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/jscholz/hermes-agent-workflow/claude-mdgit clone --depth 1 https://github.com/jscholz/hermes-agent-workflowWrote 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/jscholz/hermes-agent-workflow/claude-md)<a href="https://agentmods.dev/instructions/jscholz/hermes-agent-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/jscholz/hermes-agent-workflow/claude-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 5.1 | $0.05644 | $0.05644 |
| Opus 5 | $0.02822 | $0.02822 |
| Sonnet 5 | $0.01129 | $0.01129 |
| Haiku 4.5 | $0.00564 | $0.00564 |
Grade D, and why
hermes-agent-workflow CLAUDE.md scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
have the user run `sudo tailscale set --operator=$USER` once, then Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- If `bun` is missing: "Sidekick (the PWA frontend) needs bun. Want sidekick? If yes, install line is `curl -fsSL https://bun.sh/install | bash`. If no, skip — sidekick is optional." Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- If `bun` is missing: "Sidekick (the PWA frontend) needs bun. Want sidekick? If yes, install line is `curl -fsSL https://bun.sh/install | bash`. If no, skip — sidekick is optional." How it starts
The opening of the file, as written. The whole thing — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — install conductor for hermes-agent-workflow
You are Claude Code, opened inside (or near) a clone of
hermes-agent-workflow.
The user has asked you to install this template. Follow the
sections below in order. Each section names: what state the user
is in, what you should probe, what to ask, what to do, success
criteria. Read this whole file before starting so you know what's
ahead.
How to use this file
- Voice: address the user in 2nd person. Narrate each step before you run it. Surface every destructive action for explicit confirmation.
- Authority:
scripts/bootstrap.sh --env-file <path>is the source of truth for install steps. Don't re-implement what bootstrap does. Your job is to gather values, write the env-file, invoke bootstrap, narrate output, and verify withdoctor.sh. - Idempotency: every step is safe to re-run. If the user interrupts mid-install, "claude, continue installing hermes-agent-workflow" picks up from wherever the file system state indicates we left off.
- Failure model: if a step fails, print the failing command + log location, ask the user whether to retry / skip / abort. Never silently move on.
- Self-detect state at every section start: probe before asking. If a step is already done, narrate that and skip.
Section 0 — State detection (run first, every time)
Before any user-facing prompt, probe the file system to figure out where we are. All probes are read-only.
# 0a. Are we inside a hermes-agent-workflow clone?
git rev-parse --show-toplevel 2>/dev/null
ls "$(git rev-parse --show-toplevel 2>/dev/null)/scripts/bootstrap.sh" 2>/dev/null
# 0b. Is there a clone elsewhere?
ls ~/code/hermes-agent-workflow/.git 2>/dev/null
# 0c. Has bootstrap run before? (sentinel)
ls ~/.hermes/.bootstrap.complete 2>/dev/null
stat -c '%y' ~/.hermes/.bootstrap.complete 2>/dev/null
# 0d. Is git-crypt unlocked? (read first 9 bytes of any encrypted file)
head -c 9 ~/.hermes/.env 2>/dev/null | od -c | head -1
# "GITCRYPT" magic bytes = encrypted/locked, anything else = plaintext or absent
# 0e. Is the gateway healthy?
systemctl --user is-active hermes-gateway.service 2>/dev/null
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.
- 5d ago First seen · 561 lines · 5,644 tokens per session scan D f8c820eb787b
hermes-agent-workflow CLAUDE.md is an instructions file published in the GitHub repository jscholz/hermes-agent-workflow (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 5,644 tokens to every session, about $0.0282 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).