dev-workflow-kit AGENTS.md

Repository instructions for `dev-workflow-kit`, a Claude Code marketplace plugin that provides a specification-led workflow for building software with coding agents. Its deliverables are prompts, skills, commands, agent definitions, reminders, templates, and one shell hook rather than application code.

In plain words
What is it for?
Use it when changing, reviewing, or extending the plugin’s workflow files, templates, documentation, or shell hook.
Why use it?
It gives coding agents the project’s architecture, invariants, review gates, hardening ledger, and required quality checks in one reference. This is important because ordinary application type-checking is not available for a prompt-focused project.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/dsnger/dev-workflow-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/dsnger/dev-workflow-kit

Made for: Codex, OpenCode.

Per session 4,944 This file is loaded in full into every session.
When invoked 4,944 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.04944 $0.04944
Opus 5 $0.02472 $0.02472
Sonnet 5 $0.00989 $0.00989
Haiku 4.5 $0.00494 $0.00494

Measured yesterday against content hash 66eb45030c51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 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 architecture and invariants. 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 escalates one rung harder (prose → lint → type → 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

The tree below is the meaningful surface — the files a change is likely to touch or break. Ordinary repo furniture (.gitignore, .claude/settings.json, generated state under .mcp/) is deliberately absent, not overlooked.

README.md                         # what the kit is, setup, daily use, contributing
MANIFEST.md                       # inventory of source-files/, the frozen extraction seed
AGENTS.md                         # this file — the invariants both gates check
CLAUDE.md                         # discipline rules + the two review gates
todos.md                          # backlog; `pending` ledger rows point here by ref
.gitattributes                    # union merge for the append-only ledger
.mcp.json                         # the Codex reviewer, pinned
.claude-plugin/marketplace.json
.github/workflows/ci.yml          # lint + hook tests + invariant checks + validate
scripts/check-invariants.sh       # invariants 5, 6 + prompt conformance (rung 2)
scripts/check-invariants.test.sh  # its regression suite — reject/accept pairs
scripts/check-version-bump.sh     # invariant 12, mechanically — PR-only (rung 2)
scripts/check-version-bump.test.sh # its regression suite — policy/operational/accept
plugins/dev-workflow/
  .claude-plugin/plugin.json      # metadata only — no component keys (invariant 6)
  CHANGELOG.md                    # every manifest version, newest first
  skills/{intake,harden-finding}/SKILL.md
  agents/finding-triage.md        # read-only PR-comment checker (convention-loaded)
  commands/{workflow-init,process-pr-review}.md
  hooks/{hooks.json,codex-gate.sh,codex-gate.test.sh}
  hooks/fixtures/                 # captured PostToolUse payloads the suite replays
  examples/                       # ships, but never scaffolded — one stack's answers
docs/
  architecture.md                 # layout + the two non-obvious design decisions
  coding-workflow.md              # the methodology this plugin encodes
  getting-started.md              # first story, end to end
  prompt-standards.md             # the 12-item checklist every prompt must pass
  hardening-log.md                # append-only findings ledger (union-merged)
  hardening-taxonomy.md           # this project's fingerprint classes
  pr-review-bots.md               # the Wait-for routing list + where each bot's findings appear
  superpowers/{specs,plans,stories}/ # the approved artifacts behind past changes
source-files/                     # the extraction seed this repo was built from

Read the full file on GitHub · 284 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. yesterday First seen · 284 lines · 4,944 tokens per session scan A 66eb45030c51

Subscribe to this mod's changes

dev-workflow-kit AGENTS.md is an instructions file published in the GitHub repository dsnger/dev-workflow-kit (5 stars, last pushed 6d ago), licensed MIT. It adds 4,944 tokens to every session, about $0.0247 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.