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/brn-mwai/scribe/agents-mdgit clone --depth 1 https://github.com/brn-mwai/scribeWrote 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/brn-mwai/scribe/agents-md)<a href="https://agentmods.dev/instructions/brn-mwai/scribe/agents-md"><img src="https://agentmods.dev/badge/instructions/brn-mwai/scribe/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 | $0.01497 | $0.01497 |
| Opus 5 | $0.00749 | $0.00749 |
| Sonnet 5 | $0.00299 | $0.00299 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
scribe 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 3d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Scribe
This file is the context layer for AI agents working on this repository. It is also a live example of what Scribe produces: the blocks between
<!-- scribe:begin ... -->and<!-- scribe:end ... -->are machine-maintained; everything outside them is human-owned and never touched by Scribe.
For AI coding agents — start here
You can set up and build this project autonomously. Before writing any code, engage the coding-standards skill and apply Standards and process below.
- Read
docs/scribe-system-design.md(the authoritative spec) anddocs/IMPLEMENTATION.md(the ordered build plan). - Run the Autonomous setup steps in
INSTALL.md. Stop and report if any verification check fails. - Implement
docs/IMPLEMENTATION.mdtasks in order (T0 → T10). After each task, run its acceptance check and the test suite. Do not start the next task until the current one is green. - Keep the pure core (extractor, synthesizer, renderer, fingerprinter, drift gate) free of I/O so it stays unit-testable. All Orbit and GitLab access lives behind adapters.
- Never edit content outside Scribe markers in any
AGENTS.md(including this one's human blocks). Determinism is a hard requirement: same input ⇒ byte-identical output.
Standards and process (mandatory)
Built under the team coding standards loaded in Claude Code. Apply them on every task — do not hand-roll a different process.
- Process: follow the 7-phase coding system — reason → requirements → design → implement → test → review → deploy → monitor. The Phase 0 reasoning gate precedes any code.
- Design framework:
docs/scribe-system-design.mdfollows the 7-step framework (clarify → estimate → architect → detail → design → scale → verify). Scribe is a batch CLI/flow, not a high-QPS service, so estimate and scale are intentionally light — runs per repo, on a schedule, no QPS surface. Verify maps every NFR back to a design decision. - Quality metrics (hard gates):
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.
- 3d ago First seen · 126 lines · 1,497 tokens per session scan A ccf003bb8167
scribe AGENTS.md is an instructions file published in the GitHub repository brn-mwai/scribe (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,497 tokens to every session, about $0.0075 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
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).