Borrowing it
Nothing to install: this file belongs to dsnger/dev-workflow-kit. 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/dsnger/dev-workflow-kit/main/AGENTS.mdgit clone --depth 1 https://github.com/dsnger/dev-workflow-kitWrote 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/dsnger/dev-workflow-kit/agents-md)<a href="https://agentmods.dev/instructions/dsnger/dev-workflow-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/dsnger/dev-workflow-kit/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/dsnger/dev-workflow-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/dsnger/dev-workflow-kit/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 | $0.05985 | $0.05985 |
| Opus 5.5 | $0.02394 | $0.02394 |
| Sonnet 5.5 | $0.01197 | $0.01197 |
| Haiku 4.5 | $0.00598 | $0.00598 |
Grade A, and why
dev-workflow-kit 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 yesterday.
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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — dev-workflow-kit
Single source of truth for invariants and conventions; the architecture lives in
docs/ARCHITECTURE.md. Read directly by Codex at both
review gates and by the PR review bots. Discipline rules live in @CLAUDE.md.
What this project is
A Claude Code marketplace shipping one plugin, dev-workflow, which installs a
spec-driven workflow for building software with coding agents. It adds three
mechanisms: two independent cross-model review gates (a different model reviews the
design at Gate A and the diff at Gate B), a fingerprinted hardening ledger where a
recurring finding is hardened with lint or a test, and one
repo-enforced quality command. Users are developers running Claude Code.
The product is prompts. Skills, slash commands, agent definitions, hook reminder
messages and every template /workflow-init scaffolds are the deliverable — plus one
POSIX-shell hook.
There is no application code, so there is no typechecker to catch a defect; review and
docs/prompt-standards.md are the only gates a prompt passes through.
Architecture
docs/ARCHITECTURE.md holds the repository tree, the components, the scripts' inventory and the
two design decisions. docs/PRD.md holds the product's problem, success measures, non-goals and
feature map. docs/TECH-STACK.md holds the tools the repo runs on and where each version is
pinned.
Boundaries (binding)
skills/,commands/,agents/andhooks/hooks.jsonare loaded by convention from their paths.scripts/ledger-metrics.{py,test.sh},scripts/loop-usefulness.{py,test.sh},scripts/spec-delta.{py,test.sh}andscripts/live-effort.{py,test.sh}(read-only)scripts/run-analytics.{py,test.sh}(writes only its own store under.context/telemetry/)scripts/status-view.{py,test.sh}(writes only its page, cache and lock under.context/status/)- the hook ships in the plugin, the checkers and the reports do not
- The plugin depends on superpowers (skills it hands off to) and on a Codex MCP server
exposing both
execandreview(the gates key on those two tool names). Initialized projects that have third-party dependencies also depend on the Context7 MCP server, which/workflow-initwrites pinned into their.mcp.json; the library-API rule in the gate rules needs it, and falls back to the library's own docs when it is unavailable. - Nothing may depend on this repo's internal layout — an installed plugin lives under a version-keyed cache path, which is an implementation detail.
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.
- yesterday Changed · +9 lines · +276 tokens per session d2dee6b6a405
- 4d ago Changed · -7 tokens per session cf3558cebef7
- 5d ago Changed · -47 lines · -823 tokens per session 67cef575c53e
- 6d ago Changed · +2 lines · +34 tokens per session 3037443d16fb
- 8d ago Changed · +6 lines · +121 tokens per session ec9d10eeaa21
- 9d ago Changed · +24 lines · +419 tokens per session d65cf63ba244
- 10d ago Changed · +5 lines · +157 tokens per session 80a41d9784d1
- 12d ago Changed · +8 lines · +193 tokens per session 6c32d8a12f77
- 13d ago Changed · +5 lines · +228 tokens per session f9218631fc6b
- 14d ago First seen · 299 lines · 5,387 tokens per session scan A d4bc26916421
dev-workflow-kit AGENTS.md is an instructions file published in the GitHub repository dsnger/dev-workflow-kit (6 stars, last pushed today), licensed MIT. It adds 5,985 tokens to every session, about $0.0239 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.
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.
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).