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/p2ergmbh/agentic-coding/github-issue-createnpx skills add P2ERGmbH/agentic-coding --skill github-issue-creategit clone --depth 1 https://github.com/P2ERGmbH/agentic-codingWhat 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 | $0.00022 | $0.01525 |
| Opus 5 | $0.00011 | $0.00763 |
| Sonnet 5 | $0.00004 | $0.00305 |
| Haiku 4.5 | $0.00002 | $0.00153 |
Grade A, and why
github-issue-create 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Agent Task Workflow
This workflow guides you through creating a detailed GitHub issue using the gemini_agent_workflow.md template. This is the mandatory first step when a user requests a new feature or complex change.
Trigger
Use this workflow when the user asks to "create a task," "plan a feature," "spec out a ticket," or "create a workflow issue."
Phase 1: Deep Research & Analysis (Using Subagent)
- Analyze User Request: Identify the core goal and any implicit requirements.
- Delegate to Subagent: ALWAYS use the
codebase_investigatorsubagent to perform the deep research. Pass it the user's objective and ask it to:- Walk through the feature as a user and define the Browser Click Path (relevant routes, exact steps).
- Investigate Schema & Database: Check project configuration (
package.jsonunder"agents"key, ordocs/project.json) forpaths.dbandpaths.types. If configured, use those paths to search for database/migration files and types/data models. If not configured, dynamically search for directories nameddb,prisma,database, ortypesusing codebase search tools. - Identify all relevant files (Page components, API routes, Service logic) that need modification to ensure complete coverage.
- Review Subagent Report: Use the structured report provided by the
codebase_investigatorto inform the implementation plan.
Phase 2: Formulate & Refine Implementation Plan (Subagent-Driven)
Before creating any issue on GitHub, the implementation plan must be drafted, scrutinized by a subagent, and interactively approved by the user.
-
Draft Initial Plan:
- Synthesize the research and draft an initial implementation plan.
- Break down the work into logical, atomic steps with precise reasons for each step.
- Fill out all template fields (Proposed Changes, Testing Strategy, Browser Click Path, i18n/translations, Performance/Edge cases).
-
Subagent Grilling & Refinement:
- Mandatory: ALWAYS delegate the initial plan to a specialized
general-purposesubagent to grill it. - Instruct the subagent to locate potential architectural flaws, edge cases, missing translations, verification gaps, and project-rule violations (
docs/rules/). - The subagent MUST perform all plan refinements, producing a highly secure, detailed, and polished version of the plan.
- Mandatory: ALWAYS delegate the initial plan to a specialized
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 · 101 lines · 22 tokens per session scan A 8d168b65a7f4
github-issue-create is a skill published in the GitHub repository P2ERGmbH/agentic-coding (9 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 1,525 once invoked, about $0.0001 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…