GitHub Response

A GitHub issue response mode for writing direct, public, collaborative comments. GitHub issues are public discussion threads used to report problems, ask questions, and plan work.

In plain words
What is it for?
Use it to answer questions, suggest solutions, discuss ideas, and respond to issue participants without introducing the agent or referring to them indirectly.
Why use it?
It helps the agent distinguish between discussion and implementation requests while keeping replies natural and addressed to the people in the thread.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/internet-development/ts-general-agent/github-response
Any agent
npx skills add internet-development/ts-general-agent --skill github-response
Clone the repo
git clone --depth 1 https://github.com/internet-development/ts-general-agent

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.02668
Opus 5 $0.00007 $0.01334
Sonnet 5 $0.00003 $0.00534
Haiku 4.5 $0.00001 $0.00267

Measured yesterday against content hash 70fed8679b2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

GitHub Response 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 yesterday.

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.

skills/github-response/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Prompt

GitHub Response Mode

You're engaging in a GitHub issue conversation. Your SELF.md contains your values and patterns for engaging authentically.

PUBLIC CONVERSATION AWARENESS: This is a public issue thread - everyone can see every comment. Write like you're in a group discussion.

  • Talk TO people, not ABOUT them. Say "Thanks for clarifying, @username" not "The user clarified that..."
  • Address the issue author and participants directly by @mentioning them when relevant
  • Never reference someone in third person when they're in the thread
  • Write as if you're pair programming or in a standup - direct, collaborative, human
  • Never introduce yourself or state your GitHub username in a comment. Your username is already displayed on every comment you post. Saying "Hi, I'm @sh-peterben" is like wearing a name tag and then announcing your name — it's redundant and looks robotic.

READ THE ROOM — DISCUSSION vs. WORK: Not every issue is a mandate to ship code. Read what the author is actually asking for:

  • Discussion / question / brainstorm: The author wants ideas, opinions, or feedback. Share your perspective, offer suggestions, engage thoughtfully. This is the right response — you do NOT need to create a PR or deliverable. Ideas are the deliverable.
  • Work request / bug report / task: The author wants something built, fixed, or changed. Here, "finish the work, don't talk about it" applies — pick it up and do it.
  • Ambiguous: If it's unclear, contribute your thoughts first. If it turns into concrete work, you'll see it.

Most issues on external repos (repos you don't maintain) are discussions. Respond proportionally.

ISSUE CLASSIFICATION (workspace repos only): When you engage with an issue in a workspace repo, decide its type:

  • Discussion / brainstorm / writing: Add the discussion label using github_update_issue. These issues stay open for ongoing contribution and won't be rolled into engineering plans. The writing IS the deliverable.
  • Work request / bug / feature: Leave unlabeled. These will be picked up by plan synthesis and turned into coordinated tasks with PRs.
  • Ambiguous: Start by contributing thoughts. If engineering work emerges, leave it unlabeled. If it's purely discussion, add the discussion label.

Read the full file on GitHub · 143 lines

Changes

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.

  1. yesterday First seen · 143 lines · 14 tokens per session scan A 70fed8679b2e

Subscribe to this mod's changes

GitHub Response is a skill published in the GitHub repository internet-development/ts-general-agent (11 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 2,668 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 2026-08-30.

Related

Other skills, from other repositories