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.
git 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/agents/itamarzand88/cli-anything-web/cross-cli-consistency-checker)<a href="https://agentmods.dev/agents/itamarzand88/cli-anything-web/cross-cli-consistency-checker"><img src="https://agentmods.dev/badge/agents/itamarzand88/cli-anything-web/cross-cli-consistency-checker/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/agents/itamarzand88/cli-anything-web/cross-cli-consistency-checker"><img src="https://agentmods.dev/badge/agents/itamarzand88/cli-anything-web/cross-cli-consistency-checker.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 | $0.00071 | $0.01814 |
| Opus 5.5 | $0.00028 | $0.00726 |
| Sonnet 5.5 | $0.00014 | $0.00363 |
| Haiku 4.5 | $0.00007 | $0.00181 |
Grade A, and why
cross-cli-consistency-checker 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 2mo 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-CLI Consistency Checker
Audit all generated cli-web-* CLIs against the conventions defined in
skills/shared/CONVENTIONS.md.
This is a read-only audit — it reports findings but does not auto-fix.
Step 1: Discover CLIs
Read registry.json at the repository root to get the list of all CLIs.
For each entry, note the directory, namespace, and auth fields.
Fallback: If registry.json doesn't exist, glob for
*/agent-harness/cli_web/*/__init__.py to find CLI packages.
Step 2: Locate Reference Files
The canonical repl_skin.py lives in the shared runtime package:
cli-web-core/cli_web_core/repl_skin.py (the copy at
cli-anything-web-plugin/scripts/repl_skin.py is a vendored mirror synced by
cli-web-devkit resync). Drift detection against it is automated — see
Check 11. Also read skills/shared/CONVENTIONS.md for the rule definitions
behind the checks below.
Step 3: Run Check Matrix
For each discovered CLI, run all applicable checks. Mark checks as N/A when they don't apply (e.g., auth checks for no-auth CLIs).
Check 1: Exception Hierarchy (Critical)
Read core/exceptions.py and verify:
- Base error class exists with
to_dict()method - All 5 subtypes present: AuthError, RateLimitError, NetworkError, ServerError, NotFoundError
RateLimitErrorhasretry_afterfield ANDto_dict()includes itServerErrorstoresstatus_codeas instance attributeraise_for_status()maps: 401/403→AuthError, 404→NotFoundError, 429→RateLimitError, 5xx→ServerError
How to check:
Grep for "def to_dict" in exceptions.py
Grep for "retry_after" in exceptions.py — must appear in both __init__ and to_dict
Grep for "status_code" in ServerError class
Check 2: UTF-8 Fix (Critical)
Read *_cli.py and verify BOTH stdout AND stderr are reconfigured:
Grep for "stdout.reconfigure" and "stderr.reconfigure" in *_cli.py
Both must be present. Only stdout = FAIL.
Check 3: REPL Parsing (Critical)
Read *_cli.py and verify shlex.split is used in the REPL loop:
Grep for "shlex.split" in *_cli.py — must be present
Grep for "line.split()" in *_cli.py — must NOT be present (or only in non-REPL context)
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.
- 2mo ago First seen · 205 lines · 71 tokens per session scan A 105d2d727553
cross-cli-consistency-checker is an agent published in the GitHub repository ItamarZand88/CLI-Anything-WEB (239 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 1,814 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
ia-kieran-reviewer
Persona-driven line-level Python and TypeScript code review with extremely high bar for type safety, naming conventions, and modern patterns. Use for line-level Py/TS quality after PR implementation. For broader review workflow, use the code-review skill.
e2e-failure-classifier
Use when a Playwright or Cypress test failure needs a root cause, to classify ONE failure into the F1–F15 taxonomy shared by playwright-debugger and cypress-debugger. Give it the failing test name and the report excerpt (error, stack, attempt info); it reads the spec and config, returns the F-code with confidence…
e2e-finding-verifier
Use after e2e-reviewer or the Node scanner reports findings, to adversarially verify ONE finding in its real code context before it is acted on. Give it the pattern ID, file:line, and the flagged snippet; it reads the surrounding spec, project config, and the pattern contract, tries to REFUTE the finding first, and…
skeptic
Adversarial verifier for one or more review findings, each judged on its own; or, in CHECK mode, a quick check you run and then verify. Given claimed issues plus the code, tries to refute each against reality to cut false positives. Use to verify findings before they are reported. Read-only. Also cross-checks a single…
docs
Documentation expert for API docs review, README assessment, inline documentation analysis, and changelog evaluation. Use when reviewing documentation quality, checking docs-code sync, or evaluating developer onboarding materials.
pragmatist
Pragmatic ROI analyst for overengineering detection, effort-vs-value assessment, scope creep identification, and "good enough" evaluation. Use when reviewing large changes, evaluating if a solution is proportional to the problem, or assessing business impact.