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 commands/latestaiagents/agent-skills/explain-codegit clone --depth 1 https://github.com/latestaiagents/agent-skillsWhat 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 | $0.00007 | $0.01065 |
| Opus 5 | $0.00003 | $0.00532 |
| Sonnet 5 | $0.00001 | $0.00213 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
explain-code 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 2d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/explain-code
Generate clear explanations for complex code sections.
What to Explain
Share the code you want explained, or point me to a file.
You can ask for:
- Overview - What does this code do at a high level?
- Line-by-line - Explain each part in detail
- Concept - Explain the underlying pattern or algorithm
- Why - Explain design decisions and tradeoffs
Explanation Levels
Level 1: Quick Summary
One paragraph explaining what the code does:
This function implements a debounce mechanism that delays executing
a callback until after a specified wait time has passed since the
last invocation. It's commonly used to limit the rate of API calls
triggered by user input like typing in a search box.
Level 2: Annotated Code
Comments explaining each significant line:
function debounce<T extends (...args: any[]) => any>(
func: T, // The function to debounce
wait: number // Milliseconds to wait
): (...args: Parameters<T>) => void {
let timeoutId: NodeJS.Timeout | null = null; // Store timeout reference
return (...args: Parameters<T>) => {
// Clear any existing timeout (reset the timer)
if (timeoutId) {
clearTimeout(timeoutId);
}
// Set new timeout - func will only run if no new calls come in
timeoutId = setTimeout(() => {
func(...args); // Call original function with arguments
timeoutId = null; // Clean up reference
}, wait);
};
}
Level 3: Concept Deep Dive
Explain the underlying pattern:
## Debouncing Explained
**Problem:** User types in search box, triggering API call on every keystroke.
Typing "hello" causes 5 API calls (h, he, hel, hell, hello).
**Solution:** Debouncing waits until user stops typing before making the call.
Only 1 API call for "hello" (after 300ms of no typing).
**How it works:**
1. User types 'h' → Start 300ms timer
2. User types 'e' (100ms later) → Cancel timer, start new 300ms timer
3. User types 'l' (100ms later) → Cancel timer, start new 300ms timer
4. ... continues until user stops
5. 300ms passes with no typing → Execute API call with "hello"
**Visual timeline:**
Keystrokes: h----e----l----l----o-------------------> Timers: [==X] [==X] [==X] [==X] [=====EXECUTE!] └── 300ms pause
**Related concepts:**
- **Throttling:** Execute at most once per interval (different from debounce)
- **Leading edge:** Execute immediately, then debounce subsequent calls
- **Trailing edge:** (default) Execute after the wait period
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.
- 2d ago First seen · 143 lines · 7 tokens per session scan A 2c63f090eab5
explain-code is a command published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 1,065 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
fw-setup-use
Workspace FDK stack switch — nvm use from .nvmrc or explicit 10/9 (Node 24.11 vs 18); optional --write-nvmrc and --global flags.
fdk-migrate
Migrate a legacy Freshworks app from platform-version 2.3 (2.x), FDK 9.x, and Node 18 to Platform 3.0 with FDK 10.0.1 and Node 24.11.0. Transforms manifest, request templates, Crayons UI, and validates on the new toolchain. Does not install fdk/Node—use fw-setup (or prompt user to add it) per SKILL.md.
fdk-fix
Fix all platform validation errors and lint errors in a Freshworks app. Runs fdk validate, identifies fatal errors and lint issues, applies fixes iteratively, and re-validates until all errors are resolved.
fdk-react-create
Create a new Platform 3.0 React Meta app (default UI stack). Uses fdk create react-starter-template or react-meta skeletons with DEW components, metaConfig in manifest.json, and React Router.
fw-setup-status
Check FDK and Node.js installation status (/fw-setup status); optional --verbose diagnostics.
fdk-refactor
Reduce function complexity in a Freshworks app to meet cyclomatic complexity ≤ 7 per function. Extracts helper functions, simplifies conditionals, and preserves behavior while improving code quality.