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 Varnan-Tech/opendirectory --skill explain-this-prgit clone --depth 1 https://github.com/Varnan-Tech/opendirectoryWrote 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/varnan-tech/opendirectory/explain-this-pr)<a href="https://agentmods.dev/skills/varnan-tech/opendirectory/explain-this-pr"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/explain-this-pr/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/varnan-tech/opendirectory/explain-this-pr"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/explain-this-pr.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 | $0.00121 | $0.01121 |
| Opus 5.5 | $0.00048 | $0.00448 |
| Sonnet 5.5 | $0.00024 | $0.00224 |
| Haiku 4.5 | $0.00012 | $0.00112 |
Grade A, and why
explain-this-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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain This PR
Read a GitHub pull request, understand what it changes, and write a plain-English explanation. Post it as a PR comment so reviewers have instant context.
Step 1: Check Setup
Confirm gh is authenticated:
gh auth status
If not authenticated: gh auth login and follow the prompts.
Confirm input. The user must provide one of:
- A GitHub PR URL (e.g.
https://github.com/owner/repo/pull/123) - A PR number in the current repo (e.g.
#123) - The keyword "current" to use the PR for the current branch
If no input, ask: "Which PR should I explain? Share the URL, PR number, or say 'current' for the active branch."
Step 2: Fetch PR Context
Get PR metadata:
gh pr view PR_URL_OR_NUMBER --json number,url,title,body,author,baseRefName,headRefName,additions,deletions,changedFiles,commits,labels,state,isDraft
If isDraft is true, note this to the user: "This PR is still in draft. The explanation is based on its current state."
Get the diff:
gh pr diff PR_URL_OR_NUMBER
If the diff is over 400 lines, read the --stat summary and the first 200 lines of the diff:
gh pr view PR_URL_OR_NUMBER --json files
gh pr diff PR_URL_OR_NUMBER | head -200
Get existing comments (to avoid repeating what is already there):
gh pr view PR_URL_OR_NUMBER --json comments --jq '.comments[].body' 2>/dev/null | head -20
Step 3: Write the Explanation
Write two paragraphs. Read each rule before writing.
Paragraph 1: What it does (technical)
- One sentence per major change
- Name the specific files, functions, or systems that changed
- State the before/after if the diff makes it clear
- Include concrete numbers if present in the diff (lines removed, tables dropped, endpoints added)
- Active voice, present tense
Example:
Replaces the in-memory session cache in auth.middleware.ts with a Redis-backed cache (src/cache/redis.ts). Adds get, set, and invalidate methods to the new Redis module and wraps UserService.getById() with a 5-minute TTL. Removes the Map-based cache that was limited to a single process and caused session drift across multiple instances.
What ships with it
2 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.
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.
- 9d ago Changed · -1 lines eee76cb7ca0a
- 1mo ago First seen · 131 lines · 121 tokens per session scan A a0c22a5941a2
explain-this-pr is a skill published in the GitHub repository Varnan-Tech/opendirectory (682 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 1,121 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
coding-worktree-recovery
Use this skill when coding-agent work is interrupted, an agent exits without a clean commit, multiple controllers target the same checkout, or the checkout produces inconsistent file/Git behavior.
github-pre-push-gates
Before pushing a branch to a shared remote, run through these gates. They prevent pushing credentials, PII, private history, or a broken tree. The skill covers the pre-PR quality phase — use github-pr-workflow for the PR lifecycle itself.
local-app-github-publishing
Use this when the user asks to push a local app/prototype/project to GitHub for the first time, especially Electron, iOS/Xcode, mobile, desktop, or AI/API-integrated apps.
stale-patch-reconciliation
Use when a patch/diff must be compared with, repaired against, or refreshed for a moving checkout — "is this patch still needed", "does upstream already contain it", "what changed since it was written", "reconcile X.diff with HEAD", or "make apply-patches pass again".
github-workflows
Use this skill for the full GitHub operating loop: 1) authenticate, 2) manage repos and remotes, 3) open and review PRs, 4) work on issues, and 5) monitor CI.
github-pages-portfolio
Build, update, and verify a single-page static portfolio / intro site on GitHub Pages (pure HTML+CSS+JS, no build step). Covers sourcing content read-only from the user's existing GitHub repos (public AND private), the free-tier public-repo requirement, anchor+accordion single-page design (hidden content revealed on…