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/sandover/ergo/agents-mdgit clone --depth 1 https://github.com/sandover/ergoWhat 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 | $0.00192 | $0.00192 |
| Opus 5 | $0.00096 | $0.00096 |
| Sonnet 5 | $0.00038 | $0.00038 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
ergo 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
This repository adds Ergo-specific instructions to the shared global policy in
~/.config/AGENTS.md.
Project goals
- Ergo manages a dependency-aware backlog. User-facing language says backlog,
task, dependency, and epic.
containeris only an internal implementation term. - The agent manual has two authoritative layers:
help.txtis the root front door: mental model, first workflow, command inventory, global flags, and navigation.quickstart.txtowns the complete cross-command model and operating guide.
- Generated command help provides syntax and options only; it is not a third manual.
- The two manual layers are complete together. Keep each succinct, accurate, humane, and nonredundant while preserving full tool-surface coverage.
- README, the shipped skill, specification, errors, and release guidance consume this contract; they do not become competing manuals.
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 · 18 lines · 192 tokens per session scan A 4ec7ea86f4d6
ergo AGENTS.md is an instructions file published in the GitHub repository sandover/ergo (40 stars, last pushed 8d ago), licensed MIT. It adds 192 tokens to every session, about $0.0010 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
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
agentx AGENTS.md
Instructions for sageox/agentx, covering agent instructions, quick reference, releases, code quality and landing the plane (session completion).
corral AGENTS.md
Instructions for x0c/corral, covering corral, 文档导航, 组件一览, 领域地图（doc-init） and 待补充知识库（doc-init backlog）.
soloe AGENTS.md
AGENTS.md instructions for mheraskin/soloe, covering repository instructions, commit messages, code discovery, agent skills and issue tracker.
review-switch AGENTS.md
AGENTS.md instructions for okqixiaobao727-design/review-switch, covering review-switch, agent skills, issue tracker, triage labels and domain docs.
gskill CLAUDE.md
Instructions for itsmostafa/gskill, covering claude.md, project overview, project management, entry point & cli and project structure.