Borrowing it
Nothing to install: this file belongs to phantomyard/phantombot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/phantomyard/phantombot/main/AGENTS.mdgit clone --depth 1 https://github.com/phantomyard/phantombotWrote 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/phantomyard/phantombot/agents-md)<a href="https://agentmods.dev/instructions/phantomyard/phantombot/agents-md"><img src="https://agentmods.dev/badge/instructions/phantomyard/phantombot/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/phantomyard/phantombot/agents-md"><img src="https://agentmods.dev/badge/instructions/phantomyard/phantombot/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.07367 | $0.07367 |
| Opus 5.5 | $0.02947 | $0.02947 |
| Sonnet 5.5 | $0.01473 | $0.01473 |
| Haiku 4.5 | $0.00737 | $0.00737 |
Grade B, and why
phantombot AGENTS.md scanned grade B with 1 finding 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- [3](docs/contributing/invariants/release-and-install.md#inv-3) `sudo cp` to install someone's binary How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — guide for any agent contributing to phantombot
This file is for any agent (human or LLM) working on the phantombot codebase itself. If you're a Claude Code session, an OpenAI-Codex agent, a future maintainer, or just yourself catching up after time away — read this before opening a PR. It captures the small set of project-specific conventions that aren't obvious from the code.
Naming-collision warning. This
/AGENTS.md(project root) is not the same aspersonas/<name>/AGENTS.md(a persona-specific tool-hint file phantombot reads when loading that persona). They share a name because OpenClaw uses the same convention for persona files; phantombot's persona loader accepts bothtools.mdandAGENTS.mdas the persona-tools slot. If a contributor refers to "AGENTS.md" without context, they almost always mean this file (the repo-level one). If you're editing a file underpersonas/oragents/, you're touching a persona, not the contributor guide.
HARD RULE — review findings are fixed in the PR, never filed for later
Binding on every agent (Kai, Lena, Omar, Robbie, Atlas, Max, Jake, any other) on every PR. Only the human principal can grant an exception, in writing, on the PR. This rule beats any older habit, template or procedure that says otherwise.
- Every review finding gets exactly one of two outcomes. It's either blocking, so it gets fixed in this PR before approval, or it's dropped, because it isn't worth fixing. Say that in one line or don't mention it. There is no third outcome. "Non-blocking, follow-up", "filed as #NNN", "parked for a later PR" and "tracked separately" are all forbidden.
- Agents never open an issue without the principal's explicit OK. This covers reviews, PR descriptions, ticks, pollers and triage. If you find a real bug in existing code outside the PR's scope, ask the principal in chat first, and only open the issue if they say yes.
- Follow-up PRs can't spawn more follow-ups. Their findings get fixed in them or dropped.
- Nits are never blockers and never issues. That covers style, naming, wording, comment polish and "could be cleaner". Drop them.
- Don't widen scope during review. A PR fixes what it says it fixes. A finding that would need a separate change is either blocking, so it gets fixed here, or dropped.
- Only approve when nothing is left open. An approval that lists leftovers is not an approval.
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.
- today Changed · +3 lines · +79 tokens per session 46101690cd90
- 2d ago Changed · +14 lines · +432 tokens per session fee873d37cc0
- 7d ago Changed · +4 lines · +217 tokens per session 0260f26f67e3
- 9d ago Changed · +2 lines · +124 tokens per session db26ce665f3a
- 10d ago Changed · +5 lines · +136 tokens per session d8ca6792c985
- 16d ago Changed · +1 lines · +50 tokens per session bdec0a3519c3
- 19d ago First seen · 219 lines · 6,329 tokens per session scan B 35b5b61cba19
phantombot AGENTS.md is an instructions file published in the GitHub repository phantomyard/phantombot (18 stars, last pushed yesterday), licensed MIT. It adds 7,367 tokens to every session, about $0.0295 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
phantombot AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| phantombot AGENTS.mdphantomyard/phantombot | Instructions file | 18 | yesterday | MIT | B | 7,367 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |