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 internet-development/ts-general-agent --skill github-responsegit clone --depth 1 https://github.com/internet-development/ts-general-agentWrote 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/internet-development/ts-general-agent/github-response)<a href="https://agentmods.dev/skills/internet-development/ts-general-agent/github-response"><img src="https://agentmods.dev/badge/skills/internet-development/ts-general-agent/github-response/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/internet-development/ts-general-agent/github-response"><img src="https://agentmods.dev/badge/skills/internet-development/ts-general-agent/github-response.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 | $0.00014 | $0.02668 |
| Opus 5.5 | $0.00006 | $0.01067 |
| Sonnet 5.5 | $0.00003 | $0.00534 |
| Haiku 4.5 | $0.00001 | $0.00267 |
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 1mo 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 — 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
discussionlabel usinggithub_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
discussionlabel.
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.
- 1mo ago First seen · 143 lines · 14 tokens per session scan A 70fed8679b2e
GitHub Response is a skill published in the GitHub repository internet-development/ts-general-agent (11 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 2,668 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 2026-08-30.
Other skills, from other repositories
Code Execution
Run Python, Node.js, AND arbitrary shell commands in a secure E2B cloud sandbox that PERSISTS across calls within a conversation. Clone repos, install packages, run CLI tools (git, psql, ffmpeg, duckdb), and build up state turn over turn.
Parallel Web Research
Deep web research powered by Parallel.ai — fast search with excerpts, URL→markdown extraction, long-running Task Runs, structured find-all datasets, and persistent web monitors.
CSV / Spreadsheet Operations
List sheets, read rows, read a single line, and write back to spreadsheets. Supports .csv / .tsv / xlsx / Google Sheets. Canonical partner for agentbatch when iterating row-by-row.
Platos RAG
Ingest documents into the agent's long-term memory, then retrieve chunks semantically at turn-time. Five tools — ingest, retrieve, list, reindex, delete. Chunks are stored on the user's PlatosMemory rows with kind="rag" in metadata, so scope + user isolation comes for free.
Email Send
Send transactional emails through Resend. Supports HTML / plain-text bodies, reply-to, cc, bcc, and tags.
File Operations
Read and write files in the agent's per-conversation MinIO workspace.