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 agentmods add skills/nicolasmelo1/logion/with-evalnpx skills add nicolasmelo1/logion --skill with-evalgit clone --depth 1 https://github.com/nicolasmelo1/logionWrote 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/nicolasmelo1/logion/with-eval)<a href="https://agentmods.dev/skills/nicolasmelo1/logion/with-eval"><img src="https://agentmods.dev/badge/skills/nicolasmelo1/logion/with-eval.svg" alt="Measured on agentmods" 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 | $0.00104 | $0.01530 |
| Opus 5 | $0.00052 | $0.00765 |
| Sonnet 5 | $0.00021 | $0.00306 |
| Haiku 4.5 | $0.00010 | $0.00153 |
Grade A, and why
with-eval 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 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.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
With-Eval: Checklist-Driven PR Review
This skill reviews code diffs against a bundled checklist. The agent reads references/checklist.md, walks the diff category by category, and writes a structured review naming any violated categories by their stable code (e.g. security:sql-injection, reliability:missing-error-handling).
The output format is deliberately structured — one line per finding, with the category code, file path, line number, and a short description. The categories don't change between versions, so reviews are comparable across diffs and across time.
How the agent uses this skill
When asked to review a diff:
- Read
references/checklist.md(loaded on-demand via progressive disclosure — not loaded at activation). - Walk the diff against each category in the checklist.
- For each issue found, write one line in the format:
<category-code> <path>:<line> — <short description> - If the diff is clean, write a single line:
no issues.
That's the entire workflow. The user gets a list of categorised findings or a clean bill of health.
Example output
For a diff that introduces a string-concatenated SQL query and a hardcoded API key:
security:sql-injection users/dao.py:7 — query built via string concatenation with user-supplied `email`
security:hardcoded-secret users/dao.py:4 — API key stored as a string literal
When to use this skill
- Pre-merge PR review (the obvious case).
- Auditing a vendor patch before applying it.
- Self-review before pushing a feature branch.
- Anywhere you'd otherwise get a free-form "looks good 👍" from an agent — this skill forces a categorised answer.
Capability declarations
tools: [file, terminal]— reads the diff, the checklist, writes the review.filesystem.write: [./evals/reviews, ./evals/reports]— review output + self-test verdicts (see below).- No network, no secrets, no human approval. The skill runs entirely locally.
Verifying the skill works: bundled self-test
What ships with it
12 files 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.
- course/capabilities.yaml 1.1 KB
- evals/expected/buggy_pr.json 396 B
- evals/expected/clean_pr.json 427 B
- evals/fixtures/buggy_pr.diff 772 B
- evals/fixtures/clean_pr.diff 439 B
- evals/reports/.gitkeep 0 B
- evals/reviews/.gitkeep 0 B
- evals/runner.py 3.3 KB runs code
- evals/scenarios.json 612 B
- LICENSE 1.0 KB
- README.md 5.1 KB
- references/checklist.md 2.6 KB
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 · 131 lines · 104 tokens per session scan A ce5fa599aaba
with-eval is a skill published in the GitHub repository nicolasmelo1/logion (36 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 1,530 once invoked, about $0.0005 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
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
convex-seed
Seed or import data into the Convex database.
antivibe
Code learning and audit framework. Analyze any codebase — new, legacy, or AI-generated — and produce educational explanations or architectural audits. Use when the user wants to understand WHAT and WHY behind any code, not just accept it.
cloudflare-d1
Cloudflare D1 serverless SQLite on edge. Use for databases, migrations, bindings, or encountering D1ERROR, statement too long, too many requests queued errors.
cloudflare-vectorize
Cloudflare Vectorize vector database for semantic search and RAG. Use for vector indexes, embeddings, similarity search, or encountering dimension mismatches, filter errors.
cloudflare-kv
Cloudflare Workers KV global key-value storage. Use for namespaces, caching, TTL, or encountering KVERROR, 429 rate limits, consistency issues.