Methodology

CLI-Anything-Web Methodology (Phase 2)

Analyze captured traffic, design the CLI command structure, and implement the complete Python CLI package. This skill owns the core transformation from raw HTTP traffic to a production-ready CLI.

Copy this checklist and check off items as you complete them:

Phase 2 Progress:
- [ ] Prerequisites: raw-traffic.json exists (+ auth state if the site needs auth)
- [ ] Step A: traffic analyzed, protocol identified, <APP>.md written
- [ ] Step A: api-spec.json written (every endpoint cites raw-traffic.json evidence)
       and passes `cli-web-devkit spec validate`
- [ ] Step B.0: scaffolded via scaffold-cli.py (.manifest.json present)
- [ ] Step B: client endpoint methods implemented from the spec
- [ ] Step B: command modules implemented + registered, REPL help in sync
- [ ] Smoke check passed (no protocol leaks), phase-state marked complete

Prerequisites (Hard Gate)

Do NOT start unless:

• raw-traffic.json exists (with WRITE operations, or read-only GET-only traffic)
• Auth state was captured during Phase 1 (if the site requires auth)

If raw-traffic.json is missing or has no WRITE operations, invoke the capture skill first. If Phase 1 state shows failed, follow skills/shared/RECOVERY.md §phase-state Check Failures before re-running.

Exception for read-only sites: If the site is genuinely read-only (search engine, dashboard, analytics viewer with no create/update/delete), the trace may contain only GET requests. In this case, note "read-only site — no write operations" in <APP>.md and proceed. The generated CLI will have read-only commands (list, get, search) but no create/update/delete commands. This is valid.

No-auth sites: If the target site requires no authentication (public API, no login needed), the "Auth state captured" prerequisite does not apply. Note "no-auth site" in <APP>.md and proceed.

Step A: Analyze (API Discovery)

Goal: Map raw traffic to a structured API model.

Process:

0. Read traffic-analysis.json first (if it exists alongside raw-traffic.json). This file is auto-generated by parse-trace.py or mitmproxy-capture.py → analyze-traffic.py and contains pre-detected protocol type, auth pattern, endpoint grouping, GraphQL operations, batchexecute RPC IDs, and suggested CLI commands. Use it as a starting point — verify its findings and fill in anything marked "unknown" by reading raw-traffic.json manually.

   Enhanced analysis (present only when captured via mitmproxy): request_sequence (timeline-ordered requests with auth-flow detection), session_lifecycle (cookie inventory, auth-cookie identification, session pattern), and endpoint_sizes (response-size classification). If these are missing (has_timestamps: false), the capture came from the default trace path — rely on manual analysis for sequence/session detail.

   If traffic-analysis.json doesn't exist, run the analyzer:

   python ${CLAUDE_PLUGIN_ROOT}/scripts/analyze-traffic.py \
     <app>/traffic-capture/raw-traffic.json --summary
   

1. Parse raw-traffic.json (for details the analyzer couldn't extract)

2. Group requests by base path (e.g., /api/v1/boards/, /api/v1/items/)

3. For each endpoint group, identify:

   • HTTP method (GET/POST/PUT/DELETE/PATCH)
   • URL pattern (extract path parameters like :id)
   • Query parameters and their types
   • Request body schema (JSON fields, types, required/optional)
   • Response body schema
   • Authentication method (Bearer token, cookie, API key)
   • Rate limiting signals (429 responses, retry-after headers)

4. Identify RPC protocol type -- classify the API transport:

   Protocol	Detection Signal	Client Pattern
   REST	Resource URLs (/api/v1/boards/:id), standard HTTP methods	client.py with method-per-endpoint
   GraphQL	Single /graphql endpoint, query/mutation in body	client.py with query templates
   gRPC-Web	application/grpc-web content type, binary payloads	Proto-based client
   Google batchexecute	batchexecute in URL, f.req= body, )]}'\n prefix	rpc/ subpackage (see references/google-batchexecute.md)
   Custom RPC	Single endpoint, method name in body, proprietary encoding	Custom codec module
   Public REST API	Documented /api/ endpoints, OpenAPI spec, JSON responses	Standard client.py with httpx
   Plain HTML (no framework)	No SPA root, no framework globals, data in <table>/<div>	client.py with httpx + BeautifulSoup4

   This determines client architecture in Step B -- REST uses simple client.py, non-REST protocols need a dedicated rpc/ subpackage with encoder/decoder/types.

5. Detect data model:

   • Entity types (boards, items, users, projects...)
   • Relationships (board has many items, item belongs to board)
   • ID formats (UUID, numeric, slug)

6. Detect auth pattern:

   • Cookie-based sessions
   • Bearer/JWT tokens
   • OAuth refresh flow
   • API key headers
   • Browser-delegated auth: tokens embedded in page JavaScript (e.g., WIZ_global_data), not in HTTP headers. Requires CDP for initial cookies, HTTP for token extraction. See references/auth-strategies.md "Browser-Delegated Auth" section.
   • No auth / public access: fully public API, no login required. CLI may optionally support API key auth for write operations (e.g., dev.to).

7. Write <APP>.md -- software-specific SOP document

8. Write agent-harness/api-spec.json -- the machine-readable API spec. Every endpoint MUST carry an evidence field citing its captured traffic entry (raw-traffic.json#<index>) — never invent endpoints (this is the structural enforcement of the RPC-ID verification rule). Schema and validator:

   cli-web-devkit spec validate <app>/agent-harness/api-spec.json
   

   Downstream consumers: client method implementation (Step B), the gap-analyzer (cli-web-devkit gaps), and the traffic-fidelity review in Phase 4 (spec-vs-traffic becomes a deterministic diff).

Output: <APP>.md (human SOP) + api-spec.json (machine spec, validated).

References: traffic-patterns.md, google-batchexecute.md, ssr-patterns.md

Step B: Implement (Code Generation)

Study Existing CLIs First (Critical for Accuracy)

Before implementing, read an existing CLI that uses the same protocol as your target. These are battle-tested implementations that solved the same problems you'll face.

How to use reference CLIs:

1. Read the reference CLI's core/client.py — understand the request/response pattern
2. Read core/auth.py — copy the login_browser() pattern exactly for Google apps
3. Read core/rpc/ (for batchexecute) — understand encoder/decoder, DO NOT reinvent
4. Read commands/ — see how Click commands are structured, how --json works
5. Read utils/helpers.py — see handle_errors(), _resolve_cli(), repl patterns

For batchexecute apps specifically, the notebooklm CLI is your bible:

• Copy the encoder/decoder architecture (don't reinvent the batchexecute wire format)
• Copy the auth token extraction pattern (CSRF, session ID, build label)
• Copy the cookie domain priority logic (critical for Israeli/international users)
• Adapt the RPC method IDs and param structures to your target app

The agent implementing the CLI MUST read these files before writing code. Use the Agent tool to dispatch a research agent that reads the reference implementation while you design the command structure.

Design Before You Code

Before writing any code, note the command structure in <APP>.md (10 minutes max):

• Map each API endpoint group to a Click command group:
  • /api/v1/boards/* → boards command group
  • /api/v1/items/* → items command group
• Map CRUD operations to subcommands (GET list → list, GET single → get, POST → create, PUT/PATCH → update, DELETE → delete)
• Note auth design: auth login, auth status, auth refresh; credentials at ~/.config/cli-web-<app>/auth.json
• Note REPL design: bare command enters REPL, branded banner via repl_skin.py

Goal: Generate the complete Python CLI package.

Package Structure

See HARNESS.md "Generated CLI Structure" for the complete package template. Key points: cli_web/ namespace (NO __init__.py), <app>/ sub-package (HAS __init__.py), core/, commands/, utils/, tests/ directories.

Step B.0: Scaffold Core Modules

Run the scaffold generator script (v2 — Jinja2 templates, requires pip install jinja2) to create all boilerplate files:

python ${CLAUDE_PLUGIN_ROOT}/scripts/scaffold-cli.py <app>/agent-harness \
  --app-name <app> \
  --protocol <rest|graphql|html-scraping|batchexecute> \
  --http-client <httpx|curl_cffi> \
  --auth-type <none|cookie|api-key|google-sso> \
  --resource <name> [--resource <name> ...] \
  [--has-polling] [--has-context] [--has-partial-ids]

This renders exceptions.py, client.py skeleton, the unified auth.py (google-sso handled via a template conditional), helpers.py, config.py, output.py, the CLI entry point with REPL, one commands/<resource>.py per --resource flag, setup.py, conftest.py, test_e2e.py skeleton, README/SKILL skeletons, repl_skin.py, and (for batchexecute) the rpc/ subpackage. It also writes .manifest.json (template version + profile) at the harness root — keep it; fleet tooling depends on it. See skills/boilerplate/SKILL.md for the template → output map and per-profile flag recipes.

Fallback: If the script is unavailable, follow skills/shared/RECOVERY.md §scaffold-cli.py Unavailable — adapt from the newest generated CLI (e.g., capitoltrades/agent-harness/), do NOT reconstruct boilerplate from memory.

After scaffolding, review the generated files and customize client.py with actual endpoint methods from <APP>.md.

Implementation Rules

All rules below are DEFINED in skills/shared/CONVENTIONS.md — this section tells you when to apply them during implementation.

• exceptions.py -- implement first. Required hierarchy and error-code mapping: CONVENTIONS.md §Exception Hierarchy. Complete code: references/exception-hierarchy-example.py.

• client.py -- HTTP client with exception mapping and auth retry:

  • HTTP library choice:
    • httpx (default) — for most sites (REST, GraphQL, batchexecute)
    • curl_cffi — for Cloudflare-protected sites. Uses Chrome TLS fingerprint impersonation to bypass bot detection without cookies or auth:

      from curl_cffi import requests as curl_requests
      resp = curl_requests.get(url, impersonate="chrome")
      

      Use curl_cffi when Phase 1 detects Cloudflare (cf-ray header, challenge page). Add curl_cffi, beautifulsoup4 to setup.py instead of httpx.
  • Centralized auth header/cookie injection
  • Automatic JSON parsing with response body verification
  • Status code → exception mapping: 401/403→AuthError, 404→NotFoundError, 429→RateLimitError, 5xx→ServerError (CONVENTIONS.md §Exception Hierarchy)
  • Auth retry (3-attempt auto-refresh): current cookies → reload auth.json → headless refresh, never more. The full table is CONVENTIONS.md §Auth Rules; the templates generate it by default.
  • Exponential backoff for rate limits (CONVENTIONS.md §Exponential Backoff & Polling; code in references/polling-backoff-example.py)
  • For apps with 3+ resource types: split into namespaced sub-clients (client.notebooks.list(), client.sources.add())
  • See references/client-architecture-example.py for the full pattern

• auth.py -- handles token storage, refresh, expiry. Implementation depends on auth type:

  For no-auth sites: DO NOT create auth.py, session.py, or auth command groups. These files are dead code for public APIs and confuse users. The CLI should have NO auth-related files or commands. The only exception is if the site has optional auth (e.g., API key for write operations) — in that case, implement a minimal auth module.

  For browser-delegated auth (Google, Microsoft, etc.): Python sync_playwright() login flow with cookie domain priority for international users (CONVENTIONS.md §Auth Rules).

  Storage, env var, cookie priority, and dual-format handling are defined in CONVENTIONS.md §Auth Rules; implementation code for each pattern is in references/auth-strategies.md (read section-addressed).

• Anti-bot resilient client construction (when detected in Phase 2):

  • Extract session tokens via CDP first (cookies), then HTTP GET + HTML parsing (CSRF, session IDs)
  • Never hardcode build labels (bl), session IDs (f.sid), or CSRF tokens -- extract dynamically at runtime
  • Replicate same-origin headers captured during Phase 1 traffic (e.g., x-same-domain: 1 for Google apps)
  • Implement auto-retry on 401/403: re-fetch homepage -> re-extract tokens -> retry once
  • See references/google-batchexecute.md for the complete Google pattern

• RPC codec subpackage (for non-REST protocols like batchexecute): When the API uses a non-REST protocol, add core/rpc/ with:

  • types.py -- method ID enum, URL constants
  • encoder.py -- request encoding (protocol-specific format)
  • decoder.py -- response decoding (strip prefix, parse chunks, extract results) The client.py still exists but delegates encoding/decoding to rpc/.

• Progress feedback -- Use rich>=13.0 spinners for operations >2s (suppress in --json mode). See references/rich-output-example.py.

• JSON error output -- --json mode errors are JSON too, not plain text (CONVENTIONS.md §JSON Envelope). Implement via utils/output.py json_error().

• All commands use handle_errors(json_mode) context manager — centralizes error handling, exit codes (1=user, 2=system, 130=interrupt), and JSON errors. See references/helpers-module-example.py.

• Generation commands support --wait, --retry N, --output path — CONVENTIONS.md §Exponential Backoff & Polling; code in references/polling-backoff-example.py.

• Windows UTF-8 fix — at the top of <app>_cli.py, reconfigure BOTH stdout AND stderr to UTF-8 before any import that prints (CONVENTIONS.md §Windows UTF-8 Fix has the exact snippet).

• HTML table parsers MUST extract ALL visible columns — not just name/price, because missing fields in --json output make the CLI useless for filtering and analysis. If the site shows version, club, nation, stats, skills, weak foot — parse all of them. Empty fields in --json output = incomplete parser.

• Entry point: cli-web-<app> via setup.py console_scripts (CONVENTIONS.md §Naming Conventions)

• Namespace: cli_web.*

• utils/repl_skin.py, utils/doctor.py, and utils/mcp_server.py are all vendored by scaffold-cli.py (canonical source: cli-web-core/cli_web_core/, synced via cli-web-devkit resync) — never hand-edit the per-CLI copies. The entry point registers the fleet-standard doctor and mcp-serve commands from the vendored adapters (register_doctor_command(cli, ...), register_mcp_command(cli, ...)); both derive from the Click tree, so no per-command wiring is needed.

• utils/helpers.py -- shared CLI helpers (generate for every CLI):

  • resolve_partial_id(partial, items) — prefix-match UUIDs for get/rename/delete
  • handle_errors(json_mode) — context manager replacing try/except in all commands
  • require_notebook(notebook_arg) — gets notebook ID from arg or persistent context
  • sanitize_filename(name) — safe filenames from artifact titles
  • poll_until_complete(check_fn) — exponential backoff polling
  • get_context_value(key) / set_context_value(key, value) — persistent context.json See references/helpers-module-example.py for the complete module.

Not all helpers apply to every CLI. Include only what the CLI uses: handle_errors and print_json are always needed. resolve_partial_id only for UUID-based apps. require_notebook/context helpers only for apps with persistent context. poll_until_complete only for generation/async operations.

REPL Implementation Rules (Critical)

The four REPL rules are defined with code examples in CONVENTIONS.md §REPL Rules — apply them as you wire up <app>_cli.py:

1. Parse REPL lines with shlex.split(line), never line.split().
2. Propagate --json by PREPENDING it to the args list passed to cli.main(args=..., standalone_mode=False) — never **ctx.params.
3. Help-sync: every commit that adds a command/option updates _print_repl_help() in the same commit.
4. Required single values are @click.argument positionals, not @click.option(..., required=True).

These bugs appear in almost every generated REPL — read the §REPL Rules section before writing the entry point, not after the REPL breaks.

Parallel Implementation (dispatch independent modules as subagents)

When the CLI has 3+ command groups (e.g., notebooks, sources, chat, artifacts), dispatch parallel subagents -- one per command module. Each agent gets:

• The <APP>.md API spec for its resource
• The client.py and auth.py interfaces it depends on
• Clear scope: "Implement commands/notebooks.py with list, get, create, delete"

Parallelization opportunities:

Implementation order (with maximum parallelism):

Phase A (sequential): Write core foundation
  exceptions.py → client.py → auth.py (if needed) → models.py

Phase B (parallel): Dispatch ALL independent work simultaneously
  ┌─ Agent 1: commands/notebooks.py
  ├─ Agent 2: commands/sources.py
  ├─ Agent 3: commands/chat.py
  ├─ Agent 4: commands/artifacts.py
  ├─ Agent 5: rpc/encoder.py + rpc/decoder.py (if non-REST)
  └─ Agent 6 (background): test_core.py (unit tests for core modules)
  All run concurrently — each only depends on Phase A modules

Phase C (sequential): Wire everything together
  utils/helpers.py → <app>_cli.py → __main__.py → setup.py
  (repl_skin.py, doctor.py, mcp_server.py were already vendored by
   scaffold-cli.py in Step B.0; the entry point registers doctor + mcp-serve)

Key parallelism rules:

• Dispatch independent command modules as parallel subagents (one per commands/*.py file)
• Start unit test writing as a background agent during command implementation
• Entry point (<app>_cli.py, setup.py) must come last (depends on all commands)

Mandatory Smoke Check (Before Testing Phase)

Before invoking testing, install (pip install -e .) and verify:

1. cli-web-<app> --help loads
2. cli-web-<app> auth status --json shows valid (if auth-required)
3. cli-web-<app> <resource> list --json returns real data
4. One WRITE command works (if applicable)

Red flags — fix before testing: the full table is CONVENTIONS.md §Protocol-Leak Smoke Check (wrb.fr/af.httprm leaks, empty []/null, parser index mismatches). One methodology-specific case: a null WRITE response may mean the operation is client-side — see references/google-batchexecute.md "Client-Side Operations".

Update phase state:

python ${CLAUDE_PLUGIN_ROOT}/scripts/phase-state.py complete <app> \
  --phase methodology --output <app>/agent-harness/

Next Step

When implementation is complete and the smoke check passes, invoke the testing skill to plan and write tests.

Do NOT skip testing -- every CLI must have comprehensive tests before publishing.

Companion Skills

Integration

Reference Files

• references/traffic-patterns.md -- Common API patterns (REST, GraphQL, RPC)
• references/auth-strategies.md -- Auth implementation strategies
• references/google-batchexecute.md -- Google batchexecute RPC protocol spec
• references/ssr-patterns.md -- SSR framework patterns and data extraction strategies
• references/exception-hierarchy-example.py -- Complete exception hierarchy with HTTP status mapping
• references/client-architecture-example.py -- Namespaced sub-client pattern with auth retry
• references/polling-backoff-example.py -- Exponential backoff polling and rate-limit retry
• references/rich-output-example.py -- Rich progress bars, JSON error responses, table formatting