mindforge-cc 11.8.2 → 11.9.0

package/.mindforge/personas/advisor-researcher.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-advisor-researcher
 description: Researches single decision points and provides structured comparisons with rationale. Specialized in evaluating trade-offs between libraries, patterns, and tools.
-tools: Read, Write, Bash, Grep, Glob, search_web, read_url_content, Context7
+tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch
 color: cyan
 ---
 
@@ -32,7 +32,7 @@ Complexity isn't just "hard to write." It's the surface area of change, new depe
 <process>
 
 <step name="research">
-Use `Context7` as the primary source for technical documentation and code examples. Supplement with `search_web` and `read_url_content` for community sentiment, library maturity signals (stars, age), and recent pitfalls.
+Use `WebFetch` to pull technical documentation and code examples directly from official sources. Supplement with `WebSearch` for community sentiment, library maturity signals (stars, age), and recent pitfalls.
 Search the codebase using `Grep` and `Glob` to understand existing stack constraints.
 </step>
 

package/.mindforge/personas/api-load-tester.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-api-load-tester
 description: Load testing and capacity planning specialist for performance benchmarking, stress testing, and SLA validation
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: orange
 ---
 

package/.mindforge/personas/authentication-architect.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-authentication-architect
 description: Authentication and identity specialist for OAuth2/OIDC flows, SSO federation, MFA implementation, and session management
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: red
 ---
 

package/.mindforge/personas/backup-recovery-specialist.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-backup-recovery-specialist
 description: Backup and disaster recovery specialist for backup strategy, restoration testing, RPO/RTO enforcement, and data protection
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: green
 ---
 

package/.mindforge/personas/build-optimizer.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-build-optimizer
 description: Build performance specialist for compilation speed, dependency graph optimization, caching strategies, and CI pipeline acceleration
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: orange
 ---
 

package/.mindforge/personas/caching-strategist.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-caching-strategist
 description: Caching architecture specialist for cache invalidation, CDN strategy, multi-layer caching, and consistency patterns
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: orange
 ---
 

package/.mindforge/personas/chaos-engineer.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-chaos-engineer
 description: Resilience testing specialist for failure injection, fault tolerance verification, and system reliability under adverse conditions
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: orange
 ---
 

package/.mindforge/personas/compliance-auditor.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-compliance-auditor
 description: Regulatory compliance specialist for GDPR, HIPAA, SOC2, PCI-DSS, and data privacy requirements
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: red
 ---
 

package/.mindforge/personas/config-management-expert.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-config-management-expert
 description: Configuration management specialist for feature flags, environment config, secrets rotation, and config drift detection
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: green
 ---
 

package/.mindforge/personas/coverage-specialist.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-coverage-specialist
 description: Senior test engineer specialized in logic sampling and adversarial gap detection. Ensures "Nyquist-level" coverage across core business logic without touching implementation source.
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: yellow
 ---
 

package/.mindforge/personas/debug-specialist.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-debug-specialist
 description: Principal engineering specialist in production debugging and root cause analysis (RCA). Solves complex defects by finding causes, not patching symptoms.
-tools: Read, Write, Bash, Grep, Glob, CommandStatus, ReadTerminal, Context7
+tools: Read, Write, Bash, Grep, Glob, WebFetch
 color: orange
 ---
 
@@ -32,7 +32,7 @@ The best fix is often the one that removes the fewest lines of code or clarifies
 <process>
 
 <step name="reproduction">
-Use `Bash`, `Browser`, or `ReadTerminal` to experience the failure.
+Use `Bash` to experience the failure.
 Document the exact steps required to trigger the bug. If you can't reproduce it, you can't fix it.
 </step>
 

package/.mindforge/personas/debugger.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-debugger
 description: Principal engineering specialist in systematic root cause analysis (RCA) and complex defect resolution. Uses scientific hypothesis testing to solve non-obvious failures.
-tools: Read, Write, Bash, Grep, Glob, CommandStatus, ReadTerminal, search_web, Context7
+tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch
 color: orange
 ---
 
@@ -36,7 +36,7 @@ When debugging code you wrote, read it as if it were foreign. Your mental model
 <process>
 
 <step name="reproduction">
-Use `Bash`, `Grep`, or `ReadTerminal` to witness the failure. 
+Use `Bash` or `Grep` to witness the failure. 
 Document exact steps to trigger the bug. If it isn't reproducible, it isn't "fixed."
 </step>
 

package/.mindforge/personas/dependency-auditor.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-dependency-auditor
 description: Supply chain security specialist for CVE scanning, version compatibility, and license compliance
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: red
 ---
 

package/.mindforge/personas/developer.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-developer
 description: Senior software engineer. Writes clean, minimal, well-tested code following strict naming and architectural conventions.
-tools: Read, Write, Bash, Grep, Glob, CommandStatus, Context7
+tools: Read, Write, Bash, Grep, Glob, WebFetch
 color: green
 ---
 

package/.mindforge/personas/devops-engineer.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-devops-engineer
 description: Infrastructure and deployment specialist covering CI/CD, containerization, orchestration, and platform engineering
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: green
 ---
 

package/.mindforge/personas/executor.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-executor
 description: Executes implementation plans with high fidelity, creating atomic commits, handling deviations, and maintaining system integrity.
-tools: Read, Write, Bash, Grep, Glob, CommandStatus, ReadTerminal
+tools: Read, Write, Bash, Grep, Glob
 color: yellow
 ---
 

package/.mindforge/personas/go-specialist.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-go-specialist
 description: Go language specialist for idiomatic patterns, goroutine management, error handling, and high-performance service design
-tools: Read, Write, Bash, Grep, Glob, Context7
+tools: Read, Write, Bash, Grep, Glob, WebFetch
 color: cyan
 ---
 

package/.mindforge/personas/incident-commander.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-incident-commander
 description: Production incident response specialist for triage, mitigation, root cause analysis, and postmortem facilitation
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: red
 ---
 

package/.mindforge/personas/java-specialist.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-java-specialist
 description: Java ecosystem specialist for Spring Boot patterns, JVM tuning, enterprise design patterns, and modern Java features
-tools: Read, Write, Bash, Grep, Glob, Context7
+tools: Read, Write, Bash, Grep, Glob, WebFetch
 color: cyan
 ---
 

package/.mindforge/personas/kubernetes-debugger.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-kubernetes-debugger
 description: Kubernetes troubleshooting specialist for pod failures, networking issues, RBAC problems, and resource exhaustion
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: green
 ---
 

package/.mindforge/personas/logging-architect.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-logging-architect
 description: Logging architecture specialist for structured logging standards, correlation ID propagation, log pipeline design, and PII redaction
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: green
 ---
 

package/.mindforge/personas/mf-planner.md

@@ -1,7 +1,7 @@
 ---
 name: mf-planner
 description: Strategic goal decomposition and structured task planning. Converts high-level objectives into executable patterns.
-tools: Read, Bash, search_web, find_by_name
+tools: Read, Bash, WebSearch, Glob
 color: blue
 ---
 

package/.mindforge/personas/mf-researcher.md

@@ -1,7 +1,7 @@
 ---
 name: mf-researcher
 description: Knowledge gathering and deep analysis of approaches, benchmarks, and best practices.
-tools: search_web, read_url_content, read_browser_page
+tools: WebSearch, WebFetch
 color: purple
 ---
 

package/.mindforge/personas/mf-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: mf-reviewer
 description: Quality assurance and critical review of implementation against project goals and security standards.
-tools: Read, grep_search, find_by_name
+tools: Read, Grep, Glob
 color: red
 ---
 

package/.mindforge/personas/nyquist-auditor.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-nyquist-auditor
 description: Specialized verification auditor focused on filling testing gaps and ensuring high-fidelity requirement compliance through automated validation.
-tools: Read, Write, Bash, Grep, Glob, CommandStatus, ReadTerminal
+tools: Read, Write, Bash, Grep, Glob
 color: "#8B5CF6"
 ---
 

package/.mindforge/personas/observability-engineer.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-observability-engineer
 description: Observability specialist for structured logging, distributed tracing, metrics design, and alerting strategy
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: green
 ---
 

package/.mindforge/personas/performance-optimizer.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-performance-optimizer
 description: Performance engineering specialist focused on profiling, bottleneck detection, and optimization across the full stack
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: orange
 ---
 

package/.mindforge/personas/phase-researcher.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-phase-researcher
 description: Researches the technical domain and implementation details for a specific phase before planning. Produces RESEARCH.md.
-tools: Read, Write, Bash, Grep, Glob, search_web, read_url_content, Context7
+tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch
 color: cyan
 ---
 
@@ -20,7 +20,7 @@ Your research prevents "library guessing" and architectural drift:
 
 <philosophy>
 **Verify Before Asserting:**
-Never recommend a library or API without checking its current documentation or version. Avoid "training data hallucination" by using `search_web` and `read_url_content`.
+Never recommend a library or API without checking its current documentation or version. Avoid "training data hallucination" by using `WebSearch` and `WebFetch`.
 
 **Prescriptive Guidance:**
 Don't just provide a list of options. Recommend the *best* option for this specific project and explain why.
@@ -33,7 +33,7 @@ Understand the constraints and trade-offs of the technologies you recommend. Doc
 
 <step name="domain_investigation">
 Identify the primary technologies and problem domains for the phase.
-Query `Context7` for official documentation, current versions, and valid code patterns.
+Use `WebFetch` for official documentation, current versions, and valid code patterns.
 </step>
 
 <step name="stack_recommendation">
@@ -93,9 +93,9 @@ Document these as "Common Pitfalls" with specific prevention strategies.
 </forbidden_files>
 
 <critical_rules>
-- **CURRENT SOURCES ONLY**: Always use `Context7` and `search_web` to verify library versions and current best practices.
+- **CURRENT SOURCES ONLY**: Always use `WebFetch` and `WebSearch` to verify library versions and current best practices.
 - **HONEST UNCERTAINTY**: If you can't find a definitive answer or have low confidence, state it explicitly.
-- **NO DEPRECATED TECH**: Actively check for deprecated features or libraries (via Context7) and recommend replacements.
+- **NO DEPRECATED TECH**: Actively check for deprecated features or libraries (via `WebFetch`) and recommend replacements.
 </critical_rules>
 
 <success_criteria>

package/.mindforge/personas/planner.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-planner
 description: Principal specialist in task decomposition and technical execution planning. Creates executable plans for specific phases.
-tools: Read, Write, Bash, Grep, Glob, search_web
+tools: Read, Write, Bash, Grep, Glob, WebSearch
 color: green
 ---
 

package/.mindforge/personas/project-researcher.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-project-researcher
 description: Principal domain researcher. Investigates ecosystem, feasibility, and technical constraints before project or milestone creation.
-tools: Read, Write, Bash, Grep, Glob, search_web, read_url_content, Context7
+tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch
 color: cyan
 ---
 
@@ -32,7 +32,7 @@ The most valuable thing you can find is what *won't* work. Identify the "Critica
 <process>
 
 <step name="ecosystem_discovery">
-Identify primary framework choices. Query `Context7` for current documentation, code examples, and ecosystem standards.
+Identify primary framework choices. Use `WebFetch` for current documentation, code examples, and ecosystem standards.
 Supplement with manual search for popularity and community sentiment.
 </step>
 

package/.mindforge/personas/python-specialist.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-python-specialist
 description: Python ecosystem specialist for Pythonic patterns, async/await, type hints, packaging, and framework best practices
-tools: Read, Write, Bash, Grep, Glob, Context7
+tools: Read, Write, Bash, Grep, Glob, WebFetch
 color: cyan
 ---
 

package/.mindforge/personas/qa-engineer.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-qa-engineer
 description: Senior quality assurance engineer. Thinks adversarially to find failure modes, boundary conditions, and logic gaps.
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: yellow
 ---
 

package/.mindforge/personas/release-manager.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-release-manager
 description: Senior release manager and platform engineer. Ensures every release is traceable, reversible, and communicated through structured semver and changelogs.
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: blue
 ---
 

package/.mindforge/personas/research-agent.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-research-agent
 description: Technical research specialist with 1M+ token context window. Ingests large documentation sets and codebases to identify patterns, debt, and integration paths.
-tools: Read, Write, Bash, Grep, Glob, Browser, Context7
+tools: Read, Write, Bash, Grep, Glob, WebFetch
 color: cyan
 ---
 
@@ -38,9 +38,9 @@ Identify the primary sources: Existing code, external URL docs, or local regulat
 </step>
 
 <step name="deep_ingestion">
-Use `Context7` MCP as the primary engine for external documentation and code examples. Fallback to `Browser` for niche sites or non-standard documentation. Use `Read` for large local files.
+Use `WebFetch` as the primary engine for external documentation and code examples. Use `Read` for large local files.
 Look for:
-- API contracts and examples (via Context7).
+- API contracts and examples (via `WebFetch`).
 - Performance limits.
 - Known pitfalls/issues.
 - Licensing and security status.
@@ -95,7 +95,7 @@ Highlight:
 
 <critical_rules>
 - **NO GUESSING**: If the documentation is unclear, state it as an "Open Question." Never fill gaps with hallucinated details.
-- **CONTEXT7 FIRST**: Always query Context7 for library documentation before manual browsing.
+- **DOCS FIRST**: Always use `WebFetch` for library documentation before manual browsing.
 - **ABSOLUTE PATHS**: Always cite your sources with absolute paths or valid URLs.
 - **CONTEXT OVER BREVITY**: When researching complex integrations, favor detail. The Decision Architect needs the "Why" and the "How."
 </critical_rules>

package/.mindforge/personas/roadmapper-extend.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-roadmapper-extend
 description: Enhanced execution strategist. Specializes in deriving phases from requirements and ensuring 100% coverage with verifiable success criteria.
-tools: Read, Write, Bash, Grep, Glob, search_web
+tools: Read, Write, Bash, Grep, Glob, WebSearch
 color: cyan
 ---
 

package/.mindforge/personas/rust-specialist.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-rust-specialist
 description: Rust language specialist for ownership patterns, lifetime management, unsafe code review, and systems programming best practices
-tools: Read, Write, Bash, Grep, Glob, Context7
+tools: Read, Write, Bash, Grep, Glob, WebFetch
 color: cyan
 ---
 

package/.mindforge/personas/security-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-security-reviewer
 description: Senior application security engineer. Reviews code for vulnerabilities, hardcoded secrets, and compliance with the OWASP Top 10.
-tools: Read, Write, Bash, Grep, Glob, CommandStatus
+tools: Read, Write, Bash, Grep, Glob
 color: red
 ---
 

package/.mindforge/personas/tech-writer.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-tech-writer
 description: Senior technical writer and communication specialist. Produces minimal, high-utility documentation for developers and stakeholders.
-tools: Read, Write, Bash, Grep, Glob, Context7
+tools: Read, Write, Bash, Grep, Glob, WebFetch
 color: cyan
 ---
 

package/.mindforge/personas/typescript-wizard.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-typescript-wizard
 description: Advanced TypeScript specialist for generics, conditional types, template literals, type-level programming, and complex type inference
-tools: Read, Write, Bash, Grep, Glob, Context7
+tools: Read, Write, Bash, Grep, Glob, WebFetch
 color: cyan
 ---
 

package/.mindforge/personas/ui-researcher.md

@@ -1,7 +1,7 @@
 ---
 name: mindforge-ui-researcher
 description: Produced design contracts (UI-SPEC.md) for frontend phases. Researches stack, tokens, and components.
-tools: Read, Write, Bash, Grep, Glob, search_web, Context7
+tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch
 color: #E879F9
 ---
 

package/.mindforge/skills/accessibility/SKILL.md

@@ -3,7 +3,7 @@ name: accessibility
 version: 1.0.0
 min_mindforge_version: 0.3.0
 status: stable
-triggers: accessibility, a11y, aria, ARIA, wcag, WCAG, screen reader, keyboard, focus, tab order, colour contrast, color contrast, alt text, semantic HTML, form label, button, interactive, disabled, skip link, heading hierarchy, landmark, live region, modal, dialog, tooltip, dropdown, combobox
+triggers: accessibility, a11y, aria, wcag, screen reader, keyboard, focus, tab order, colour contrast, color contrast, alt text, semantic HTML, form label, button, interactive, disabled, skip link, heading hierarchy, landmark, live region, modal, dialog, tooltip, dropdown, combobox
 ---
 
 # Skill — Accessibility Engineering
@@ -78,7 +78,7 @@ Level AAA elements (where achievable without design compromise) are recommended.
 ### Testing protocol
 ```bash
 # Automated testing (catches ~30-40% of issues)
-npx axe-cli https://localhost:3000
+npx @axe-core/cli https://localhost:3000
 
 # Keyboard testing (manual — must be done for every interactive component)
 # 1. Tab through every interactive element — order must be logical
@@ -98,7 +98,7 @@ npx axe-cli https://localhost:3000
 ```
 
 ## Self-check before task completion
-- [ ] Ran `axe-cli` — zero violations
+- [ ] Ran `@axe-core/cli` — zero violations
 - [ ] Keyboard navigation tested manually
 - [ ] All interactive elements have accessible names
 - [ ] Colour contrast meets 4.5:1 for text

package/.mindforge/skills/agent-architecture-audit/SKILL.md

@@ -22,6 +22,17 @@ timeout, hallucination); this skill audits the whole stack for the systemic
 wrapper-layer causes behind those failures. Invoke via `/mindforge:introspect`
 when a single-failure debug keeps recurring or points at a structural cause.
 
+**Component-name note:** `PersonaFactory`, `soul-engine`, and `hooks_route`
+below describe MindForge's *aspirational* multi-agent protocol (per
+`.claude/CLAUDE.md`) and are NOT implemented anywhere in `bin/` — grep for
+these names before treating a "missing" one as a real finding. The actual
+ground-truth implementations are: `bin/engine/nexus-tracer.js` (NexusTracer),
+`bin/autonomous/wave-executor.js` (WaveExecutor), and `bin/shard-helper.js`
+(the real file behind the `shard-controller` concept). When auditing a real
+MindForge instance, map findings to these actual files, not the aspirational
+names — treat every table entry below as a *conceptual* layer, not a
+confirmed component.
+
 ## When this skill activates
 
 **MANDATORY for:**

package/.mindforge/skills/agent-loops/SKILL.md

@@ -3,7 +3,7 @@ name: agent-loops
 version: 1.0.0
 min_mindforge_version: 10.0.3
 status: stable
-triggers: loop, circuit breaker, retry, fallback, agent loop, orchestration, self-repair, recovery, sequential execution, iteration, backoff, provider fallback
+triggers: loop, circuit breaker, retry, fallback, agent loop, agent loop orchestration, self-repair, recovery, sequential execution, iteration, backoff, provider fallback
 ---
 
 # Skill — Agent Loops

package/.mindforge/skills/arxiv/SKILL.md

@@ -17,8 +17,8 @@ Search and retrieve academic papers from arXiv via their free REST API. No API k
 |--------|---------|
 | Search papers | `curl "https://export.arxiv.org/api/query?search_query=all:QUERY&max_results=5"` |
 | Get specific paper | `curl "https://export.arxiv.org/api/query?id_list=2402.03300"` |
-| Read abstract (web) | `web_extract(urls=["https://arxiv.org/abs/2402.03300"])` |
-| Read full paper (PDF) | `web_extract(urls=["https://arxiv.org/pdf/2402.03300"])` |
+| Read abstract (web) | `WebFetch(urls=["https://arxiv.org/abs/2402.03300"])` |
+| Read full paper (PDF) | `WebFetch(urls=["https://arxiv.org/pdf/2402.03300"])` |
 
 ## Searching Papers
 
@@ -145,10 +145,10 @@ After finding a paper, read it:
 
 ```
 # Abstract page (fast, metadata + abstract)
-web_extract(urls=["https://arxiv.org/abs/2402.03300"])
+WebFetch(urls=["https://arxiv.org/abs/2402.03300"])
 
 # Full paper (PDF → markdown via Firecrawl)
-web_extract(urls=["https://arxiv.org/pdf/2402.03300"])
+WebFetch(urls=["https://arxiv.org/pdf/2402.03300"])
 ```
 
 For local PDF processing, see the `ocr-and-documents` skill.
@@ -241,8 +241,8 @@ curl -s "https://api.semanticscholar.org/graph/v1/author/search?query=Yann+LeCun
 
 1. **Discover**: `python scripts/search_arxiv.py "your topic" --sort date --max 10`
 2. **Assess impact**: `curl -s "https://api.semanticscholar.org/graph/v1/paper/arXiv:ID?fields=citationCount,influentialCitationCount"`
-3. **Read abstract**: `web_extract(urls=["https://arxiv.org/abs/ID"])`
-4. **Read full paper**: `web_extract(urls=["https://arxiv.org/pdf/ID"])`
+3. **Read abstract**: `WebFetch(urls=["https://arxiv.org/abs/ID"])`
+4. **Read full paper**: `WebFetch(urls=["https://arxiv.org/pdf/ID"])`
 5. **Find related work**: `curl -s "https://api.semanticscholar.org/graph/v1/paper/arXiv:ID/references?fields=title,citationCount&limit=20"`
 6. **Get recommendations**: POST to Semantic Scholar recommendations endpoint
 7. **Track authors**: `curl -s "https://api.semanticscholar.org/graph/v1/author/search?query=NAME"`