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/mheraskin/soloe/agents-mdgit clone --depth 1 https://github.com/mheraskin/soloeWhat 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 | $0.00344 | $0.00344 |
| Opus 5 | $0.00172 | $0.00172 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
soloe 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 2d 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.
What it actually says
Repository instructions
Commit messages
All commits use Conventional Commits:
<type>[optional scope][!]: <description>
Use one of feat, fix, docs, style, refactor, perf, test, build, ci,
chore, or revert. Keep the header at 100 characters or fewer, use a concise
lowercase description without a trailing period, and split unrelated concerns.
When staging files to commit immediately, stage and commit in one command.
Code discovery
Prefer codebase-memory-mcp graph tools for code discovery. Use text search for configuration, documentation, string literals, or when the graph is insufficient.
Agent skills
Issue tracker
Issues and PRDs are tracked in this repository's GitHub Issues. Infer the repository from the
current Git remote. Read issues with their comments and labels. Publishing an issue or PRD means
creating a GitHub issue. See docs/agents/issue-tracker.md.
Triage labels
Use the canonical five-role label vocabulary:
needs-triage: maintainer evaluation is requiredneeds-info: more information is required from the reporterready-for-agent: fully specified and ready for an agentready-for-human: human implementation is requiredwontfix: the issue will not be actioned
See docs/agents/triage-labels.md.
Domain docs
This repository uses the single root CONTEXT.md domain glossary. Read it before changing
behavior and use its vocabulary in tests, code, and public writing. See docs/agents/domain.md.
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.
- 2d ago First seen · 44 lines · 344 tokens per session scan A f3608ffcad64
soloe AGENTS.md is an instructions file published in the GitHub repository mheraskin/soloe (1 stars, last pushed 4d ago), licensed MIT. It adds 344 tokens to every session, about $0.0017 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 2026-08-31.
Other instructions, from other repositories
CLITrigger CLAUDE.md
Instructions for HyperAITeam/CLITrigger, covering claude.md, project overview, commands, development (runs server + client concurrently) and build.
SubFrame AGENTS.md
Instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.
SubFrame CLAUDE.md
Instructions for Codename-11/SubFrame, covering subframe, core rule, architecture, tech stack and key modules.
braid AGENTS.md
Instructions for openbraid/braid, covering agents.md, what braid is, repository layout, the two modes — read this before touching storage and migration code that looks like a botched rename.
ensemblr AGENTS.md
Instructions for ensemblr-hq/ensemblr, covering agent instructions, project naming, app scaffolding requires current official docs, package manager policy and biome policy.
braid CLAUDE.md
Instructions for openbraid/braid, a project described as: Mission control for your agent swarm — know which agent is working, which is stuck, and which is done. Works with 14 coding agents, runs entirely on your machine.