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/kimgoetzke/coding-agent-configs/explain-prnpx skills add kimgoetzke/coding-agent-configs --skill explain-prgit clone --depth 1 https://github.com/kimgoetzke/coding-agent-configsWrote 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/kimgoetzke/coding-agent-configs/explain-pr)<a href="https://agentmods.dev/skills/kimgoetzke/coding-agent-configs/explain-pr"><img src="https://agentmods.dev/badge/skills/kimgoetzke/coding-agent-configs/explain-pr.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 | $0.00062 | $0.05958 |
| Opus 5 | $0.00031 | $0.02979 |
| Sonnet 5 | $0.00012 | $0.01192 |
| Haiku 4.5 | $0.00006 | $0.00596 |
Grade A, and why
explain-pr 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 — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain PR
You are tasked with helping the user understand a GitHub pull request, not review it. The goal is comprehension through visualisation and a structured, interactive tour of the diffs. You do not produce a review document. You do not score dimensions. You guide the user.
Step 1: Resolve the PR and detect mode
Verify gh is available with gh --version. If missing, tell the user this skill needs GitHub CLI and stop.
Detect the mode:
- If any argument equals
html(case-insensitive), setmode = html. The remaining arguments (if any) identify the PR. - Otherwise, set
mode = interactive.
Resolve the PR identifier from the remaining arguments:
- If a PR number or URL was provided:
- If the URL points to a different repository, tell the user to switch to that repo and rerun, then stop.
- Otherwise, extract the PR number.
- If no PR identifier was provided:
- Run
gh pr view --json number,title,urlto detect a PR from the current branch. - If none, stop and ask the user for a PR number or URL.
- Run
Fetch metadata and diff:
gh pr view {number} --json number,title,url,body,author,headRefName,baseRefName,headRefOid,state,additions,deletions,changedFiles,files
gh pr diff {number}
Build the permalink prefix for later use:
-
Parse
{owner}/{repo}from the PR URL (https://github.com/{owner}/{repo}/pull/{number}). -
Read
{head_sha}fromheadRefOid. -
Permalink for any file in this PR is:
https://github.com/{owner}/{repo}/blob/{head_sha}/{file path}
Use these permalinks everywhere a file path is mentioned to the user — scope listings, walkthrough plan stops, stop headings, HTML output — so the user can click straight to the pinned source.
Step 2: Build the introduction
In interactive mode: produce a single markdown message with these four sections, in order. Be ruthlessly concise.
In html mode: produce the same content but capture it for later substitution into the template (see Step 7). Do not print it to the user.
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.
- 4d ago First seen · 417 lines · 62 tokens per session scan A 08d9e0b48f4e
explain-pr is a skill published in the GitHub repository kimgoetzke/coding-agent-configs (2 stars, last pushed 14d ago), licensed MIT. It adds 62 tokens to every session and 5,958 once invoked, about $0.0003 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 skills, from other repositories
teach
Teach the user a new skill or concept, within this workspace.
scaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
pr-review-response
Teaches agents to reply to PR review comment threads after fixing issues, making resolutions traceable.
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
using-pi-subagents
Operate pi-subagents jobs safely, including direct-work decisions, least-privilege tool selection, thinking-level selection, delegation, bidirectional messaging, parallel starts, timeout selection, waiting, cancellation, result handling, verification, and writer isolation.
pi-ralph-wiggum
Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.