Borrowing it
Nothing to install: this file belongs to CoderBhoid/ai-format. 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/CoderBhoid/ai-format/main/AGENTS.mdgit clone --depth 1 https://github.com/CoderBhoid/ai-formatWrote 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/coderbhoid/ai-format/agents-md)<a href="https://agentmods.dev/instructions/coderbhoid/ai-format/agents-md"><img src="https://agentmods.dev/badge/instructions/coderbhoid/ai-format/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/coderbhoid/ai-format/agents-md"><img src="https://agentmods.dev/badge/instructions/coderbhoid/ai-format/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 | $0.00602 | $0.00602 |
| Opus 5.5 | $0.00241 | $0.00241 |
| Sonnet 5.5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
ai-format 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIF V4 Cognitive Memory & Synaptic Bridge
Mandatory Cognitive Persistence Invariant
This invariant governs cognitive memory lifecycle across ALL execution harnesses, workflows, and subagent delegates (including poteto-mode, agystack, autonomous swarms, and coordinator sessions).
Subagent delegation (such as poteto-agent or research) does NOT waive this invariant. The coordinator MUST execute the boot recall and scratch checkpoints before spawning subagents, and MUST commit turn notes upon receiving subagent results.
1. Chat Boot Recall (Mandatory on First Turn)
Before invoking subagents, reading playbooks, or modifying files:
Check for the aif executable or ./ai.sh script, and run:
aif recall --core-and-bridge
- Instantly loads active project Red Core (
INT16_CORE) blocks, including any[PAUSED_MID_TASK]checkpoint from interrupted prior sessions. - Injects relevant cross-project pointers from the Cross-Project Bridge Nexus (
bridge_nexus.ai) into working context.
2. Pre-Task Volatile Scratch (Interrupt Protection)
Before initiating multi-file edits, long test runs, refactors, or delegating code writes to a subagent:
aif scratch "<current goal, subagent task spec, and active working state>"
- Arms the OS-level signal trap. If execution is interrupted (
Ctrl+C,SIGINT,SIGTERM), the engine automatically flushes this scratch buffer into the active project'sINT16_COREwith importance0.95and the[PAUSED_MID_TASK]marker.
3. Subagent Memory Synchronization
When coordinating delegate subagents (e.g., poteto-agent):
- Pass relevant
INT16_COREarchitectural constraints and schemas directly in the subagent prompt. - When the subagent yields control or returns diffs, record the completed milestone and architectural changes into AIF immediately.
4. End-of-Turn Cognitive Commit (Every Productive Turn)
Before concluding any productive turn, evaluate the cognitive importance of the turn (0.0 to 1.0) and commit a note:
aif note --importance <0.0-1.0> --summary "<concise summary of decisions and code modifications>"
- 0.70 - 1.00 (Red Core /
INT16_CORE): Critical architecture, API schemas, breaking changes, or interrupted tasks. Automatically indexed intobridge_nexus.ai. - 0.30 - 0.69 (Black Middle Ring /
INT8_RING): Implementation notes, bug fixes, routine turn summaries. Pruned for token efficiency. - 0.00 - 0.29 (Blue Outer Crust /
INT2_CRUST): Transient observations, fleeting logs, deep summaries.
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.
- 10d ago First seen · 38 lines · 602 tokens per session scan A 39ae6e31c203
ai-format AGENTS.md is an instructions file published in the GitHub repository CoderBhoid/ai-format (12 stars, last pushed 2d ago), licensed MIT. It adds 602 tokens to every session, about $0.0024 per session on Opus 5.5. 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 2026-10-18.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.