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 agentmods add commands/itamarzand88/cli-anything-web/refinegit clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEBWrote 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/commands/itamarzand88/cli-anything-web/refine)<a href="https://agentmods.dev/commands/itamarzand88/cli-anything-web/refine"><img src="https://agentmods.dev/badge/commands/itamarzand88/cli-anything-web/refine.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 | $0.00043 | $0.00756 |
| Opus 5 | $0.00022 | $0.00378 |
| Sonnet 5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
cli-anything-web:refine 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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL: Read HARNESS.md First
Before refining, read ${CLAUDE_PLUGIN_ROOT}/HARNESS.md. All new commands and tests must follow the same standards as the original build. HARNESS.md is the navigational overview; the rules themselves are defined in ${CLAUDE_PLUGIN_ROOT}/skills/shared/CONVENTIONS.md.
CLI-Anything-Web: Refine Existing Harness
Read the methodology SOP: @${CLAUDE_PLUGIN_ROOT}/HARNESS.md
Target: $1 Focus area: $2
Process
Skills used:
gap-analyzer(mandatory FIRST step),methodology(pipeline),capture(if re-recording)
- Gap analysis (FIRST step — always): Invoke the
gap-analyzerskill (${CLAUDE_PLUGIN_ROOT}/skills/gap-analyzer/SKILL.md) withAPP_PATH=<app>/agent-harness. It diffs the captured/documented API surface against the implemented commands and client methods. Every reported gap must cite its evidence: the endpoint entry in<APP>.mdand/ortraffic-capture/traffic-analysis.json(withraw-traffic.jsonhit counts for priority). If a focus area is specified, filter the report to that domain. - Present gap report: Show the user the gap analysis results and confirm which gaps to address before proceeding with any recording or implementation
- Record new traffic: Use playwright-cli (see HARNESS.md Phase 1) or chrome-devtools-mcp fallback
- Analyze new endpoints: Add to API map in
<APP>.md - Implement new commands: Add to existing command groups or create new ones
- Update REPL help: Edit
_print_repl_help()in<app>_cli.pyto reflect every new command and option added (CONVENTIONS.md §REPL Rules help-sync rule). Users typinghelpin the REPL must see all available filters and options. - Update tests: Add unit + E2E tests for new commands
- Run full test suite: Ensure no regressions
- Update TEST.md: Document new coverage
Rules
- NEVER break existing commands
- NEVER change existing command signatures
- ADD new commands and options only
- Run full test suite after changes
- Update
<APP>.mdwith new endpoints - Always update
_print_repl_help()to match the actual command surface
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.
- 4d ago First seen · 65 lines · 43 tokens per session scan A 2564881e8f7b
cli-anything-web:refine is a command published in the GitHub repository ItamarZand88/CLI-Anything-WEB (216 stars, last pushed 10d ago), licensed MIT. It adds 43 tokens to every session and 756 once invoked, about $0.0002 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 commands, from other repositories
record-demo
Guided Playwright browser recording.
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; request automation of…
feature-video
Record a video walkthrough of a feature and add it to the PR description.
run-yaml-test
Execute YAML-based Playwright test cases with step library references and parameter substitution support.
update-success-rate
Check benchmark JSONL results and update success rates in benchmark-comparison.md.
git
Git operations with intelligent commit messages and workflow optimization.