Borrowing it
Nothing to install: this file belongs to vladm3105/aidoc-flow-framework. 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/vladm3105/aidoc-flow-framework/dev/AGENTS.mdgit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/agents-md)<a href="https://agentmods.dev/instructions/vladm3105/aidoc-flow-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/vladm3105/aidoc-flow-framework/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/vladm3105/aidoc-flow-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/vladm3105/aidoc-flow-framework/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 | $0.05602 | $0.05602 |
| Opus 5.5 | $0.02241 | $0.02241 |
| Sonnet 5.5 | $0.01120 | $0.01120 |
| Haiku 4.5 | $0.00560 | $0.00560 |
Grade A, and why
aidoc-flow-framework 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working agreement for AI coding agents on aidoc-flow-framework
Orients any AI agent (Claude Code, Codex, Gemini CLI, Copilot, Hermes, custom)
working on this repo. This file is the single working agreement — the short
orientation plus the rules that are most often missed. There is no second
agreement: the former CLAUDE.md was retired and its live rules folded in
below (conflicting clauses resolved in this file's favour); git history
preserves the old file.
What this repo is
One engine-agnostic specification (framework/) defining the 10-layer SDD
flow (BRD → PRD → EARS → BDD → ADR → SPEC → TDD → IPLAN → [Code] → CHG → EVAL).
Platforms (Hermes MCP server, Claude Code plugin) were archived — any capable AI
agent derives its behavior from the framework spec, templates, and playbooks
directly. The repo ships sdd_doc_lint/ (structural linter) and hooks/
(advisory hooks — PostToolUse + PreCommit, see hooks/README.md) as the only retained tooling.
The pristine pre-migration project is preserved on the protected, read-only
legacy-ucx-v3.2-read-only branch.
Filing gaps — open a GitHub issue
When you find a defect, inconsistency, or missing capability, open a GitHub issue on this repo. That is the whole rule — there is one surface.
Capture at discovery still applies, unchanged: open the issue when you find it, not in a "later PR". What moved is the surface, not the timing.
The issue body carries: reproduction at file:line, blast radius run rather
than assumed, why it was hard to diagnose, a suggested fix, and what is not
broken. One issue per defect. Move the analysis verbatim — never summarise a
finding into an issue, because a re-derived finding silently contracts.
Search before filing (gh issue list --search … --state all); comment on an
open match instead of duplicating it; a closed match gets a new issue
cross-linked as a regression, never a reopen. The merge closes the issue — the PR
body carries Closes #N, one keyword per reference (Closes #A and #B closes
only #A). On merge, post a closing comment on each resolved issue — what
shipped plus verification evidence (green checks, merge SHA on the target) —
never leave a resolved issue closed without its record.
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 Changed · +17 lines · +418 tokens per session 1b5cef73dc91
- 11d ago Changed · +1 lines · +29 tokens per session 53d7f325aa52
- 15d ago Changed · +24 tokens per session eaef2f231a7c
- 20d ago Changed · +3 lines · +94 tokens per session e2831a8b0fad
- 21d ago Changed · +12 tokens per session 62ad07d55d2d
- 22d ago Changed · +76 tokens per session 59fe8e292132
- 25d ago Changed · +14 lines · +666 tokens per session 800362fa4f31
- 28d ago Changed · +63 lines · +934 tokens per session 344727fb460f
- 29d ago Changed · +1 lines · +93 tokens per session faa73c8d1fe6
- 1mo ago First seen · 200 lines · 3,256 tokens per session scan A 9db18cbeedbc
aidoc-flow-framework AGENTS.md is an instructions file published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 5,602 tokens to every session, about $0.0224 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 2026-08-31.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.