Borrowing it
Nothing to install: this file belongs to Innocent-children/dev-flow. 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/Innocent-children/dev-flow/main/AGENTS.mdgit clone --depth 1 https://github.com/Innocent-children/dev-flowWrote 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/innocent-children/dev-flow/agents-md)<a href="https://agentmods.dev/instructions/innocent-children/dev-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/innocent-children/dev-flow/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/innocent-children/dev-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/innocent-children/dev-flow/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 | $0.04538 | $0.04538 |
| Opus 5.5 | $0.01815 | $0.01815 |
| Sonnet 5.5 | $0.00908 | $0.00908 |
| Haiku 4.5 | $0.00454 | $0.00454 |
Grade A, and why
dev-flow 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 1mo 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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Flow Repository Instructions
This file defines how AI agents maintain this repository. Put repository-specific AI instructions,
implementation constraints, and documentation-update rules here. CONTRIBUTING* guides human
contributors; product README files guide users. The shipped Dev Flow Skills govern Host interaction
with the product and remain in the locations listed under Skill Maintenance.
Authority
Before implementation work, read in this order:
- the user's current explicit request and acceptance criteria;
CONTRIBUTING_zh-CN.mdorCONTRIBUTING.md;docs/PRODUCT.mdordocs/PRODUCT_en.md;- the technical documents directly related to the change;
- the current source code, schemas, package manifests, and executable tests for the affected surface.
Before a version-only release, read in this order:
release/README.md;- the selected product's release README under
release/; - the current prepare and publisher contracts under
release/; - the package manifest and current public-version metadata.
When documentation and executable behavior disagree, use the executable implementation to determine current behavior and update the affected documentation in the same change. Do not infer requirements from branch names, directory names, chat history, or historical design documents.
Documentation Responsibilities
Choose a document by its reader and purpose before editing it. A code change does not automatically require a README or PRODUCT change. Keep detailed explanations in their owning reference and link to them from user guides when needed.
| Document | Reader and responsibility |
|---|---|
AGENTS.md |
Repository AI agents: instruction priority, scope, architecture constraints, implementation, review, validation, documentation maintenance, and release boundaries. |
Root README*.md |
End users: what Dev Flow does, suitable tasks, prerequisites, installation, starting and resuming work, common operations, necessary usage limits, and links to further help. |
packages/*/README.md, docs/CODEX_en.md, docs/DEEPSEEK_en.md, docs/CLAUDE*, docs/ZCODE* |
Users of that package or Host: setup, supported operations, troubleshooting, maintenance, removal, and Host-specific limitations. |
docs/PRODUCT* |
Product readers: target users, problems, business functionality, user workflows, product scope, and non-goals. |
docs/DEMO*, docs/WEBUI*, docs/DESKTOP-PETS* |
Users following a walkthrough or operating a specific interface; detailed interface and artwork guidance stays here. |
docs/ARCHITECTURE*, docs/ARTIFACTS*, docs/WORKTREE-SOURCES*, docs/THREAT-MODEL* |
Developers and integrators: component responsibilities, protocols, state and data rules, implementation design, and trust boundaries. |
docs/CORE-RESPONSES* |
Core and Host developers: success/failure envelopes, structured error detail, recovery instructions and response validation. |
docs/COMMANDS* |
Users and integrators needing exact commands, options, selectors, environment variables, and MCP inputs and results. |
docs/SUPPORT-MATRIX*, docs/PROJECT-STATUS*, docs/WINDOWS-ADAPTATION* |
Readers checking supported environments, delivered capability, recorded verification, and remaining limitations. |
docs/ROADMAP* |
Product readers: future outcomes and priorities, clearly distinguished from delivered capability. |
CONTRIBUTING* |
Human contributors: issues, proposals, development setup, validation, and pull requests. |
MANIFEST*, docs/I18N* |
Readers navigating documentation and source locations; translators checking maintained languages, document families, and translation consistency. |
internal/README*, scripts/README*, tests/**/README.md, protocol/fixtures/README.md |
Maintainers of those directories: local structure, development commands, test procedures, and fixture usage. |
release/**/README.md, docs/RELEASE-STRATEGY.md, docs/VERSIONING.md, docs/TOOLCHAIN-BASELINES* |
Maintainers: build environments, version policy, artifact preparation, verification, and publication procedures. |
SECURITY.md |
Users and researchers reporting vulnerabilities and checking the security reporting policy. |
skills/dev-flow/core/ and Host Skill directories |
Agents using the installed product: maintained Core interaction instructions and Host-specific authorization, workspace, and tool operations. |
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.
- 1mo ago Changed · +4 lines · +100 tokens per session 7171a07063be
- 1mo ago Changed · -1 lines · -8 tokens per session c8e246213a64
- 1mo ago Changed · +11 lines · +207 tokens per session 9bddd31a5d7e
- 1mo ago Changed · +27 lines · +1,011 tokens per session 63f41c179ef1
- 1mo ago Changed · +9 lines · +158 tokens per session 38d868567dd8
- 1mo ago Changed · +128 lines · +1,214 tokens per session e90670d2cfd8
- 1mo ago First seen · 190 lines · 1,856 tokens per session scan A b99c72b27a1c
dev-flow AGENTS.md is an instructions file published in the GitHub repository Innocent-children/dev-flow (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 4,538 tokens to every session, about $0.0182 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.