An explicit workflow for implementing a confirmed specification or software change. It checks the target, instructions, tests, and verification steps before editing.

Use it to implement settled changes and produce ordered verification evidence, while leaving route selection, review, commits, deployment, and release decisions to other tools.

It keeps implementation separate from deciding the design, writing proposals, reviewing code, debugging without a known cause, and releasing work.

flow-drive — Skill for Claude Code and Codex by hmj1026/dhpk

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.

Any agent

npx skills add hmj1026/dhpk --skill flow-drive

Clone the repo

git clone --depth 1 https://github.com/hmj1026/dhpk

Made for: Claude Code, Codex.

Or install dhpk, the plugin that ships this one along with the rest of its 39 skills, 1 command, 1 agent, 3 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hmj1026/dhpk/flow-drive/github.svg)](https://agentmods.dev/skills/hmj1026/dhpk/flow-drive)

Your own site

<a href="https://agentmods.dev/skills/hmj1026/dhpk/flow-drive"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/flow-drive/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hmj1026/dhpk/flow-drive"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/flow-drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,247 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.02247
Opus 5.5	$0.00026	$0.00899
Sonnet 5.5	$0.00013	$0.00449
Haiku 4.5	$0.00006	$0.00225

Measured yesterday against content hash 99c210b29042, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flow-drive 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.

The scan reads SKILL.md. This mod also ships 11 executable files (references/_dependencies/scripts/lib/flow-handoff-contract.js, references/execution-bundle/scripts/fast-worker-selector.js, references/execution-bundle/scripts/lib/dispatch-capability-evidence.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

generated/claude-marketplace/package/skills/flow-drive/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flow Drive

Use $flow-drive <task-text|task-file|confirmed-spec-or-change-id> [options] for one bounded implementation task. The Host resolves that single positional input into a goal, acceptance criteria, and structured constraints before dispatch. Pass the input as one positional argument; quote multiword task text or a path containing spaces, for example $flow-drive "Fix checkout flow and verify receipt totals" --worker=codex. Preserve that argument boundary when invoking the parser. When ownership is unclear, return an explicit blocker or use the separately invoked route owner; use the external OpenSpec authoring owner when a proposal or artifact is still missing. Flow Drive consumes the shared neutral handoff contract and does not load a peer skill to validate its input.

When NOT to Use

The route, target, or acceptance contract is unclear: return a blocker with the missing evidence; do not infer a route or load a peer skill. A separately invoked flow-guide route may provide a handoff, but Flow Drive never calls it as a prerequisite.
A proposal or OpenSpec artifact still needs authoring: use external $openspec-propose.
The task is review-only or diagnostic-only: use change-verdict or code-trace.
The requested outcome is a standalone commit, release, deployment, or archive action. Flow Drive implements confirmed changes but does not perform those actions.

Boundary

Flow Drive owns implementation of the confirmed work, including evidence collection and diagnosis when the outcome is settled but a cause is unknown. Only dependent writes wait for sufficient cause, repair, and verification evidence; independent work continues. A manual proposal may be written inside an explicitly assigned scratch scope. External OpenSpec proposal/artifact authoring remains with its separate owner. It does not choose a route, author formal OpenSpec artifacts, review an existing diff, or claim archive, commit, merge, release, deployment, or pilot evidence. Its explicit-only boundary is preserved even when a caller presents a ready-looking route.

Read the full file on GitHub · 174 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday Changed · -1 lines 99c210b29042
2d ago Changed · -104 lines 6981c471294f
8d ago Changed · +119 lines · +8 tokens per session c43a234f9ee4
10d ago Changed · +48 lines f600a000020e
23d ago Changed · -2 lines 0e1c4153388d
1mo ago Changed · +18 lines 521a7fbf5b44
1mo ago Changed · +8 lines d8cfaf12a528
1mo ago First seen · 88 lines · 56 tokens per session scan A 30fc3e16590b

Subscribe to this mod's changes

flow-drive is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 2,247 once invoked, about $0.0003 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 2026-09-05.

Claude Code OpenSpec Planning ai-tooling claude-code-plugin harness

harness

A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.

revfactory/harness · 184 tokens

evolve

A workflow for improving an existing setup that guides coding agents. It collects results and feedback, compares the current setup with its starting version, and records useful changes.

revfactory/harness · 184 tokens

dev-plan

A planning tool that breaks a software project into features arranged in dependency-based waves, or groups of work that can be done in sequence or parallel.

andrewcigan/vibe-dev-plugin · 77 tokens

research

A research workflow that assigns separate agents to study open-source projects, competing products, and current development practices. Git worktrees are separate working copies used to keep those investigations isolated.

andrewcigan/vibe-dev-plugin · 69 tokens

glean

This skill should be used BEFORE any feature design. It runs structured gleaning with the user — asking 5 high-leverage questions per round, up to 3 rounds, to extract Goal / Scope / Constraints / Edges / Done. Output is saved to .mumei/scratch/ .md and used as input for /mumei:compose. Triggers include "I want to add…

iroha924/mumei · 107 tokens

validation-sample

A skill for building a reference test set of 50–100 realistic scenarios for checking an agent or product. It separates user inputs from expected answers to prevent answer leakage and requires at least 90% before shipping.

andrewcigan/vibe-dev-plugin · 85 tokens