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/tbcrawford/opm/agents-mdgit clone --depth 1 https://github.com/tbcrawford/opmWrote 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/tbcrawford/opm/agents-md)<a href="https://agentmods.dev/instructions/tbcrawford/opm/agents-md"><img src="https://agentmods.dev/badge/instructions/tbcrawford/opm/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 | $0.01573 | $0.01573 |
| Opus 5 | $0.00787 | $0.00787 |
| Sonnet 5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
opm 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 3d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project
opm — OpenCode Profile Manager
A Go CLI tool that manages multiple OpenCode configurations by symlinking ~/.config/opencode to named profile directories. Users switch between completely isolated OpenCode environments (different MCPs, plugins, agents, models, AGENTS.md) with a single command.
Core Value: Switching OpenCode profiles should be one command — opm use <name> — and take effect after reloading OpenCode.
Command API
All subcommands are flat (no context grouping):
| Command | Description |
|---|---|
opm init |
Initialize opm and migrate existing OpenCode config |
opm use <name> |
Switch to a profile |
opm create <name> |
Create a new profile |
opm list |
List all profiles |
opm show |
Print the name of the currently active profile |
opm inspect <name> |
Show detailed information about a profile |
opm rename <old> <new> |
Rename a profile |
opm copy <src> <dst> |
Copy a profile to a new name |
opm remove <name> [name...] |
Remove one or more profiles |
opm path <name> |
Print the filesystem path to a profile directory |
opm reset |
Restore ~/.config/opencode to a plain directory |
opm doctor |
Check opm installation health |
Constraints
- Language: Go — single binary, fast, no runtime dependencies
- Mechanism: Directory-level symlink (
~/.config/opencode→ profile dir), not file-level - UX: Flat subcommand surface (not
docker context-style grouping) - Compatibility: Must not break existing OpenCode setup —
opm initmigrates current config non-destructively
Technology Stack
| Layer | Choice |
|---|---|
| CLI framework | github.com/spf13/cobra v1.10.2 |
| Output color | github.com/fatih/color v1.19.0 |
| Test assertions | github.com/stretchr/testify v1.10.0 |
| Release | GoReleaser v2 (just release / just snapshot) |
| Linting | golangci-lint v2.x |
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.
- 3d ago First seen · 142 lines · 1,573 tokens per session scan A 62d94d8c735e
opm AGENTS.md is an instructions file published in the GitHub repository tbcrawford/opm (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,573 tokens to every session, about $0.0079 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
no-mistakes AGENTS.md
AGENTS.md instructions for kunchenguid/no-mistakes, covering agents.md and maintaining this file.
agent-of-empires AGENTS.md
AGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
stackql AGENTS.md
Instructions for stackql/stackql, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
pg-aiguide CLAUDE.md
Claude Code instructions for timescale/pg-aiguide, covering tiger docs mcp server - development guidelines, build, test & run commands, code style guidelines and python (ingest/).
goai AGENTS.md
Instructions for zendev-sh/goai, covering agents.md - goai, commands, architecture, key rules and adding providers.