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 myclaude-sh/myclaude-creator-engine --skill creategit clone --depth 1 https://github.com/myclaude-sh/myclaude-creator-engineWrote 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/myclaude-sh/myclaude-creator-engine/create)<a href="https://agentmods.dev/skills/myclaude-sh/myclaude-creator-engine/create"><img src="https://agentmods.dev/badge/skills/myclaude-sh/myclaude-creator-engine/create/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/myclaude-sh/myclaude-creator-engine/create"><img src="https://agentmods.dev/badge/skills/myclaude-sh/myclaude-creator-engine/create.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 | $0.00052 | $0.06903 |
| Opus 5 | $0.00026 | $0.03452 |
| Sonnet 5 | $0.00010 | $0.01381 |
| Haiku 4.5 | $0.00005 | $0.00690 |
Grade A, and why
create 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 9d 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffolder
Generate complete, MCS-1-valid project structure for any product type with guidance comments baked in.
When to use: Starting a new product — any of the 13 types.
When NOT to use: When the product already exists in workspace/ and you want to add content (use /fill). Do not use to overwrite an existing scaffold unless --force is specified.
Activation Protocol
- Shared preamble: Load
references/quality/activation-preamble.md— context assembly, persona adaptation, deterministic routing rules. - Read
creator.yaml— load defaults. Checkschema_version:< 3→ invoke/onboardskill to run Phase 2.5d silent migration first. Migration is atomic + backed up tocreator.yaml.bak.v2. After migration succeeds, re-read the v3 file and continue.- Missing → micro-onboard: scan silently, infer defaults, ask ONE name question, generate minimal
creator.yaml(v3). Never block.
- Persona: Adapt to
profile.type+technical_level. Loadreferences/quality/engine-voice-core.md. Load the fullreferences/quality/engine-voice.mdonly when composing peak moments (scaffold celebration, Step 10 proposal rendering, first-product WOW). 2c. Exemplar load: Loadreferences/quality/exemplar-outputs.mdsection E3 only — the scaffold celebration reference. Your scaffold announcement MUST carry the same visual rhythm (Frame + pipeline position + portfolio context + 🎯 next action). Adapt to this creator's language and journey position. 2d. Load proactives: Loadreferences/engine-proactive.md— wire #1 (pipeline guidance: after scaffold, guide to /fill), #18 (WOW moment for first product scaffold), #21 (portfolio pattern detection on brownfield check). 2b. Load architectural DNA: Readstructural-dna.md. The 10 architectural principles and the Tier 1 DNA patterns (D1-D4, D13, D14) govern every scaffold — the skill applies them during Step 11 template generation and flags any violation before the scaffold is written to disk. - Discovery Mode Routing (W3.2 — PRIMARY ROUTER): Load
${CLAUDE_SKILL_DIR}/references/create-router.mdSection 0 — the 12-step discovery walk. Apply the Mode Selection table (Express vs Guided) based oncreator.profile.technical_level+creator.preferences.workflow_style+ any--express/--discoveryflag.- Express mode → run the "12 Steps — Express Mode Fast Path" section of create-router.md Section 0. Reads type + sub-type flags, applies defaults from
config.yaml routing.{type}.intent_topology, skips interactive questions, derives the full 19-fieldintent_declarationin one pass, and writes it at Step 11 of the walk. - Guided mode → run the "12 Steps — Guided Mode Walk". Asks Q1 (verb family) interactively, reads
creator.intent_profilesilently for Steps 2/3/6, escalates at Step 6 if cognitive justification incomplete, proposes form at Step 10 with confirmation, writesintent_declarationat Step 11. - Discovery returns unroutable (Step 9 zero-match) → fall through to create-router.md Section 1 legacy Q1/Q2/Q3 tree (Contract C4). The creator is never blocked.
unroutable: true+unroutable_reasonrecorded inintent_declaration. - Creator chose "I don't know yet" at Step 1 → route to
/scoutsuggestion OR legacy tree, at creator's choice.
- Express mode → run the "12 Steps — Express Mode Fast Path" section of create-router.md Section 0. Reads type + sub-type flags, applies defaults from
- Gates: Read
config.yaml → gates.confirm_create. Confirm iftrue; proceed iffalse. - Brownfield check: Glob
workspace/*/. If sameproduct.typeor overlapping tags found, surface slugs and ask before continuing. - Exemplar guard: Glob
references/exemplars/{category}*. If found: show condensed preview. If not: skip gracefully — never halt. - Load
product-dna/{category}.yaml→ DNA requirements. 7b. Load entity ontology (squad/system/agent/workflow/minds): If type ∈ {squad, system, agent, minds, workflow}, readreferences/entity-ontology.md. This substrate governs:- Which agent ROLES to suggest during composition discovery (§AGENT_ROLES — 7 functional archetypes with tool boundaries)
- The heritage chain — what this type inherits from and composes with (§HERITAGE, §COMPOSITION)
- The 8 squad anatomy components that MUST appear in the scaffold (§SQUAD_ANATOMY)
- The intelligence gradient — where this type sits in the determinism↔autonomy spectrum (§INTELLIGENCE_GRADIENT)
- The distinction between workflow (YAML decides) and squad (LLM decides) coordination (§WORKFLOW_VS_SQUAD)
- Promotion/demotion heuristics — is this really the right type? (§HEURISTICS)
- Runtime behavior — how this type activates and its token cost (§RUNTIME_BEHAVIOR)
- For /scout-informed creates: type recommendation matrix (§SCOUT_INTELLIGENCE)
- Isomorphic human↔CC mapping for creator-facing explanations (§ISOMORPHIC)
- For type=system ONLY: the 13 functional gears (§SYSTEM_ENGINES) — ask which gears the creator wants active, scaffold coupling declarations
- The intelligence pipeline that governs how scout research enters the product (§INTELLIGENCE_PIPELINE)
- The foundational thesis: restrictions generate intelligence flow — ask "What should this NEVER do?" (§FOUNDATIONAL_THESIS)
- Transversal axes: after type selection, calibrate Delivery × Nature × Depth (§TRANSVERSAL_AXES)
- Composition principles: how products think together — convergence by independence, symbiosis > aggregation (§COMPOSITION_PRINCIPLES)
- Load
${CLAUDE_SKILL_DIR}/references/discovery-questions.md→ category questions. - Load
references/product-specs/{category}-spec.md+templates/{category}/. - Load
workspace/domain-map.mdif exists → prefill scaffold sections. 10b. Link scout report if used —scout_sourceis already recorded inintent_declaration.scout_sourceby Section 0 Step 11. No additional action needed here; the canonical home for scout_source isintent_declaration, not a parallel field. 10c2. CLI contract: Loadreferences/cli-contract.mdfor unified error handling. This skill has minimal CLI surface — one command at Step 1.5. Severity map:
- Silent-skip:
search --category {type} --sort downloads --limit 3— marketplace scan for competitive context. Skip without warning on failure. First-product guard: skip entirely ifis_first_product(already documented at Step 1.5) - All queries: append
--json 2>/dev/null, 15s timeout 10c. Portfolio intelligence (back-reference from /validate): ReadSTATE.yaml → workspace.products[]ANDSTATE.yaml → mcs_results. Group by domain. If domain has existing products: - Show: "Your {domain} portfolio: {slugs}. This will be product #{N}."
- If N >= bundle threshold (
config.yaml → intelligence.portfolio.bundle_suggestion_threshold): suggest bundling. - If complementary type opportunity exists: surface composition suggestion.
- MCS target calibration: If domain has 0 products → default MCS-1 (ship fast, test market). If domain has 2+ validated products → default MCS-2 (quality matters, audience exists).
- Record
intelligence.domainandintelligence.market_positionin.meta.yaml.
- Generate scaffold in
workspace/{product-slug}/with DNA patterns + WHY comments. The scaffold's type + structure come from thematched_cell.canonical_formdecided at Section 0 Step 10. Ontology-aware scaffold verification (requires entity-ontology.md loaded at step 7b): For type=squad: verify scaffold contains all 8 anatomy components from entity-ontology.md §SQUAD_ANATOMY:- Agent roster (agents/) — each specialist as separate .md file with role-appropriate frontmatter
- Routing table (config/routing-table.md) — IF intent → agent mapping with judgment points
- Handoff protocols (config/handoff-protocol.md) — structured envelope format (from, to, task, state, constraints)
- Workflows (workflows/) — multi-agent sequences with gates and loops
- Skills-as-instruments (skills/) — reusable fragments agents invoke
- Checklists — deterministic verification section in SQUAD.md
- Templates — output format standards in kernel/
- Escalation/quality gates — confidence thresholds and loop limits in SQUAD.md
For type=agent or type=minds: apply §AGENT_ROLES — the role selected during discovery determines frontmatter tool boundaries (
allowed-tools/denied-tools) and handoff format expectations. Generate role-appropriate frontmatter. For type=workflow: verify scaffold distinguishes from squad per §WORKFLOW_VS_SQUAD — workflows use skills (not agents), fixed sequence (not LLM routing), deterministic gates (not judgment). If scaffold looks like a squad, surface heuristic coaching. For type=system: apply §HERITAGE — system inherits all squad DNA + adds CLAUDE.md fragment, hooks, output-style, STATE.yaml. Scaffold must include provisions for all composed types per §COMPOSITION. For type=system: apply §SYSTEM_ENGINES — scaffold agears_declarationsection in the system's primary file. Ask the creator: "Which of these organism capabilities do you want active?" Present the 13 gears grouped by function:
- Boundary: E0 (clausura) — always required
- Metabolism: E1 (token budget), E2 (constitution re-injection)
- Memory: E3 (triple memory), E10 (persistent state)
- Perception-Reflex: E4 (hooks perception), E5 (cognitive reflex)
- Judgment-Coordination: E6 (isolated judgment), E7 (coordination network)
- Identity: E8 (external voice)
- Integrity: E9 (recursive validation), E11 (longitudinal self-observation — advanced, MCS-3)
- Lifecycle: E12 (reversible install/uninstall)
For each active gear, the scaffold includes a section with WHY comment and its counterpart declaration.
11b. Locale-adaptive clause substitution (W3.6 — MANDATORY for 6 certified types): For each template file written (SKILL.md, AGENT.md, SQUAD.md, CLAUDE.md for system, AGENT.md for minds, OUTPUT-STYLE.md), perform placeholder substitution for
{{LOCALE_ADAPTIVE_CLAUSE}}: a. Read the canonical clause block fromreferences/locale-adaptive-clause.md §2(the fenced markdown block between<<< LOCALE-ADAPTIVE CLAUSE ... >>>and<<< END CLAUSE >>>, inclusive). b. Read the localized header fromconfig.yaml → routing.common.locale_adaptive_clause.localized_header_catalog.{creator.language}. If the creator's language is not in the catalog, use thefallbackentry and emit an advisory note. c. Build the substitution block:<!-- {localized_header} -->\n\n{canonical_clause}. d. Replace the literal string{{LOCALE_ADAPTIVE_CLAUSE}}in each written template file with the substitution block. Use a literal-string replace, not a regex — the placeholder is unique and must not be interpreted. e. Verify post-substitution: the forged file must contain both marker strings (<<< LOCALE-ADAPTIVE CLAUSE (runtime contract, do not edit) >>>and<<< END CLAUSE >>>). If either marker is missing after substitution, the forge fails + rollback. e2. Duplication guard: Before substitution in step (d), check if the target file ALREADY contains the marker<<< LOCALE-ADAPTIVE CLAUSE. If found, skip substitution for that file and emit advisory: "Locale clause already present in {file} — skipping to prevent duplication." This handles re-forge (--force) scenarios where the template already carried a clause from a prior run. f. For typesquad, also perform the substitution on every file inworkspace/{slug}/agents/*.md(sub-agents inherit the clause perreferences/locale-adaptive-clause.md §4). g. For typesystem, also perform the substitution on every sub-part file (claude-md fragment, sub-agents, sub-squads) per §4. h. Recordintent_declaration.language(already populated at Section 0 Step 11) as the source language used for the lookup — this becomes thesource_languagefield in vault.yaml at /package time.
- Create
.meta.yaml(see template below). Theintent_declarationblock is already populated from Section 0 Step 11; the rest of the template is filled by this step (product, state, history, intelligence). - Move
workspace/domain-map.md→workspace/{product-slug}/domain-map.mdif loaded. - Atomic commit (Contract C5): write order matters —
.meta.yamlfirst (it is the local source of truth), thenSTATE.yaml decisions_historyappend.- If
.meta.yamlwrite fails: abort, announce failure. Nothing else proceeds. - If
STATE.yamlappend fails after.meta.yamlsucceeds: do not roll back the scaffold. The scaffold on disk is recoverable; a deleted scaffold is not. Instead: logstate.tracking_sync: falsein.meta.yaml, emit Engine-fault voice line — "Scaffold forged but Engine lost tracking. Run /status to resync." — and continue./statuswill detect the orphan on next run and surface it for recovery. - Only report
forge_readywhen both writes succeed without error.
- If
- Engine voice: "Scaffold ready. {N} sections with WHY guidance. Run /fill to start." In Guided mode, also include one-line summary of the cell matched and why: "Forjado como {canonical_form} — {rationale}."
What ships with it
2 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.
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.
- 9d ago First seen · 350 lines · 52 tokens per session scan A 1752494f5103
create is a skill published in the GitHub repository myclaude-sh/myclaude-creator-engine (25 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 6,903 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 2026-08-30.
Other skills, from other repositories
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
foundation-models
On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.
analytics-interpretation
Interpret app metrics and make data-driven decisions. Covers DAU/MAU, retention, LTV, ARPU, App Store Connect analytics, AARRR funnel analysis, cohort analysis, and diagnostic decision trees. Use when user wants to understand their metrics, diagnose problems, or build a data-driven growth plan.
app-namer
Turn an app idea into validated, App-Store-ready name candidates. Use when the user says "name my app", "what should I call it", "app name ideas", "help me name this app", "is this name available", or needs to pick a brandable, ownable name before reserving it in App Store Connect.
in-app-events
Generates In-App Event metadata templates for App Store Connect — event names, descriptions, badge types, image specs, and deep link configuration. Use when creating events for App Store visibility, engagement campaigns, or seasonal promotions.