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 hyhmrright/logic-lens --skill logic-healthgit clone --depth 1 https://github.com/hyhmrright/logic-lensWrote 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/hyhmrright/logic-lens/logic-health)<a href="https://agentmods.dev/skills/hyhmrright/logic-lens/logic-health"><img src="https://agentmods.dev/badge/skills/hyhmrright/logic-lens/logic-health/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/skills/hyhmrright/logic-lens/logic-health"><img src="https://agentmods.dev/badge/skills/hyhmrright/logic-lens/logic-health.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00180 | $0.00972 |
| Opus 5 | $0.00090 | $0.00486 |
| Sonnet 5 | $0.00036 | $0.00194 |
| Haiku 4.5 | $0.00018 | $0.00097 |
Grade A, and why
logic-health 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 11d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logic-Lens — Logic Health
Setup
Use lazy loading per ../_shared/common.md §13:
- Read
../_shared/common.mdonly for language, Iron Law, Logic Score, scope routing, Remedy discipline, config fields, and loading budget. - Read only the relevant step in
logic-health-guide.mdas you reach it. - Load
../_shared/logic-risks.md,../_shared/semiformal-guide.md,../_shared/semiformal-checklist.md,../_shared/report-template.md, and../logic-review/logic-review-guide.mdon demand when the current module trace needs them.
Process
Step 0. Language + scope routing. Detect language per common.md §1. Proceed for multi-file scopes and for single-module scopes when the user explicitly uses "health check", "health overview", or "logic health". If scope is one file and none of those health phrases appear, switch to logic-review.
Step 1. Enumerate modules and plan the sweep (guide Step 1) — prioritize public API surfaces, recently changed files, and user-flagged modules. Read .logic-lens.yaml only for ignore:, focus:, disable:, severity:, custom_risks, and trace.* fields. For broad scopes, build a ranked worklist before opening files.
Step 2. Run focused logic-review per module (guide Step 2) — apply Premises → Trace → Divergence on public-facing functions; skip internal helpers unless a trace leads into them. Apply the per-module function budget from guide Step 2 (small/medium/large line-count tiers) — do not trace all functions in large modules.
Step 3. Record findings per module (guide Step 3) — tag module, L-code, severity.
Step 4. Aggregate findings (guide Step 4) — counts by severity and by L-code; cross-reference modules.
Step 5. Compute scores (guide Step 5) — per-module Logic Score via the standard formula; overall score is the line-weighted average (per common.md §6).
Step 6. Identify systemic patterns (guide Step 6) — L-codes appearing in ≥ 3 modules or ≥ 30% of scanned modules (whichever threshold is lower) indicate codebase-wide habits; architectural enablers (heavy global state → L7; deep callee chains → L6) get explicit mention.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 67 lines · 180 tokens per session scan A f9de78a503cd
logic-health is a skill published in the GitHub repository hyhmrright/logic-lens (22 stars, last pushed 12d ago), licensed MIT. It adds 180 tokens to every session and 972 once invoked, about $0.0009 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 skills, from other repositories
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
skeptic
Adversarial code reviewer for Bug Hunter. Rigorously challenges each reported bug to determine if it's real or a false positive. Uses doc-lookup (Context Hub + Context7) to verify framework claims before disproval. The immune system that kills false positives.
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
debug
Systematic bug investigation with a five-phase framework: reproduce, narrow, diagnose, fix, verify. Supports automated regression bisect via --regression flag. Produces a structured debug report with root cause analysis, regression test, and CQ/Q self-evaluations.
ai-antipatterns
Audit for AI-written-code anti-patterns: hallucinated APIs/symbols/imports, invented config/env keys, needless dependencies, over-engineering, ignored existing conventions/helpers. Use for AI code review, hallucination check, over-engineering or ignored-conventions audit of a diff.
river-review-code
A general code-review skill that checks readability, maintainability, and type safety, with routing for several specialized checks.