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 wrannaman/agentic-engineering --skill github-reviewgit clone --depth 1 https://github.com/wrannaman/agentic-engineeringWrote 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/wrannaman/agentic-engineering/github-review)<a href="https://agentmods.dev/skills/wrannaman/agentic-engineering/github-review"><img src="https://agentmods.dev/badge/skills/wrannaman/agentic-engineering/github-review/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/wrannaman/agentic-engineering/github-review"><img src="https://agentmods.dev/badge/skills/wrannaman/agentic-engineering/github-review.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 | $0.00020 | $0.02704 |
| Opus 5.5 | $0.00008 | $0.01082 |
| Sonnet 5.5 | $0.00004 | $0.00541 |
| Haiku 4.5 | $0.00002 | $0.00270 |
Grade A, and why
github-review 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 2mo 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Review Skill
You are entering the github-review phase. You will address review comments from a GitHub Pull Request.
Process
Step 0: Detect Stack Structure
Detect the active stack workflow using the git-stacks KB partition as the shared source of truth:
-
list_kb_documentsfor partitiongit-stacks -
read_kb_document_by_pathfor/index.md -
Run the dedicated-client checks from
git-stacks/index.md- If a dedicated client is detected, record
STACK_CLIENTaccordingly - If no dedicated client is detected, inspect the current PR base and local branch relationships to decide whether this repo is using a native git stack
- If confirmed, record
STACK_CLIENT=native-git
- If a dedicated client is detected, record
-
Load the matching KB client doc before running any stack-specific command:
charcoal→read_kb_document_by_pathfor/charcoal.mdgit-town→read_kb_document_by_pathfor/git-town.mdnative-git→read_kb_document_by_pathfor/native-git.md- Use the client doc as the source of truth for stack navigation commands
If in a stack:
- You may have multiple PRs with review comments
- Present option to address comments from all PRs or just current
Present to user (if in stack):
## Stack Detected
Your stack has N PRs with open review comments:
| PR | Branch | Open Comments |
|----|--------|---------------|
| #123 | feat/part-1 | 2 |
| #124 | feat/part-2 | 5 |
| #125 | feat/part-3 | 0 |
How would you like to proceed?
1. Address all PRs (recommended) - Fix comments across all PRs
2. Address current PR only (#124) - Fix comments on feat/part-2 only
Step 1: Pull OPEN (Unresolved) PR Review Comments
For stacked PRs: Pull comments from each PR in scope.
First, identify the PR(s) and pull only unresolved review threads using GraphQL (the REST API does not expose resolved/unresolved status):
# Get PR number and basic info from current branch
gh pr view --json number,title,url,reviewDecision
# Get ONLY unresolved review threads using GraphQL
gh api graphql -f query='
query($owner: String!, $repo: String!, $pr: Int!) {
repository(owner: $owner, name: $repo) {
pullRequest(number: $pr) {
reviewThreads(first: 100) {
nodes {
isResolved
path
line
comments(first: 10) {
nodes {
author { login }
body
createdAt
}
}
}
}
}
}
}' -f owner='{owner}' -f repo='{repo}' -F pr=<PR_NUMBER>
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.
- 2mo ago First seen · 392 lines · 20 tokens per session scan A a6e3549e522a
github-review is a skill published in the GitHub repository wrannaman/agentic-engineering (2 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 2,704 once invoked, about $0.0001 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.
github-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| github-reviewwrannaman/agentic-engineering | Skill | 2 | 6mo ago | MIT | A | 20 | Claude Code, Codex |
| prYeachan-Heo/oh-my-claudecode | Skill | 41k | today | MIT | A | 47 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 83k | 6d ago | MIT | A | 46 | Claude Code |
| otto-pr-review-loopomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 17 | Claude Code, Codex |
| engram-branch-prGentleman-Programming/engram | Skill | 7.8k | today | MIT | A | 37 | Claude Code, Codex |
| github-contributordaymade/claude-code-skills | Skill | 1.5k | today | MIT | A | 105 | Claude Code, Codex |
| revdiffumputun/revdiff | Skill | 947 | 2d ago | MIT | A | 250 | Claude Code |