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 skills add tomzx/agents --skill find-type-gapsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/skills/tomzx/agents/find-type-gaps)<a href="https://agentmods.dev/skills/tomzx/agents/find-type-gaps"><img src="https://agentmods.dev/badge/skills/tomzx/agents/find-type-gaps.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.02573 |
| Opus 5 | $0.00018 | $0.01287 |
| Sonnet 5 | $0.00007 | $0.00515 |
| Haiku 4.5 | $0.00004 | $0.00257 |
Grade A, and why
find-type-gaps scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `src/client.py` | 42 | `def fetch(url, timeout)` | param types + return type | How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d
Find Type Gaps
Identifies missing or incomplete type annotations in gradually-typed codebases. Type coverage is a safety net that sits alongside test coverage: typed code catches a class of bugs at analysis time, makes refactoring safer, and reduces the cognitive load of reading unfamiliar code. This skill surfaces gaps ranked by how much adding types would help — prioritizing public API surfaces and high-churn files.
Prerequisites
- Working directory is the root of the repository
- Optional:
$1— path to limit the scan (defaults to.) - Language support:
- Python:
mypy(uv tool install mypy) orpyright(npm install -g pyright) - TypeScript: type errors via
tsc --noEmit; strict mode gaps viatsconfig.jsonflags - JavaScript:
@ts-checkJSDoc annotations;tsc --allowJs --checkJs
- Python:
- Not applicable to fully-typed languages (Go, Rust, Java, C#)
What Counts as a Type Gap
| Language | Gap |
|---|---|
| Python | Function parameter with no annotation; return type missing; Any used where a concrete type is possible; untyped class attribute |
| TypeScript | any used explicitly; as any cast; function with implicit any parameter; missing return type on exported function |
| JavaScript | No JSDoc @param/@returns; no @ts-check at file top; untyped exported function |
Steps
1. Detect Language
find ${1:-.} -type f | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -5
Proceed only if Python, TypeScript, or JavaScript files are present. Report "not applicable" for fully-typed languages.
2. Measure Type Coverage
Python — mypy:
mypy ${1:-.} \
--ignore-missing-imports \
--no-error-summary \
--any-exprs-report .mypy-type-report \
2>/dev/null | rg "error:|note:" | head -40
Parse the any-exprs report for per-file coverage:
cat .mypy-type-report/any-exprs.txt 2>/dev/null | \
awk 'NR>1 {print $3"% typed\t"$1}' | sort -n | head -30
Python — pyright (stricter, faster):
pyright ${1:-.} --outputjson 2>/dev/null | \
python3 -c "
import json, sys
data = json.load(sys.stdin)
for d in data.get('generalDiagnostics', []):
if 'unknown' in d.get('message','').lower() or 'Any' in d.get('message',''):
print(d['file'].split('/')[-1], d['range']['start']['line'], d['message'][:80])
" 2>/dev/null | head -30
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 · 266 lines · 36 tokens per session scan A 329bea1f9528
find-type-gaps is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 2,573 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
plankton-code-quality
Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.
verify-language
Language-specific verification for Python, TypeScript/JavaScript, and Go. Checks type safety, language idioms, and best practices. Use when asked to "verify language", "check types", or for language-specific checks.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.