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 jamestorrevillas/dev-skills --skill code-explanationgit clone --depth 1 https://github.com/jamestorrevillas/dev-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/skills/jamestorrevillas/dev-skills/code-explanation)<a href="https://agentmods.dev/skills/jamestorrevillas/dev-skills/code-explanation"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/code-explanation/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/jamestorrevillas/dev-skills/code-explanation"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/code-explanation.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 | $0.00067 | $0.00685 |
| Opus 5.5 | $0.00027 | $0.00274 |
| Sonnet 5.5 | $0.00013 | $0.00137 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
code-explanation 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 1mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Explanation
Core Principle
Comments explain WHY. Code explains WHAT.
If you need a comment to explain what the code does, the code should be cleaner. If you need a comment to explain why it's done this way — write that comment.
The Four Levels of Code Explanation
| Level | Where | Explains |
|---|---|---|
| Inline comment | Next to specific line | Non-obvious logic or gotcha |
| Function docstring | Top of function | What it does, parameters, returns, side effects |
| Module header | Top of file | What this module is responsible for |
| Architecture note | README / ADR | Why this approach was chosen over alternatives |
What to Comment (and What Not To)
Comment This
// Using exponential backoff here because the payment API
// has a 429 rate limit that triggers on burst traffic
await retryWithBackoff(() => paymentAPI.charge(amount))
// Intentionally not validating here — validation happens
// upstream in the middleware layer (see auth.middleware.ts)
const user = req.user
// This looks backwards but the API returns results
// in reverse chronological order — newest = index 0
const latest = results[0]
Don't Comment This
// Increment counter by 1
count++
// Check if user is authenticated
if (user.isAuthenticated) {
Docstring Template
/**
* Calculates the discount amount for a given order.
*
* @param order - The order to calculate discount for
* @param promoCode - Optional promo code to apply
* @returns The discount amount in cents, or 0 if no discount applies
* @throws InvalidPromoCodeError if the promo code format is invalid
*
* Note: Does NOT check if the promo code is active —
* call validatePromoCode() first.
*/
PR Description: Explaining Your Decisions
When your PR makes non-obvious decisions, explain them:
## Technical Decisions
**Why I chose X over Y:**
[reasoning — constraints, trade-offs, what you considered]
**Known limitations:**
[what this doesn't handle and why that's acceptable for now]
**What I'd do differently with more time:**
[honest reflection — shows growth mindset]
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.
- 1mo ago First seen · 119 lines · 0 tokens per session scan A 7c49eedd25e8
code-explanation is a skill published in the GitHub repository jamestorrevillas/dev-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 67 tokens to every session and 685 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.
semantic-codebase-intelligence
Deep structural analysis of a codebase—dependency mapping, architecture boundary detection, coupling/cohesion scoring, and dead code discovery. Use when asked to "analyze codebase structure", "map dependencies", "find dead code", "architecture analysis", "coupling analysis", "trace dependencies", or "understand this…
code-review
Systematic code review for correctness, security, and growth — not just style enforcement.
deep-review
Adversarial code review with three parallel perspectives — Advocate, Skeptic, Architect — that create productive tension. Use for high-stakes PRs, architectural changes, or when single-pass review would miss issues. Surfaces findings through disagreement, not consensus.
extension-audit-methodology
Systematic 5-dimension audit framework for VS Code extensions — debug hygiene, dead code, performance, menu validation, dependency cleanup.
parity-guard-test-pattern
When checking that all callers of a contract implement it correctly, you get false positives from wrapper delegators.