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/newturn2017/hermes-profile-kit/agents-mdgit clone --depth 1 https://github.com/NewTurn2017/hermes-profile-kitWrote 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/newturn2017/hermes-profile-kit/agents-md)<a href="https://agentmods.dev/instructions/newturn2017/hermes-profile-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/newturn2017/hermes-profile-kit/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 | $0.01272 | $0.01272 |
| Opus 5 | $0.00636 | $0.00636 |
| Sonnet 5 | $0.00254 | $0.00254 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade B, and why
hermes-profile-kit AGENTS.md scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Seeds `.env` from `.env.example` (chmod 600). NEVER overwrites an existing `.env`. How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Execution Playbook
Canonical instructions for LLM agents (Claude Code, Codex, Cursor). This kit is a CLI installer. Treat any "install / add / set up " request as execution work, not design work.
Standing user instructions (highest priority)
When a user asks you to install a profile from this kit:
- Do NOT invoke
brainstorming,writing-plans,test-driven-development,requesting-code-review, or any superpowers process skill. They turn a 2-minute install into a 30-minute design cycle. The user has explicitly told you not to. - Do NOT read
docs/superpowers/specs/, fullmanifest.yaml, orsrc/hpk/unless the user reports a specific error. - Read this file + the
tokens.requiredsection ofmanifest.yamlfor the target profile. That's enough. - Ask the user for required tokens in one message. (Optional tokens listed in the per-profile table can be skipped for the 2-minute path or offered separately if the user wants them.) Then run
hpk setup <profile> --non-interactive --token KEY=VAL ... --accept-plugin ID. - Finish with
hpk verify <profile>and report.
Fast-path: seb
pipx install --upgrade hermes-profile-kit
hpk setup seb --non-interactive \
--token SLACK_BOT_TOKEN=<xoxb-...> \
--token SLACK_SIGNING_SECRET=<32-hex> \
--token SLACK_APP_TOKEN=<xapp-...>
hpk verify seb
Only 3 Slack tokens are required. Fastest path to get them: tell the
user to create the app from profiles/seb/slack-app-manifest.json at
https://api.slack.com/apps → Create New App → From an app manifest →
paste the JSON. That provisions all bot scopes, app_mention event,
Socket Mode, and interactivity in one step; the user then copies
SLACK_BOT_TOKEN (Install App), SLACK_APP_TOKEN (Basic Information →
App-Level Tokens → Generate with connections:write), and
SLACK_SIGNING_SECRET (Basic Information → App Credentials).
The model uses Hermes's native openai-codex provider — no proxy plugin,
no OpenAI API key. Prerequisite: the user has codex auth login done.
The codex-openai-proxy plugin is now opt-in (default false); do NOT
pass --accept-plugin codex-openai-proxy unless the user explicitly asks
for the local HTTP bridge.
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 · 98 lines · 1,272 tokens per session scan B 487413d8fddf
hermes-profile-kit AGENTS.md is an instructions file published in the GitHub repository NewTurn2017/hermes-profile-kit (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,272 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.