification passes over the same event risk landing on two different stages for it — treating the first pass as the starting point removes that risk instead of hoping both agree. Absent the file (inventories under 50 events, classified inline bylifecycle-connectitself, or no prior connect run), load the mapping sources fresh, in lookup order:${CLAUDE_PLUGIN_ROOT}/knowledge/event-taxonomy/ga4-recommended-events.md(exact + alias lookup)- the active industry playbook's funnel table (the event's own vertical's playbook, for multi-vertical brands)
${CLAUDE_PLUGIN_ROOT}/knowledge/event-taxonomy/stage-mapping-rules.md(heuristics for unknowns — apply its rules 1→5 in order)
- Classify every event from the inventory. Track WHICH rule classified each one.
- Batch unmappable events into a single question to the user (max 10, best-guess pre-filled). Continue with what is mapped; mark dependent outputs provisional.
- Build the funnel skeleton: order the mapped events along the industry playbook's canonical funnel (one skeleton per vertical, for multi-vertical brands); note observed drop-off between steps if T1 volumes exist — and flag, don't silently build past, any step whose volume exceeds the previous step's. An inverted funnel means a mapping error or a data-integrity problem, not real user behavior; report it as a finding rather than presenting the funnel as if the numbers were trustworthy.
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.
- 5d ago First seen · 61 lines · 66 tokens per session scan A 1b4fce3fc891
lifecycle-map is a skill published in the GitHub repository ali-demirbas/claude-lifecycle (2 stars, last pushed 18d ago), licensed MIT. It adds 66 tokens to every session and 1,390 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-source
Use when the user wants to add, edit, disable, or remove a job-listing source that /refresh-listings sweeps. Triggers: /add-source, "add a source", "also pull from ", "stop pulling from LinkedIn", "I only want DOU", "just parse these links for me". Edits config/sources.json (the source list, crossLink toggle…