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/adrielp/ai-engineering-harness/github-trackernpx skills add adrielp/ai-engineering-harness --skill github-trackergit clone --depth 1 https://github.com/adrielp/ai-engineering-harnessWhat 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 | $0.00204 | $0.02175 |
| Opus 5 | $0.00102 | $0.01087 |
| Sonnet 5 | $0.00041 | $0.00435 |
| Haiku 4.5 | $0.00020 | $0.00217 |
Grade A, and why
github-tracker scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The `gh` CLI must be installed and authenticated (`gh auth status` should succeed). All commands use `gh` — never raw `curl` with tokens. How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Tracker
Surface GitHub pull requests, issues, notifications, and project board items that need attention using the gh CLI.
Read-Only Safety Constraint
This skill is strictly read-only. NEVER execute any gh command that creates, modifies, or deletes GitHub resources. This means:
Allowed: gh search, gh pr view, gh issue view, gh pr checks, gh api (GET requests), gh api graphql (queries only), gh repo list, gh pr list, gh issue list, gh notification list
Forbidden: gh pr create, gh pr merge, gh pr close, gh pr edit, gh pr review, gh issue create, gh issue close, gh issue edit, gh pr comment, gh issue comment, gh api -X POST/PUT/PATCH/DELETE (any mutating HTTP method), any GraphQL mutations, or any other command that writes data to GitHub.
If the user asks you to take an action on GitHub (merge a PR, comment on an issue, close something), tell them this skill is read-only and they should do it themselves in the GitHub UI or CLI.
Prerequisites
The gh CLI must be installed and authenticated (gh auth status should succeed). All commands use gh — never raw curl with tokens.
Before running any commands, verify gh is available:
gh auth status
If this fails, tell the user to install and authenticate gh: https://cli.github.com/
Getting the Current User
Never hardcode a username. Always resolve it dynamically:
gh api user --jq '.login'
Cache the result in a variable for the session.
Core Workflows
1. PRs Needing My Attention
This is the most common ask. "Attention" means multiple things — combine these signals:
a) Review requests (highest priority):
gh search prs --review-requested=@me --state=open --json repository,title,number,url,updatedAt,labels --limit 50
b) PRs where I'm mentioned or assigned:
gh search prs --mentions=@me --state=open --json repository,title,number,url,updatedAt --limit 30
gh search prs --assignee=@me --state=open --json repository,title,number,url,updatedAt --limit 30
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 · 222 lines · 204 tokens per session scan A 6c0de066bb86
github-tracker is a skill published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 204 tokens to every session and 2,175 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…