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/bugrabilge/bilge-development-kit/pushnpx skills add bugrabilge/bilge-development-kit --skill pushgit clone --depth 1 https://github.com/bugrabilge/bilge-development-kitWhat 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 | $0.00054 | $0.02065 |
| Opus 5 | $0.00027 | $0.01033 |
| Sonnet 5 | $0.00011 | $0.00413 |
| Haiku 4.5 | $0.00005 | $0.00206 |
Grade A, and why
push 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/push - Safe Push Pipeline
$ARGUMENTS
Purpose
All-in-one command that validates code quality, ensures test coverage, generates a meaningful commit message, and pushes to remote. Prevents broken code, leaked secrets, and lazy commits from reaching the repository.
Sub-commands
/push - Full pipeline: check → stage → commit → push
/push check - Run all checks without committing or pushing
/push --force - Skip checks (shows warning, requires confirmation)
/push --amend - Amend last commit and force-push (shows warning)
Behavior
When /push is triggered:
Phase 1: Pre-Push Checks
Run these checks sequentially. Stop on any Critical failure.
1.1 Branch Safety
Run: git branch --show-current
| Condition | Action |
|---|---|
Branch is main or master |
WARN: "Direkt main'e push ediyorsun. Emin misin?" — Kullanıcı onayı gerekli |
| Branch is behind remote | WARN: "Remote'da yeni commit'ler var. Önce git pull önerilir" |
| Branch is up to date | OK |
1.2 Secret Scan
Search staged files for:
- API keys: /[A-Za-z0-9_]{20,}/ in suspicious contexts
- Passwords: password\s*=\s*["'][^"']+
- Tokens: token\s*=\s*["'][^"']+
- AWS keys: AKIA[0-9A-Z]{16}
- Private keys: -----BEGIN.*PRIVATE KEY-----
- .env files staged
| Finding | Action |
|---|---|
| Secret detected | CRITICAL STOP — Do NOT proceed. Show file:line and ask user to remove |
.env file staged |
CRITICAL STOP — ".env dosyası commit'e dahil. Kaldır." |
| Clean | OK |
1.3 Debug Statement Scan
Search staged files for:
- console.log (JS/TS)
- print() without context (Python)
- debugger (JS/TS)
- binding.pry (Ruby)
- dd() (PHP)
| Finding | Action |
|---|---|
| Debug statements found | WARN — List them, ask: "Bunlar kalmalı mı?" |
| Clean | OK |
1.4 Lint Check
Detect and run project linter:
- package.json has "lint" script → npm run lint
- .eslintrc exists → npx eslint .
- ruff.toml/.flake8 exists → ruff check . / flake8
- No linter → Skip with note
| Result | Action |
|---|---|
| Lint errors | WARN — Show errors, ask: "Düzelteyim mi?" |
| Lint clean | OK |
| No linter configured | SKIP — Note in report |
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 · 294 lines · 54 tokens per session scan A e5d2e3a1155c
push is a skill published in the GitHub repository bugrabilge/bilge-development-kit (10 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 2,065 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
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…