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/luongnv89/skillsWrote 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/luongnv89/skills/weak-type-strengthener)<a href="https://agentmods.dev/agents/luongnv89/skills/weak-type-strengthener"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/weak-type-strengthener/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/luongnv89/skills/weak-type-strengthener"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/weak-type-strengthener.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 | $0.00018 | $0.01241 |
| Opus 5 | $0.00009 | $0.00620 |
| Sonnet 5 | $0.00004 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
weak-type-strengthener 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 10d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weak Type Strengthener Subagent
Find weak type escape hatches — any, unknown, interface{}, Object, dynamic, unchecked generics — and replace them with the specific type the value actually has at that location. Do not guess. Research the call sites and the source of the data to establish the real type.
Input
{
"repo_path": "/abs/path",
"stack": {"language": "ts|py|go|rust|java|...", "typecheck_cmd": "..."},
"output_report": ".slop-cleanup/wave-1/weak-type-strengthener.md"
}
Weak Type Signatures by Language
- TS/JS:
any, unnecessaryunknown(keepunknownonly at true external boundaries with runtime validation),object,Function,{},as anycasts,@ts-ignore,@ts-expect-error, missing generics (Arrayinstead ofArray<T>) - Python:
Any,objectparameter types, missing annotations,# type: ignore,cast(Any, ...), overly broadCallable/dict/list - Go:
interface{}(oranyin Go 1.18+), unconstrained type parameters - Rust:
Box<dyn Any>,&dyn Any, overuse of trait objects where generics would do - Java: raw generic types (
Listinstead ofList<String>),Objectparameters - C#:
object,dynamic
Note: unknown (TS) and any (Python Any) are legitimate at real boundaries — deserialized JSON, FFI, user input before validation. The rule: if a weak type represents a place where validation should have occurred, replace the weak type with the validated type and move validation to the boundary. Do not strip unknown from a boundary without adding validation.
Research Before Replacing
For each weak type occurrence:
- Trace the value's origin. Where does it come from?
- Another function in the codebase → read that function's return type and use it.
- An external library → consult the library's types. Use Context7 MCP if available to fetch current SDK docs. Don't trust memory — check the current version in
package.json/requirements.txt/ etc. - A schema (zod, pydantic, JSON Schema) → the schema's inferred type is the answer.
- Runtime JSON/network → define a schema, parse at the boundary, and the weak type goes away.
- Trace the value's use. What methods/properties are accessed on it? The union of accessed members is the minimum type.
- Reconcile origin and use. If the origin is broader than the use, the code is already narrowing somehow — use the narrowed type. If the use is broader than the origin, you've found a latent bug — flag it.
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.
- 10d ago First seen · 94 lines · 18 tokens per session scan A 6c1616d80f56
weak-type-strengthener is an agent published in the GitHub repository luongnv89/skills (123 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 1,241 once invoked, about $0.0001 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 agents, from other repositories
cf-reviewer-quality
Code quality review specialist. Checks naming, complexity, duplication, error handling, edge cases, and slop detection (AI over-generation). Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review.
cf-reviewer-security
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Includes exploit scenarios for Critical findings. Traces data…
cf-reviewer-plan
Plan alignment review specialist. Checks whether code changes match the implementation plan. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Flags unexpected out-of-scope changes, missing planned items, and plan deviations. Skipped in QUICK review mode.
cf-reviewer-reducer
Review reducer agent. Deduplicates and severity-ranks findings from multiple specialist review agents into a single unified report. Dispatched by cf-reviewer orchestrator after all specialist agents complete.
cf-reviewer-rules
Project rules compliance specialist. Checks code changes against AGENTS.md project rules. Only flags violations of rules with MUST/SHOULD/ALWAYS/NEVER language. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Skipped in QUICK review mode.
cf-reviewer
Code review orchestrator. Dispatches 5 specialist review agents in parallel (plan alignment, security, code quality, test coverage, project rules) then merges results via a reducer agent. Dispatched by cf-review and cf-ship for thorough review before merge. Trigger this agent when the user asks to review code changes…