mindforge-cc 11.8.2 → 11.9.0

package/.agent/skills/pixel-art/SKILL.md

@@ -127,7 +127,7 @@ pixel_art("in.png", "out.png", preset="snes", palette="PICO_8", block=6)
 
 ```python
 import sys
-sys.path.insert(0, "/home/teknium/.hermes/skills/creative/pixel-art/scripts")
+sys.path.insert(0, "<path-to-this-skill>/scripts")  # e.g. ~/.agent/skills/pixel-art/scripts
 from pixel_art import pixel_art
 from pixel_art_video import pixel_art_video
 
@@ -149,7 +149,7 @@ pixel_art_video(
 ### CLI
 
 ```bash
-cd /home/teknium/.hermes/skills/creative/pixel-art/scripts
+cd <path-to-this-skill>/scripts  # e.g. ~/.agent/skills/pixel-art/scripts
 
 python pixel_art.py in.jpg out.png --preset gameboy
 python pixel_art.py in.jpg out.png --preset snes --palette PICO_8 --block 6

package/.agent/skills/plan/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: plan
-description: "Plan mode: write an actionable markdown plan to .hermes/plans/, no execution. Bite-sized tasks, exact paths, complete code."
+description: "Plan mode: write an actionable markdown plan to .planning/plans/, no execution. Bite-sized tasks, exact paths, complete code."
 version: 2.0.0
 ---
 
@@ -16,7 +16,7 @@ For this turn, you are planning only.
 - Do not edit project files except the plan markdown file.
 - Do not run mutating terminal commands, commit, push, or perform external actions.
 - You may inspect the repo or other context with read-only commands/tools when needed.
-- Your deliverable is a markdown plan saved inside the active workspace under `.hermes/plans/`.
+- Your deliverable is a markdown plan saved inside the active workspace under `.planning/plans/`.
 
 ## Output requirements
 
@@ -35,13 +35,13 @@ If the task is code-related, include exact file paths, likely test targets, and
 
 ## Save location
 
-Save the plan with `write_file` under:
-- `.hermes/plans/YYYY-MM-DD_HHMMSS-<slug>.md`
+Save the plan with `Write` under:
+- `.planning/plans/YYYY-MM-DD_HHMMSS-<slug>.md`
 
 Treat that as relative to the active working directory / backend workspace. the agent file tools are backend-aware, so using this relative path keeps the plan with the workspace on local, docker, ssh, modal, and daytona backends.
 
 If the runtime provides a specific target path, use that exact path.
-If not, create a sensible timestamped filename yourself under `.hermes/plans/`.
+If not, create a sensible timestamped filename yourself under `.planning/plans/`.
 
 ## Interaction style
 
@@ -188,16 +188,16 @@ Use tools to understand the project:
 
 ```python
 # Understand project structure
-search_files("*.py", target="files", path="src/")
+Grep("*.py", target="files", path="src/")
 
 # Look at similar features
-search_files("similar_pattern", path="src/", file_glob="*.py")
+Grep("similar_pattern", path="src/", file_glob="*.py")
 
 # Check existing tests
-search_files("*.py", target="files", path="tests/")
+Grep("*.py", target="files", path="tests/")
 
 # Read key files
-read_file("src/app.py")
+Read("src/app.py")
 ```
 
 ### Step 3: Design Approach
@@ -311,7 +311,7 @@ After saving the plan, offer the execution approach:
 **"Plan complete and saved. Ready to execute using subagent-driven-development — I'll dispatch a fresh subagent per task with two-stage review (spec compliance then code quality). Shall I proceed?"**
 
 When executing, use the `subagent-driven-development` skill:
-- Fresh `delegate_task` per task with full context
+- Fresh `Agent` per task with full context
 - Spec compliance review after each task
 - Code quality review after spec passes
 - Proceed only when both reviews approve

package/.agent/skills/requesting-code-review/SKILL.md

@@ -117,13 +117,13 @@ Quick scan before dispatching the reviewer:
 
 ## Step 5 — Independent reviewer subagent
 
-Call `delegate_task` directly — it is NOT available inside execute_code or scripts.
+Call `Agent` directly — it is NOT available inside Bash or scripts.
 
 The reviewer gets ONLY the diff and static scan results. No shared context with
 the implementer. Fail-closed: unparseable response = fail.
 
 ```python
-delegate_task(
+Agent(
     goal="""You are an independent code reviewer. You have no context about how
 these changes were made. Review the git diff and return ONLY valid JSON.
 
@@ -162,7 +162,6 @@ Return ONLY this JSON:
   "summary": "one sentence verdict"
 }""",
     context="Independent code review. Return only JSON verdict.",
-    toolsets=["terminal"]
 )
 ```
 
@@ -192,7 +191,7 @@ Spawn a THIRD agent context — not you (the implementer), not the reviewer.
 It fixes ONLY the reported issues:
 
 ```python
-delegate_task(
+Agent(
     goal="""You are a code fix agent. Fix ONLY the specific issues listed below.
 Do NOT refactor, rename, or change anything else. Do NOT add features.
 
@@ -208,7 +207,6 @@ Current diff for context:
 
 Fix each issue precisely. Describe what you changed and why.""",
     context="Fix only the reported issues. Do not change anything else.",
-    toolsets=["terminal", "file"]
 )
 ```
 
@@ -266,7 +264,7 @@ tests exist, tests pass, no regressions.
 - **Empty diff** — check `git status`, tell user nothing to verify
 - **Not a git repo** — skip and tell user
 - **Large diff (>15k chars)** — split by file, review each separately
-- **delegate_task returns non-JSON** — retry once with stricter prompt, then treat as FAIL
+- **Agent returns non-JSON** — retry once with stricter prompt, then treat as FAIL
 - **False positives** — if reviewer flags something intentional, note it in fix prompt
 - **No test framework found** — skip regression check, reviewer verdict still runs
 - **Lint tools not installed** — skip that check silently, don't fail

package/.agent/skills/research-paper-writing/SKILL.md

@@ -236,17 +236,17 @@ find . -name "*.bib"
 
 ### Step 1.2: Search for Related Work
 
-**Load the `arxiv` skill** for structured paper discovery: `skill_view("arxiv")`. It provides arXiv REST API search, Semantic Scholar citation graphs, author profiles, and BibTeX generation.
+**Load the `arxiv` skill** for structured paper discovery: `Skill(skill="arxiv")`. It provides arXiv REST API search, Semantic Scholar citation graphs, author profiles, and BibTeX generation.
 
-Use `web_search` for broad discovery, `web_extract` for fetching specific papers:
+Use `WebSearch` for broad discovery, `WebFetch` for fetching specific papers:
 
 ```
-# Via web_search:
-web_search("[main technique] + [application domain] site:arxiv.org")
-web_search("[baseline method] comparison ICML NeurIPS 2024")
+# Via WebSearch:
+WebSearch("[main technique] + [application domain] site:arxiv.org")
+WebSearch("[baseline method] comparison ICML NeurIPS 2024")
 
-# Via web_extract (for specific papers):
-web_extract("https://arxiv.org/abs/2303.17651")
+# Via WebFetch (for specific papers):
+WebFetch("https://arxiv.org/abs/2303.17651")
 ```
 
 Additional search queries to try:
@@ -293,7 +293,7 @@ Round 3 (Targeted): Fill specific gaps
 
 **When to stop**: If a round returns >80% papers already in your collection, the search is saturated. Typically 2-3 rounds suffice. For survey papers, expect 4-5 rounds.
 
-**For agent-based workflows**: Delegate each round's queries in parallel via `delegate_task`. Collect results, deduplicate, then generate the next round's queries from the combined learnings.
+**For agent-based workflows**: Delegate each round's queries in parallel via `Agent`. Collect results, deduplicate, then generate the next round's queries from the combined learnings.
 
 ### Step 1.3: Verify Every Citation
 
@@ -2114,12 +2114,12 @@ Compose this skill with other skills for specific phases:
 
 | Skill | When to Use | How to Load |
 |-------|-------------|-------------|
-| **arxiv** | Phase 1 (Literature Review): searching arXiv, generating BibTeX, finding related papers via Semantic Scholar | `skill_view("arxiv")` |
-| **subagent-driven-development** | Phase 5 (Drafting): parallel section writing with 2-stage review (spec compliance then quality) | `skill_view("subagent-driven-development")` |
-| **plan** | Phase 0 (Setup): creating structured plans before execution. Writes to `.hermes/plans/` | `skill_view("plan")` |
+| **arxiv** | Phase 1 (Literature Review): searching arXiv, generating BibTeX, finding related papers via Semantic Scholar | `Skill(skill="arxiv")` |
+| **subagent-driven-development** | Phase 5 (Drafting): parallel section writing with 2-stage review (spec compliance then quality) | `Skill(skill="subagent-driven-development")` |
+| **plan** | Phase 0 (Setup): creating structured plans before execution. Writes to `.planning/plans/` | `Skill(skill="plan")` |
 | **qmd** | Phase 1 (Literature): searching local knowledge bases (notes, transcripts, docs) via hybrid BM25+vector search | Install: `skill_manage("install", "qmd")` |
-| **diagramming** | Phase 4-5: creating Excalidraw-based figures and architecture diagrams | `skill_view("diagramming")` |
-| **data-science** | Phase 4 (Analysis): Jupyter live kernel for interactive analysis and visualization | `skill_view("data-science")` |
+| **concept-diagrams** | Phase 4-5: creating Excalidraw-based figures and architecture diagrams | `Skill(skill="concept-diagrams")` |
+| **jupyter-live-kernel** | Phase 4 (Analysis): Jupyter live kernel for interactive analysis and visualization | `Skill(skill="jupyter-live-kernel")` |
 
 **This skill supersedes `ml-paper-writing`** — it contains all of ml-paper-writing's content plus the full experiment/analysis pipeline and autoreason methodology.
 
@@ -2127,13 +2127,13 @@ Compose this skill with other skills for specific phases:
 
 | Tool | Usage in This Pipeline |
 |------|----------------------|
-| **`terminal`** | LaTeX compilation (`latexmk -pdf`), git operations, launching experiments (`nohup python run.py &`), process checks |
+| **`Bash`** | LaTeX compilation (`latexmk -pdf`), git operations, launching experiments (`nohup python run.py &`), process checks |
 | **`process`** | Background experiment management: `process("start", ...)`, `process("poll", pid)`, `process("log", pid)`, `process("kill", pid)` |
-| **`execute_code`** | Run Python for citation verification, statistical analysis, data aggregation. Has tool access via RPC. |
-| **`read_file`** / **`write_file`** / **`patch`** | Paper editing, experiment scripts, result files. Use `patch` for targeted edits to large .tex files. |
-| **`web_search`** | Literature discovery: `web_search("transformer attention mechanism 2024")` |
-| **`web_extract`** | Fetch paper content, verify citations: `web_extract("https://arxiv.org/abs/2303.17651")` |
-| **`delegate_task`** | **Parallel section drafting** — spawn isolated subagents for each section. Also for concurrent citation verification. |
+| **`Bash`** | Run Python for citation verification, statistical analysis, data aggregation. Has tool access via RPC. |
+| **`Read`** / **`Write`** / **`Edit`** | Paper editing, experiment scripts, result files. Use `Edit` for targeted edits to large .tex files. |
+| **`WebSearch`** | Literature discovery: `WebSearch("transformer attention mechanism 2024")` |
+| **`WebFetch`** | Fetch paper content, verify citations: `WebFetch("https://arxiv.org/abs/2303.17651")` |
+| **`Agent`** | **Parallel section drafting** — spawn isolated subagents for each section. Also for concurrent citation verification. |
 | **`todo`** | Primary state tracker across sessions. Update after every phase transition. |
 | **`memory`** | Persist key decisions across sessions: contribution framing, venue choice, reviewer feedback. |
 | **`cronjob`** | Schedule experiment monitoring, deadline countdowns, automated arXiv checks. |
@@ -2144,32 +2144,32 @@ Compose this skill with other skills for specific phases:
 
 **Experiment monitoring** (most common):
 ```
-terminal("ps aux | grep <pattern>")
-→ terminal("tail -30 <logfile>")
-→ terminal("ls results/")
-→ execute_code("analyze results JSON, compute metrics")
-→ terminal("git add -A && git commit -m '<descriptive message>' && git push")
+Bash("ps aux | grep <pattern>")
+→ Bash("tail -30 <logfile>")
+→ Bash("ls results/")
+→ Bash("analyze results JSON, compute metrics")
+→ Bash("git add -A && git commit -m '<descriptive message>' && git push")
 → send_message("Experiment complete: <summary>")
 ```
 
 **Parallel section drafting** (using delegation):
 ```
-delegate_task("Draft the Methods section based on these experiment scripts and configs. 
+Agent("Draft the Methods section based on these experiment scripts and configs. 
   Include: pseudocode, all hyperparameters, architectural details sufficient for 
   reproduction. Write in LaTeX using the neurips2025 template conventions.")
 
-delegate_task("Draft the Related Work section. Use web_search and web_extract to 
+Agent("Draft the Related Work section. Use WebSearch and WebFetch to 
   find papers. Verify every citation via Semantic Scholar. Group by methodology.")
 
-delegate_task("Draft the Experiments section. Read all result files in results/. 
+Agent("Draft the Experiments section. Read all result files in results/. 
   State which claim each experiment supports. Include error bars and significance.")
 ```
 
 Each delegate runs as a **fresh subagent** with no shared context — provide all necessary information in the prompt. Collect outputs and integrate.
 
-**Citation verification** (using execute_code):
+**Citation verification** (using Bash):
 ```python
-# In execute_code:
+# In Bash:
 from semanticscholar import SemanticScholar
 import requests
 
@@ -2210,9 +2210,9 @@ todo("update", id=1, status="completed")
 ```
 1. todo("list")                           # Check current task list
 2. memory("read")                         # Recall key decisions
-3. terminal("git log --oneline -10")      # Check recent commits
-4. terminal("ps aux | grep python")       # Check running experiments
-5. terminal("ls results/ | tail -20")     # Check for new results
+3. Bash("git log --oneline -10")      # Check recent commits
+4. Bash("ps aux | grep python")       # Check running experiments
+5. Bash("ls results/ | tail -20")     # Check for new results
 6. Report status to user, ask for direction
 ```
 

package/.agent/skills/rest-graphql-debug/SKILL.md

@@ -6,7 +6,7 @@ version: 1.2.0
 
 # API Testing & Debugging
 
-Drive REST and GraphQL diagnosis through tools — `terminal` for `curl`, `execute_code` for Python `requests`, `web_extract` for vendor docs. Isolate the failing layer before guessing at the fix.
+Drive REST and GraphQL diagnosis through tools — `Bash` for `curl`, `Bash` for Python `requests`, `WebFetch` for vendor docs. Isolate the failing layer before guessing at the fix.
 
 ## When to Use
 
@@ -39,25 +39,25 @@ Skip for UI rendering, DB query tuning, or DNS/firewall infra (escalate).
 
 ```python
 # Verbose request/response exchange
-terminal('curl -v https://api.example.com/users/1')
+Bash('curl -v https://api.example.com/users/1')
 
 # POST with JSON
-terminal("""curl -X POST https://api.example.com/users \\
+Bash("""curl -X POST https://api.example.com/users \\
   -H 'Content-Type: application/json' \\
   -H "Authorization: Bearer $TOKEN" \\
   -d '{"name":"test","email":"test@example.com"}'""")
 
 # Headers only
-terminal('curl -sI https://api.example.com/health')
+Bash('curl -sI https://api.example.com/health')
 
 # Pretty-print JSON
-terminal('curl -s https://api.example.com/users | python3 -m json.tool')
+Bash('curl -s https://api.example.com/users | python3 -m json.tool')
 ```
 
 ### GraphQL via terminal
 
 ```python
-terminal("""curl -X POST https://api.example.com/graphql \\
+Bash("""curl -X POST https://api.example.com/graphql \\
   -H 'Content-Type: application/json' \\
   -H "Authorization: Bearer $TOKEN" \\
   -d '{"query":"{ user(id: 1) { name email } }"}'""")
@@ -66,7 +66,7 @@ terminal("""curl -X POST https://api.example.com/graphql \\
 **GraphQL gotcha:** servers often return HTTP 200 even when the query failed. Always inspect the `errors` field regardless of status code:
 
 ```python
-execute_code('''
+Bash('''
 import os, requests
 resp = requests.post(
     "https://api.example.com/graphql",
@@ -82,10 +82,10 @@ print(data.get("data"))
 ''')
 ```
 
-### Python (requests) via execute_code
+### Python (requests) via Bash
 
 ```python
-execute_code('''
+Bash('''
 import requests
 resp = requests.get(
     "https://api.example.com/users/1",
@@ -102,8 +102,8 @@ print(resp.text[:500])
 ### Step 1 — Connectivity
 
 ```python
-terminal('nslookup api.example.com')
-terminal('curl -v --connect-timeout 5 https://api.example.com/health')
+Bash('nslookup api.example.com')
+Bash('curl -v --connect-timeout 5 https://api.example.com/health')
 ```
 
 Failures: DNS not resolving, firewall, VPN required, proxy missing.
@@ -113,14 +113,14 @@ Failures: DNS not resolving, firewall, VPN required, proxy missing.
 Distinguish *can't reach* from *reaches but slow*:
 
 ```python
-terminal('''curl -w "dns:%{time_namelookup}s connect:%{time_connect}s tls:%{time_appconnect}s ttfb:%{time_starttransfer}s total:%{time_total}s\\n" \\
+Bash('''curl -w "dns:%{time_namelookup}s connect:%{time_connect}s tls:%{time_appconnect}s ttfb:%{time_starttransfer}s total:%{time_total}s\\n" \\
   -o /dev/null -s https://api.example.com/endpoint''')
 ```
 
 In Python, always pass a tuple timeout — `requests` has no default and will hang forever:
 
 ```python
-execute_code('''
+Bash('''
 import requests
 from requests.exceptions import ConnectTimeout, ReadTimeout
 try:
@@ -137,7 +137,7 @@ Diagnosis: high `time_connect` is network/firewall; high `time_starttransfer` wi
 ### Step 2 — TLS/SSL
 
 ```python
-terminal('curl -vI https://api.example.com 2>&1 | grep -E "SSL|subject|expire|issuer"')
+Bash('curl -vI https://api.example.com 2>&1 | grep -E "SSL|subject|expire|issuer"')
 ```
 
 Failures: expired cert, self-signed, hostname mismatch, missing CA bundle. Use `-k` only for ad-hoc debug, never in code.
@@ -146,10 +146,10 @@ Failures: expired cert, self-signed, hostname mismatch, missing CA bundle. Use `
 
 ```python
 # Token validity check
-terminal('curl -s -o /dev/null -w "%{http_code}\\n" -H "Authorization: Bearer $TOKEN" https://api.example.com/me')
+Bash('curl -s -o /dev/null -w "%{http_code}\\n" -H "Authorization: Bearer $TOKEN" https://api.example.com/me')
 
 # Decode JWT exp claim — handles base64url padding correctly
-execute_code('''
+Bash('''
 import json, base64, os
 tok = os.environ["TOKEN"]
 payload = tok.split(".")[1]
@@ -167,7 +167,7 @@ Checklist:
 ### Step 4 — Request Format
 
 ```python
-terminal("""curl -v -X POST https://api.example.com/endpoint \\
+Bash("""curl -v -X POST https://api.example.com/endpoint \\
   -H 'Content-Type: application/json' \\
   -d '{"key":"value"}' 2>&1""")
 ```
@@ -195,7 +195,7 @@ Common: form-encoded vs JSON, missing required fields, wrong HTTP method, unenco
 Always inspect content-type before calling `.json()`:
 
 ```python
-execute_code('''
+Bash('''
 import requests
 resp = requests.post(url, json=payload, timeout=10)
 print(f"status={resp.status_code}")
@@ -260,7 +260,7 @@ The error body usually names the bad fields. Check:
 Check `Retry-After` and `X-RateLimit-*` headers. Exponential backoff:
 
 ```python
-execute_code('''
+Bash('''
 import time, requests
 
 def with_backoff(method, url, **kwargs):
@@ -296,7 +296,7 @@ For all 5xx: backoff with jitter, alert on persistence.
 Catch schema drift before it hits production:
 
 ```python
-execute_code('''
+Bash('''
 import requests
 
 def validate_user(data: dict) -> list[str]:
@@ -323,7 +323,7 @@ Run after API upgrades, when integrating new third parties, or in CI smoke tests
 Always capture the provider's request ID — fastest path to vendor support:
 
 ```python
-execute_code('''
+Bash('''
 import requests
 resp = requests.post(url, json=payload, headers=headers, timeout=10)
 request_id = (
@@ -350,7 +350,7 @@ Repro:       curl -X POST … (auth: <REDACTED>)
 
 ## Regression Test Template
 
-Drop this into `tests/` and run via `terminal('pytest tests/test_api_smoke.py -v')`:
+Drop this into `tests/` and run via `Bash('pytest tests/test_api_smoke.py -v')`:
 
 ```python
 import os, requests, pytest
@@ -415,16 +415,16 @@ def redact_auth(headers: dict) -> dict:
 ### terminal — for curl, dig, openssl
 
 ```python
-terminal('curl -sI https://api.example.com')
-terminal('openssl s_client -connect api.example.com:443 -servername api.example.com </dev/null 2>/dev/null | openssl x509 -noout -dates')
+Bash('curl -sI https://api.example.com')
+Bash('openssl s_client -connect api.example.com:443 -servername api.example.com </dev/null 2>/dev/null | openssl x509 -noout -dates')
 ```
 
-### execute_code — for multi-step Python flows
+### Bash — for multi-step Python flows
 
-When debugging spans auth → fetch → paginate → validate, use `execute_code`. Variables persist for the script, results print to stdout, no risk of token spam in your context:
+When debugging spans auth → fetch → paginate → validate, use `Bash`. Variables persist for the script, results print to stdout, no risk of token spam in your context:
 
 ```python
-execute_code('''
+Bash('''
 import os, requests
 
 token = os.environ["API_TOKEN"]
@@ -449,18 +449,18 @@ print(f"users={len(all_users)}")
 ''')
 ```
 
-### web_extract — for vendor API docs
+### WebFetch — for vendor API docs
 
 Pull the spec for the endpoint you're debugging instead of guessing:
 
 ```python
-web_extract(urls=["https://docs.example.com/api/v1/users"])
+WebFetch(urls=["https://docs.example.com/api/v1/users"])
 ```
 
-### delegate_task — for full CRUD test sweeps
+### Agent — for full CRUD test sweeps
 
 ```python
-delegate_task(
+Agent(
     goal="Test all CRUD endpoints for /api/v1/users",
     context="""
 Follow the rest-graphql-debug skill (optional-skills/software-development/rest-graphql-debug).
@@ -474,7 +474,6 @@ For each verb (POST, GET, PATCH, DELETE):
 
 Output: pass/fail per endpoint + correlation IDs for failures.
 """,
-    toolsets=["terminal", "file"],
 )
 ```
 

package/.agent/skills/s6-container-supervision/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: hermes-s6-container-supervision
+name: s6-container-supervision
 description: Modify, debug, or extend the s6-overlay supervision tree inside the 
 version: 1.0.0
 environments: [s6]

package/.agent/skills/scrapling/SKILL.md

@@ -18,7 +18,7 @@ prerequisites:
 - Scraping JS-rendered pages that need a real browser
 - Bypassing Cloudflare Turnstile or bot detection
 - Crawling multiple pages with a spider
-- When the built-in `web_extract` tool does not return the data you need
+- When the built-in `WebFetch` tool does not return the data you need
 
 ## Installation
 

package/.agent/skills/sherlock/SKILL.md

@@ -70,7 +70,7 @@ sherlock --print-found --no-color "<username>" --timeout 90
 
 ### 4. Execute Search
 
-Run via the `terminal` tool. The command typically takes 30-120 seconds depending on network conditions and site count.
+Run via the `Bash` tool. The command typically takes 30-120 seconds depending on network conditions and site count.
 
 **Example terminal call:**
 ```json

package/.agent/skills/simplify-code/SKILL.md

@@ -68,15 +68,13 @@ before proceeding.
 
 ### Phase 2 — Launch three reviewers in parallel
 
-Use `delegate_task` **batch mode** — pass all three tasks in one `tasks`
-array so they run concurrently. Three is the right fan-out for this pattern;
-it's well within the `delegation.max_concurrent_children` budget on any
-default install.
+Make three separate `Agent` tool calls **in the same response** so they run
+concurrently. Three is the right fan-out for this pattern.
 
 Give **every** reviewer the **complete diff** (not fragments — cross-file
 issues hide in the gaps) plus the absolute repo path so they can search the
-wider codebase. Each reviewer gets `terminal`, `file`, and `search`
-toolsets (so they can `git`, `read_file`, and `search_files`/grep).
+wider codebase. Each reviewer gets `Bash` (for `git`), `Read`, and `Grep`
+so they can inspect the full diff and the wider codebase.
 
 Tell each reviewer to:
 - Search the existing codebase for evidence (don't reason from the diff alone).
@@ -131,7 +129,7 @@ Wait for all three to return (batch mode returns them together).
    Don't apply a perf "fix" that hurts clarity unless the path is genuinely
    hot. When two suggestions are mutually exclusive and both defensible, pick
    the one that touches less code and note the alternative.
-4. **Apply** the surviving fixes directly with `patch` / `write_file` — unless
+4. **Apply** the surviving fixes directly with `Edit` / `Write` — unless
    the user asked for a dry run, in which case present the list and ask first.
 5. **Verify** you didn't break anything: run the project's targeted tests for
    the touched files (not the full suite), and re-run any linter/type check the

package/.agent/skills/skill-authoring/SKILL.md

@@ -103,7 +103,7 @@ Pick the closest existing category. Don't invent new top-level categories casual
    ```
    Read 2-3 peer SKILL.md files to match tone and structure.
 2. **Check validator constraints** in `tools/skill_manager_tool.py` if unsure.
-3. **Draft** with `write_file` to `skills/<category>/<name>/SKILL.md`.
+3. **Draft** with `Write` to `skills/<category>/<name>/SKILL.md`.
 4. **Validate locally**:
    ```python
    import yaml, re, pathlib
@@ -125,13 +125,13 @@ Pick the closest existing category. Don't invent new top-level categories casual
 ## Editing Existing In-Repo Skills
 
 - **Small fix (typo, added pitfall, tightened trigger):** `skill_manage(action='patch', name=..., old_string=..., new_string=...)` works fine on in-repo skills.
-- **Major rewrite:** `write_file` the whole SKILL.md. `skill_manage(action='edit')` also works but requires supplying the full new content.
-- **Adding supporting files:** `write_file` to `skills/<category>/<name>/references/<file>.md`, `templates/<file>`, or `scripts/<file>`. `skill_manage(action='write_file')` also works and enforces the references/templates/scripts/assets subdir allowlist.
+- **Major rewrite:** `Write` the whole SKILL.md. `skill_manage(action='edit')` also works but requires supplying the full new content.
+- **Adding supporting files:** `Write` to `skills/<category>/<name>/references/<file>.md`, `templates/<file>`, or `scripts/<file>`. `skill_manage(action='write_file')` also works and enforces the references/templates/scripts/assets subdir allowlist.
 - **Always commit** the edit — in-repo skills are source, not runtime state.
 
 ## Common Pitfalls
 
-1. **Using `skill_manage(action='create')` for an in-repo skill.** It writes to `~/.agent/skills/`, not the repo tree. Use `write_file` for in-repo creation.
+1. **Using `skill_manage(action='create')` for an in-repo skill.** It writes to `~/.agent/skills/`, not the repo tree. Use `Write` for in-repo creation.
 
 2. **Leading whitespace before `---`.** The validator checks `content.startswith("---")`; any leading blank line or BOM fails validation.
 

package/.agent/skills/spike/SKILL.md

@@ -71,11 +71,11 @@ Spikes are not research-free — you research enough to pick the right approach,
 
 Use tools for the research step:
 
-- `web_search("python websocket streaming libraries 2025")` — find candidates
-- `web_extract(urls=["https://websockets.readthedocs.io/..."])` — read the actual docs (returns markdown)
-- `terminal("pip show websockets | grep Version")` — check what's installed in the project's venv
+- `WebSearch("python websocket streaming libraries 2025")` — find candidates
+- `WebFetch(urls=["https://websockets.readthedocs.io/..."])` — read the actual docs (returns markdown)
+- `Bash("pip show websockets | grep Version")` — check what's installed in the project's venv
 
-For libraries without docs pages, clone and read their `README.md` / `examples/` via `read_file`. Context7 MCP (if the user has it configured) is also a good source — `mcp_*_resolve-library-id` then `mcp_*_query-docs`.
+For libraries without docs pages, clone and read their `README.md` / `examples/` via `Read`. WebFetch MCP (if the user has it configured) is also a good source — `mcp_*_resolve-library-id` then `mcp_*_query-docs`.
 
 ### 4. Build
 
@@ -108,20 +108,18 @@ spikes/
 **Building one spike** — a typical tool sequence:
 
 ```
-terminal("mkdir -p spikes/001-websocket-streaming")
-write_file("spikes/001-websocket-streaming/README.md", "# 001: websocket-streaming\n\n...")
-write_file("spikes/001-websocket-streaming/main.py", "...")
-terminal("cd spikes/001-websocket-streaming && python3 main.py")
+Bash("mkdir -p spikes/001-websocket-streaming")
+Write("spikes/001-websocket-streaming/README.md", "# 001: websocket-streaming\n\n...")
+Write("spikes/001-websocket-streaming/main.py", "...")
+Bash("cd spikes/001-websocket-streaming && python3 main.py")
 # Observe output, iterate.
 ```
 
-**Parallel comparison spikes (002a / 002b) — delegate.** When two approaches can run in parallel and both need real engineering (not 10-line prototypes), fan out with `delegate_task`:
+**Parallel comparison spikes (002a / 002b) — delegate.** When two approaches can run in parallel and both need real engineering (not 10-line prototypes), fan out with two `Agent` tool calls in the same response:
 
 ```
-delegate_task(tasks=[
-    {"goal": "Build 002a-pdf-parse-pdfjs: ...", "toolsets": ["terminal", "file", "web"]},
-    {"goal": "Build 002b-pdf-parse-camelot: ...", "toolsets": ["terminal", "file", "web"]},
-])
+Agent(prompt="Build 002a-pdf-parse-pdfjs: ...")
+Agent(prompt="Build 002b-pdf-parse-camelot: ...")
 ```
 
 Each subagent returns its own verdict; you write the head-to-head.