Agent skill

Verify Cascade

Verification-gated model escalation — run a cheap model, verify its output with decomposed per-field checks, and escalate to a strong model only when a flag fires.

MITAuto-check: notes

Install Verify Cascade

skills CLI

$ npx skills add alinaqi/maggy --skill verify-cascade -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install alinaqi/maggy verify-cascade --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/verify-cascade .claude/skills/verify-cascade && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "verify-cascade" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/verify-cascade into .claude/skills/verify-cascade/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-cascade", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/alinaqi/maggy/tree/main/skills/verify-cascade

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add alinaqi/maggy --skill verify-cascade -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install alinaqi/maggy verify-cascade --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/verify-cascade .agents/skills/verify-cascade && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "verify-cascade" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/verify-cascade into .agents/skills/verify-cascade/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-cascade", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alinaqi/maggy --skill verify-cascade -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install alinaqi/maggy verify-cascade --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/verify-cascade .cursor/skills/verify-cascade && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "verify-cascade" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/verify-cascade into .cursor/skills/verify-cascade/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-cascade", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/alinaqi/maggy.git --path skills/verify-cascade

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add alinaqi/maggy --skill verify-cascade -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install alinaqi/maggy verify-cascade --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/verify-cascade .gemini/skills/verify-cascade && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "verify-cascade" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/verify-cascade into .gemini/skills/verify-cascade/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-cascade", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install alinaqi/maggy verify-cascade

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add alinaqi/maggy --skill verify-cascade -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/verify-cascade .github/skills/verify-cascade && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "verify-cascade" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/verify-cascade into .github/skills/verify-cascade/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-cascade", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alinaqi/maggy --skill verify-cascade -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install alinaqi/maggy verify-cascade --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/verify-cascade .opencode/skills/verify-cascade && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "verify-cascade" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/verify-cascade into .opencode/skills/verify-cascade/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-cascade", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: verify-cascade
GitHub stars: 707
Token cost: ~1.4k tokens
SKILL.md length: 485 words
Files: 2
Skills in repo: 71
Repo updated: Sep 24, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Verification-gated model escalation — run a cheap model, verify its output with decomposed per-field checks, and escalate to a strong model only when a flag fires.

SKILL.md covers The loop, Verifiers (pluggable) —…, What makes a good verifier… and When to reach for it vs plain…, plus 1 more section
Runs Python scripts from its folder; calls python3 and pip; needs TYPESAFE_API_KEY

What it does

Verify Cascade is an agent skill from alinaqi/maggy. Verification-gated model escalation — run a cheap model, verify its output with decomposed per-field checks, and escalate to a strong model only when a flag fires. Optional TypeSafe (jev) verifier.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `verify_cascade.py`).

The repository describes itself as: What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center. The licence is MIT.

Example prompts

“/verify-cascade”

Requirements

Python 3
A credential in TYPESAFE_API_KEY
Pre-approved tools (allowed-tools): Bash, Read, Write

What it can do on your machine

Read from SKILL.md and the folder at commit 72a456e. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Bash
- Read
- Write
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- TYPESAFE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Verify Cascade loads about 1.4k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 485 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~53
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
```
allowed-tools: Bash, Read, Write
```

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from alinaqi/maggy at commit 72a456e, republished under its MIT licence (© alinaqi). 485 words, ~1,357 tokens.

Download SKILL.mdSave it as .claude/skills/verify-cascade/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: verify-cascade
description: Verification-gated model escalation — run a cheap model, verify its output with decomposed per-field checks, and escalate to a strong model only when a flag fires. Optional TypeSafe (jev) verifier.
allowed-tools: Bash, Read, Write
when-to-use: When you want the token economy of a cheap model but the reliability of a strong one — structured extraction, data pulls, patch/summary checks — and would…
user-invocable: true
effort: medium

Verify-Cascade — extract cheap, verify, escalate only on a flag

maggy already routes by task complexity. This makes routing output-aware: a cheap model does the work, a decomposed verifier checks it, and you escalate to a strong model (Claude) only when the verifier flags a real problem. The cheap rung handles the easy items for near-free; only flagged items pay for the strong model — most of the quality of the big model at a fraction of the cost.

It's the same discipline as the security-audit finder ≠ validator gate, applied to routing: an independent verifier catches the cheap model's blind spots.

The loop

1. EXTRACT   cheap model produces an output (extraction / answer / summary)
2. VERIFY    a decomposed verifier asks narrow per-field yes/no questions,
             framed so "bad = true", and returns P(wrong) per question
3. GATE      escalate if ANY question's P(wrong) > fire threshold (max, not mean)
4. ESCALATE  only the flagged items pay for the strong model; the rest keep the cheap answer

Schema-validation is necessary but not sufficient: a cheap model produces confident, schema-valid fabrications (a blank field filled with a plausible invented value). A structural check can't see that — a semantic verifier can.

Verifiers (pluggable) — `verify_cascade.py`

bash

VC="$(cat ~/.claude/.bootstrap-dir)/skills/verify-cascade/verify_cascade.py"
python3 "$VC"          # self-test (stubbed judge, no network, no model)

LocalVerifier — the default, nothing leaves your machine

Runs the whole decomposed question battery through a cheap CLI model in one call and returns {field::metric: P(wrong)}. No external service.

python

import sys
sys.path.insert(0, f"{__import__('subprocess').check_output(['cat', __import__('os').path.expanduser('~/.claude/.bootstrap-dir')]).decode().strip()}/skills/verify-cascade")
# (or simply: sys.path.insert(0, "<bootstrap-dir>/skills/verify-cascade"))
from verify_cascade import get_verifier, build_questions, cascade
v = get_verifier("local")                     # uses $MAGGY_JUDGE_CMD (default: deepseek --flash)
result = cascade(
    extract  = lambda: cheap_extract(...),     # your cheap-model call -> dict
    verify   = lambda rec: v.verify({"source_text": source}, build_questions(rec, schema)),
    escalate = lambda: strong_extract(...),    # your strong-model call -> dict
    fire_t   = 0.7,
)
# result: {record, escalated: bool, fired: [qid...], scores: {qid: p}}

Set the judge model with MAGGY_JUDGE_CMD (e.g. qwen3, deepseek --flash) or pass your own judge=callable(prompt)->text. The default passes the prompt on stdin (no shell, so prompt content is never interpreted as a command), so MAGGY_JUDGE_CMD must read from stdin. Questions are scored in complete batches and an over-long source warns on stderr rather than being silently truncated.

TypeSafeVerifier — OPT-IN, and it sends data to a third party

TypeSafe's hosted jev model is purpose-built and calibrated for this. But:

⚠️ Data leaves your machine. TypeSafeVerifier.verify() POSTs the source_text, schema, and extraction to api.typesafe.ai. Only use it for content you are willing to send to a third party. It is off by default — it will not even construct without TYPESAFE_API_KEY, so nothing is sent unless you opt in.

bash

pip install typesafe_sdk
export TYPESAFE_API_KEY=…            # opt-in; enables the external call

python

v = get_verifier("typesafe")         # raises unless TYPESAFE_API_KEY is set

Everything else (questions, gate, cascade) is identical — the verifier is the only swap.

Show full SKILL.md (183 more words)Show less

What makes a good verifier signal

Narrow + grounded — one checkable yes/no about one field against the source, not a vague "is this good?".
Bad = TRUE, explicit criteria — frame the escalate case as the true case.
Per-field, aggregate with max — a per-field flag localizes the error and stays sparse; max means one confident red flag escalates instead of being averaged away.
Independent + cheap — a dedicated verifier judges the worker's output and catches its blind spots, and it has to be cheap or there are no savings left to capture.
Calibrated — high on real errors, low on correct ones, so one threshold splits accept vs escalate.

When to reach for it vs plain routing

Use verify-cascade when the output can be checked against a source (extractions, RAG answers, data pulls, structured summaries). For open-ended generation with no ground truth, stick to maggy's task-complexity routing. The two compose: classify to pick the cheap rung, verify to decide whether to escalate.

Attribution

Pattern from TypeSafe's public "SDE cascade" cookbook, rebuilt so the verifier is pluggable and the private LocalVerifier is the default; TypeSafe is an optional adapter.

Files

SKILL.md and 1 other file in skills/verify-cascade of alinaqi/maggy.

SKILL.md
verify_cascade.py

Open the folder on GitHubat commit 72a456e

Compare with similar skills

Verify Cascade next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Verify Cascade compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Verify Cascade this skillalinaqi/maggy	707	—	~1.4k	Automated safety check: Notes	MIT	15 days ago
Gate Testsvercel/next.js	143k	—	~2.8k	Automated safety check: Pass	MIT	today
Gateplugin87/ux-ui-agent-skills	1.6k	—	~532	Automated safety check: Pass	MIT	2 days ago
Brain Ingest Gategarrytan/gbrain	31k	—	~3.9k	Automated safety check: Pass	MIT	today
Delivery Gateaffaan-m/ECC	276k	—	~1.3k	Automated safety check: Pass	MIT	today
Bill Gatessickn33/agentic-awesome-skills	47k	2 repos	~352	Automated safety check: Pass	MIT	today

Similar skills

Gate Tests
vercel/next.js
Official
How to use the @gate / @force-gate test directives instead of it.skip or fake-green skip patterns.
143k GitHub stars~2.8k tokensUpdated today
Auto-check passed
Gate
plugin87/ux-ui-agent-skills
Run the one-command quality gate and report the real N/N result.
1.6k GitHub stars~532 tokensUpdated 2 days ago
Frontend & DesignAuto-check passed
Brain Ingest Gate
garrytan/gbrain
Pre-write quality gate for content entering the brain. An agent skill from garrytan/gbrain.
31k GitHub stars~3.9k tokensUpdated today
Testing & QAAuto-check passed
Delivery Gate
affaan-m/ECC
Stop hook that blocks Claude from finishing until quality checks pass.
276k GitHub stars~1.3k tokensUpdated today
Auto-check passed
Bill Gates
sickn33/agentic-awesome-skills
Agente que simula Bill Gates — cofundador da Microsoft, arquiteto da industria de software comercial, estrategista tecnologico global, investidor sistemico e filantropo baseado em dados.
47k GitHub starsUsed in 2 repos~352 tokens
Auto-check passed
Skill Release Gate
rohitg00/ai-engineering-from-scratch
Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.
66k GitHub stars~1k tokensUpdated today
Agent WorkflowsAuto-check passed

Questions about Verify Cascade

What does Verify Cascade do?

Verification-gated model escalation — run a cheap model, verify its output with decomposed per-field checks, and escalate to a strong model only when a flag fires. Verify Cascade is an agent skill from alinaqi/maggy. Verification-gated model escalation — run a cheap model, verify its output with decomposed per-field checks, and escalate to a strong model only when a flag fires.

How do I install Verify Cascade in Claude Code?

Run `npx skills add alinaqi/maggy --skill verify-cascade -a claude-code`. Or copy the skill folder (skills/verify-cascade in alinaqi/maggy) into .claude/skills/verify-cascade in your project. Claude Code loads it when a task matches its description.

How do I install Verify Cascade in Codex?

Run `npx skills add alinaqi/maggy --skill verify-cascade -a codex`. Or copy the skill folder (skills/verify-cascade in alinaqi/maggy) into .agents/skills/verify-cascade in your project. Codex loads it when a task matches its description.

Can I use Verify Cascade in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alinaqi/maggy --skill verify-cascade -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-cascade, .gemini/skills/verify-cascade, .github/skills/verify-cascade and .opencode/skills/verify-cascade in your project.

What does Verify Cascade need to run?

Going by SKILL.md and its folder, Verify Cascade needs Python for the scripts in its folder, the command-line tools its instructions call (python3 and pip) and credentials named TYPESAFE_API_KEY. Our summary lists: Python 3; A credential in TYPESAFE_API_KEY. Its frontmatter pre-approves these tools: Bash, Read, Write.

Does Verify Cascade access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Verify Cascade safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Verify Cascade use?

Verify Cascade is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verify Cascade use?

About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Verify Cascade?

Skills that share tags, products or a category with Verify Cascade: Gate Tests (vercel/next.js, 143k stars), Gate (plugin87/ux-ui-agent-skills, 1.6k stars), Brain Ingest Gate (garrytan/gbrain, 31k stars) and Delivery Gate (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify Cascade?

alinaqi (a GitHub user) maintains it in alinaqi/maggy, which has 707 GitHub stars. The repository holds 71 skills in this directory. The repository was last updated on September 24, 2026.

Source: alinaqi/maggy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Verify Cascade

Install Verify Cascade

Facts

At a glance

What it does

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Verify-Cascade — extract cheap, verify, escalate only on a flag

The loop

Verifiers (pluggable) — `verify_cascade.py`

LocalVerifier — the default, nothing leaves your machine

TypeSafeVerifier — OPT-IN, and it sends data to a third party

What makes a good verifier signal

When to reach for it vs plain routing

Attribution

Files

Compare with similar skills

Similar skills

Gate Tests

Gate

Brain Ingest Gate

Delivery Gate

Bill Gates

Skill Release Gate

More from alinaqi/maggy

Aeo Optimization

Agent Teams

AI Models

Android Java

Android Kotlin

Autonomous Testing

Questions about Verify Cascade

Install Verify Cascade

Facts

At a glance

What it does

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Verify-Cascade — extract cheap, verify, escalate only on a flag

The loop

Verifiers (pluggable) — verify_cascade.py

LocalVerifier — the default, nothing leaves your machine

TypeSafeVerifier — OPT-IN, and it sends data to a third party

What makes a good verifier signal

When to reach for it vs plain routing

Attribution

Files

Compare with similar skills

Similar skills

More from alinaqi/maggy

Questions about Verify Cascade

Verifiers (pluggable) — `verify_cascade.py`