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/nainish-rai/agent-rollback/agents-mdgit clone --depth 1 https://github.com/Nainish-Rai/agent-rollbackWrote 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/nainish-rai/agent-rollback/agents-md)<a href="https://agentmods.dev/instructions/nainish-rai/agent-rollback/agents-md"><img src="https://agentmods.dev/badge/instructions/nainish-rai/agent-rollback/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 | $0.00219 | $0.00219 |
| Opus 5 | $0.00110 | $0.00110 |
| Sonnet 5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
agent-rollback 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 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.
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
Agent Instructions
Project Shape
bin/agent-rollback.jsis the executable entry point.src/cli.jsowns command parsing and user-facing output.src/snapshot.jsowns checkpoint creation, diffing, listing, and restore.src/workspace.jsowns workspace file discovery and path safety.src/runner.jsowns thecodex execwrapper behavior.test/*.test.jsuses Node's built-in test runner.
Commands
Run before committing:
npm test
npm run check
Engineering Rules
- Keep runtime dependencies at zero unless a dependency clearly removes more risk than it adds.
- Prefer small, focused functions with clear names.
- Do not add undocumented Codex hook assumptions without linking to official OpenAI docs or a stable upstream source.
- Storage changes need integration tests that create, mutate, diff, and restore a temporary workspace.
- Preserve content-addressed object storage unless replacing it with a simpler tested design.
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 · 32 lines · 219 tokens per session scan A 9b1c5389beed
agent-rollback AGENTS.md is an instructions file published in the GitHub repository Nainish-Rai/agent-rollback (5 stars, last pushed yesterday), licensed MIT. It adds 219 tokens to every session, about $0.0011 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
codex-rewind AGENTS.md
AGENTS.md instructions for extracurricular-ai/codex-rewind, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
apm python.instructions.md
Python development guidelines.
CodexPotter AGENTS.md
AGENTS.md instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
3notch AGENTS.md
Instructions for coldlogicAI/3notch, covering 3notch agent guide, purpose, read first, long-run goal and shipped surface (build this, nothing else).