devflow: Instructions file for Claude Code

CLAUDE.md

devflow CLAUDE.md is an instructions file for Claude Code from dean0x/devflow. It costs 3,208 tokens per session, scanned A, original, MIT.

A set of development instructions for Devflow, a tool that adds structured workflows to Claude Code, such as planning, implementation, code review, debugging, and issue resolution. It also describes how Devflow's plugins and assets are organized.

In plain words
What is it for?
Use it when modifying Devflow plugins, commands, agents, skills, rules, source assets, or the build process.
Why use it?
It keeps changes aligned with the project's architecture and its requirement for honest reviews, preserved context, and clear commands.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is dean0x/devflow's own configuration. It tells Claude Code how to work on devflow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything devflow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dean0x/devflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dean0x/devflow/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dean0x/devflow

Made for: Claude Code.

Wrote 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.

agentmods badge for devflow CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dean0x/devflow/claude-md/github.svg)](https://agentmods.dev/instructions/dean0x/devflow/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dean0x/devflow/claude-md"><img src="https://agentmods.dev/badge/instructions/dean0x/devflow/claude-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.

agentmods 80×15 button for devflow CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dean0x/devflow/claude-md"><img src="https://agentmods.dev/badge/instructions/dean0x/devflow/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,208 This file is loaded in full into every session.
When invoked 3,208 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03208 $0.03208
Opus 5.5 $0.01283 $0.01283
Sonnet 5.5 $0.00642 $0.00642
Haiku 4.5 $0.00321 $0.00321

Measured today against content hash 6f3ba3a24078, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

devflow CLAUDE.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 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.

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.

CLAUDE.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devflow Development Guide

Instructions for developers and AI agents working on Devflow. For user docs, see README.md.

Purpose

Devflow enhances Claude Code with intelligent development workflows. Modifications must:

  • Maintain brutal honesty in review outputs (no sycophancy)
  • Preserve context across sessions
  • Enhance developer empowerment without replacing judgment
  • Ensure all commands are self-documenting

Architecture Overview

Registry-driven CLI tool with 21 plugins (12 core + 9 optional). Plugins are entries in DEVFLOW_PLUGINS in src/core/plugins.ts — each entry declares its commands, agents, skills, and rules arrays. All assets live once in src/assets/; most install directly, and .mds sources compile via npm run build:mds — command hosts to dist/commands/, agent generator hosts to dist/agents/, and reference modules in src/assets/mds/ to dist/skills/git/references/.

Invariants:

  1. LLM-vs-plumbing: the LLM does all detection, matching and curation. Shell and TypeScript hold no detection or judgment logic.
  2. Read and write curation data only through the curation ops. Never edit those files. Never read the old .devflow/learning/ folder as a ledger. Only move it.
  3. Ledger IDs are machine-local. Committed and posted text states a decision in words, never by ID.
  4. One install per machine, no install scope. DEVFLOW_DIR is ignored. init --scope local exits 1.
  5. devflow never writes project.json or policy.json. The team commits them.
  6. A git-tracked .devflow/config.json counts as absent, with a warning (D-PERSONAL-UNTRACKED).
  7. Repo files only narrow the memory, curation and knowledge switches (D-FEATURES-NARROW-ONLY).
  8. features.behavior is off unless set (D-BEHAVIOR-OPT-IN).
  9. Prompts never read project.json or config.json. They take the resolve-settings.cjs line (_partials/_settings.mds).
  10. Learn conventions.md only when APPLY_CONVENTIONS is true.
  11. Uninstall keeps ~/.devflow/tracker/{provider}.md. It is user content.
  12. The Knowledge agent commits only features/index.md and {slug}/KNOWLEDGE.md (commit --only). Never git add -A, push or force.
  13. ensure-root-gitignore and ensureDevflowGitignore write the same bytes.
  14. KNOWLEDGE gates write-back only. Explore and debug do not load up-front. Freshness: write-through and verify-on-read only.
  15. Rules install only for selected plugins and keep paths: [] frontmatter.
  16. The compliance skill and rule and the behavior rule are feature-owned. No plugin lists them.
  17. Skills install for selected plugins and their requires:. Never install or delete a dormant shadow.
  18. The compliance lens is the union of all layers. A branch never removes a framework; an unreadable file never lowers it (D-LENS-UNION).
  19. The compliance directive goes into a spawn prompt only when the lens is on. No agent body names the compliance skill (D-COMPLIANCE-INJECT).
  20. Enabled compliance, or a repo compliance key (never HEAD), makes required the evidence floor. The lens never decides evidence. With compliance off no posting step is installed; under required each command prints one local TRACEABILITY: DEGRADED line.
  21. Flag --enable/--disable are boolean-only. Narrow with isEnvBooleanFlag. Never display 'unset'.
  22. Disable and uninstall remove only devflow's exact value. Init adopts a user's own value as off (D-ADOPT-RESPECTS-USER).
  23. TRACKER_MODEL and the memory hook fallbacks equal their shipped rows.
  24. Where compliance is on, PR-comment publication is visibility-gated and fails closed to a stub (D10). project.json only caps it. required turns off into stub.
  25. Where compliance is on, the test-plan comment makes no visibility probe: STUB under auto, FULL under full, none under off.
  26. Every posted body passes the scrubber (D11). If it fails, post nothing and emit TRACEABILITY: DEGRADED (redaction unavailable).
  27. File sinks chain the scrubber with &&. Tool-call sinks use --emit and check the byte count [DR-06].
  28. Review-cycle convergence warnings never block.
  29. Evidence policy comes only from the default branch's project.json (D-OFFLINE-ORIGIN-HEAD). Failures resolve required.
  30. Never parse policy.json. Its presence resolves required (D-POLICY-JSON-RETIRED).
  31. Operations see only ISSUE_REQUIRED, APPLY_CONVENTIONS and REQUIRE_NON_AUTHOR_APPROVAL. No prompt restates the mapping.
  32. Only pr-evidence.cjs and verify-evidence.cjs assign test-plan states.
  33. /code-review and /bug-analysis carry no ticket gate.
  34. Every install carries every tracker provider. session-start-context Section 3 always installs and gates at runtime.
  35. requires: lists used, unowned skills. The closure guard has one exception: Review's focus reference.
  36. Tracker settings come from the settings line. config.json only narrows them.
  37. A tracker spawn reads _contract.md once, and _mcp.md once off GitHub. A PR-host spawn reads neither.
  38. Two or more qualifying servers: degraded run, no call.
  39. Release evidence matches the project key, never a bare number.
  40. A refusal reports TRACEABILITY: DEGRADED (<reason>). On Linear, post the back-link with the dedup warning.
  41. tracker --set changes only the machine default.
  42. The Tracker agent claims first, then writes its conventions file once or not at all, scrub-gated.
  43. The manifest keeps the curation switch in curation and learning. Every write sets both. False wins.
  44. When git tracks the curation or memory folder, or does not answer, that feature reads and writes no file there.
  45. The machine switch alone picks the posting variant; a repo key never restores it, and the lens stays the run-time union. One converge, convergeVariantAxes, serves init, curation and compliance. With compliance off it fails closed unless the prompts are proved free of posting.

Read the full file on GitHub · 155 lines

Changes

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.

  1. today Changed · -1 lines · -1 tokens per session 6f3ba3a24078
  2. 6d ago Changed · -1 lines · -21 tokens per session 5fbfdd1bfff0
  3. 8d ago Changed · +1 lines · +8 tokens per session e9a4e581d4d7
  4. 14d ago Changed d8a49d6c0ca2
  5. 15d ago Changed · +23 lines · -2,081 tokens per session 09f0274b2278
  6. 16d ago Changed · +2 lines · +218 tokens per session 16d5b72af5bf
  7. 17d ago Changed · +2 lines · +311 tokens per session bbd3ebb21d1b
  8. 18d ago Changed · +63 tokens per session 5f28a958c3d7
  9. 19d ago Changed · -3 tokens per session bdeb008a775e
  10. 20d ago First seen · 129 lines · 4,714 tokens per session scan A b5142df01cd3

Subscribe to this mod's changes

devflow CLAUDE.md is an instructions file published in the GitHub repository dean0x/devflow (21 stars, last pushed today), licensed MIT. It adds 3,208 tokens to every session, about $0.0128 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 2026-08-30.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens