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/s977043/river-review/docsgit clone --depth 1 https://github.com/s977043/river-reviewWhat 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 | $0.00148 | $0.00148 |
| Opus 5 | $0.00074 | $0.00074 |
| Sonnet 5 | $0.00030 | $0.00030 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade A, and why
river-review docs.instructions.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
Documentation instructions
- Match the repository’s existing documentation structure and conventions.
- Prefer clear headings, short paragraphs, and runnable examples.
- If docs appear to follow the Diátaxis split (tutorial/how-to/reference/explanation), keep the doc in the right category.
- When adding a new doc:
- add links from the appropriate index/README if one exists
- keep multilingual pairing consistent with the repo’s convention (e.g.,
.en.mdwhen used)
- Don’t let docs drift: update them in the same PR as behavior changes.
- Procedural content (setup/release/ops) should live under
docs/runbook/to keep responsibilities clear.
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 · 15 lines · 148 tokens per session scan A 19a6fa20a9f4
river-review docs.instructions.md is an instructions file published in the GitHub repository s977043/river-review (2 stars, last pushed 2d ago), licensed MIT. It adds 148 tokens to every session, about $0.0007 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
agent-ready-repo AGENTS.md
Instructions for eugenelim/agent-ready-repo, covering agents.md, project overview, rule lookups, documentation and development workflow.
logic-lens GEMINI.md
Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (gemini cli), invoking skills, installation, project layout and key conventions.
robin AGENTS.md
Instructions for antongulin/robin, covering instructions for ai coding agents, required workflow reference, do not use, required secrets (in the consumer repo) and minimal consumer workflow.
agentic-hardening-skill AGENTS.md
Instructions for Calvin-LLC/agentic-hardening-skill, covering harden and rules.
claude-code-config CLAUDE.md
Instructions for auerbachb/claude-code-config, covering pr merge authorization, every message — non-negotiable behaviors, thread title — [#issue] prefix, github reference prefix and autonomous workflow execution — do not ask permission.
mainline AGENTS.md
AGENTS.md instructions for mainline-org/mainline: Stop AI coding agents from repeating old engineering mistakes.