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 instructions/panewslab/skills/agents-mdgit clone --depth 1 https://github.com/panewslab/skillsWrote 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/instructions/panewslab/skills/agents-md)<a href="https://agentmods.dev/instructions/panewslab/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/panewslab/skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01121 | $0.01121 |
| Opus 5 | $0.00561 | $0.00561 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
skills AGENTS.md 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 4d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is for agents developing this repository itself.
The project is neither a PANews API reference nor an end-user manual. It is the source repository for the PANews agent package: three skills, two CLI bundles, repo-root plugin manifests, and the documentation that ties them together.
What This Repo Produces
panews: structured PANews news discovery for crypto and blockchain coveragepanews-creator: authenticated PANews creator workflowspanews-web-viewer: rendered PANews page reads as Markdownskills/*/scripts/cli.mjs: bundled Node entrypoints forpanewsandpanews-creator/.codex-plugin/plugin.json: Codex-style plugin manifest at repo root/.claude-plugin/plugin.json: Claude Code plugin manifest at repo root
Canonical Sources
Treat these as the source of truth:
src/: business logic, schemas, command wiring, shared utilitiesskills/*/SKILL.md: user-facing skill contract and routing/discovery surfaceskills/*/references/workflow-*.md: detailed task recipesskills/*/agents/openai.yaml: OpenAI-specific discovery metadataREADME.md: repository-level product and installation documentation/.codex-plugin/plugin.jsonand/.claude-plugin/plugin.json: plugin metadata for repo-root plugin packaging
Treat these as generated artifacts:
skills/panews/scripts/cli.mjsskills/panews-creator/scripts/cli.mjs
Do not hand-edit generated bundles unless the user explicitly asks for that. Change src/ and rebuild instead.
Repo Shape
src/
commands/ TypeScript command implementations
utils/ shared formatting, HTTP, language, and session helpers
panews.ts panews bundle entry
panews-creator.ts panews-creator bundle entry
skills/
panews/
SKILL.md
agents/openai.yaml
references/workflow-*.md
scripts/cli.mjs
panews-creator/
SKILL.md
agents/openai.yaml
references/workflow-*.md
scripts/cli.mjs
panews-web-viewer/
SKILL.md
agents/openai.yaml
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.
- 4d ago First seen · 115 lines · 1,121 tokens per session scan A 22492758f5d2
skills AGENTS.md is an instructions file published in the GitHub repository panewslab/skills (42 stars, last pushed 4mo ago), licensed MIT. It adds 1,121 tokens to every session, about $0.0056 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.
Other instructions, from other repositories
nostr-auth-agents AGENTS.md
AGENTS.md instructions for dyegolara/nostr-auth-agents, covering agents.md — nostr-auth for coding agents, what this tool does, when to run it, quick invocation and recommended flow.
solana-glossary CLAUDE.md
Instructions for solanabr/solana-glossary, covering solana development configuration, communication style, branch workflow, mandatory workflow and security principles.
cc-master AGENTS.md
AGENTS.md instructions for nemori-ai/cc-master, covering cc-master, 1. 这个插件是什么, 2. 仓库形态 + 关键不变式, 3. non-negotiable 红线(ssot 在此) and 4. 迭代范式总图(gstack × superpowers 路由).
cc-master CLAUDE.md
Claude Code instructions for nemori-ai/cc-master, a project described as: Turn any Code Harness session into a long-horizon master orchestrator — pick the right dynamic-workflow paradigm and keep the main thread productively advancing across compaction and sessions.
bitcoin-mcp copilot-instructions.md
Instructions for Bortlesboat/bitcoin-mcp, covering bitcoin-mcp copilot instructions, rules, satoshi api reference and verification.
drpc-agent-skills GEMINI.md
Gemini CLI instructions for drpcorg/drpc-agent-skills: @./skills/drpc-rpc/SKILL.md @./skills/drpc-rpc/setup.md @./skills/drpc-rpc/direct-http.md @./skills/drpc-rpc/tools-reference.md @./skills/drpc-rpc/recipes-simple.md @./skills/drpc-rpc/recipes-crosschain.md @./skills/drpc-rpc/recipes-defi-basics.md…