What is feature-to-work-packets?

A way to split an approved feature specification into ordered implementation tasks, each assigned to specific files, dependencies, risks, evidence, and checks.

Use it before work spanning multiple files, subsystems, or agents when the feature requirements and dependency order are already settled.

It prevents different developers or coding agents from editing the same files without coordination and shows what must be done first.

feature-to-work-packets — Skill for Codex by hoatv2211

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 hoatv2211/GameStudio-CodexKIT --skill feature-to-work-packets

Clone the repo

git clone --depth 1 https://github.com/hoatv2211/GameStudio-CodexKIT

Made for: Codex.

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/hoatv2211/gamestudio-codexkit/feature-to-work-packets.svg)](https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/feature-to-work-packets)

Your own site

<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/feature-to-work-packets"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/feature-to-work-packets.svg" alt="Measured on agentmods" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 944 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	$0.00040	$0.00944
Opus 5	$0.00020	$0.00472
Sonnet 5	$0.00008	$0.00189
Haiku 4.5	$0.00004	$0.00094

Measured yesterday against content hash 69b10ad57ebf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

feature-to-work-packets 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.

skills/feature-to-work-packets/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature to Work Packets

Overview

Turn a testable feature spec into implementation units that can be owned, sequenced, reviewed, and verified without overlapping writes.

When to use

Use before multi-file, multi-subsystem, or multi-agent implementation when the specification is approved and dependency order matters.

When NOT to use

Do not use when the feature direction or specification remains unresolved, or when the task is a single-file micro-change.

Required inputs and context discovery

Require approved spec, repository map, generated/source relationships, subsystem owners, applicable instructions, dependency graph, risky files, verification commands, and unavailable tools.

Safety and risk level

Packet authoring is low-risk. Packets cannot grant destructive actions or overlapping write ownership, and they must preserve external and generated no-touch rules.

Workflow

Map specification requirements to concrete subsystems and source-of-truth files. Completion criterion: generated outputs and external dependencies are distinguished from editable sources.
Build the dependency graph and identify immediate blockers versus parallel sidecars. Completion criterion: ordering is based on real interfaces, not team preference.
Create packets with one objective, workflow_id, owner, repository phase, exact owned files, excluded files, inputs, outputs, authority handoff, and risks. For a progress-enabled KIT Goal, also require positive integer progress_weight, required evidence kinds, optional or null estimate_seconds: {low, high}, and timing policy max_active_timed_packets: 1. Completion criterion: no two concurrent packets own the same path or generated target, cross-project phases have one integration owner, and every opted-in progress packet has complete fields without inferred equal weights.
Attach focused and broader verification commands plus expected artifacts. Completion criterion: each packet has an objective completion check.
Define integration and review packets owned by the orchestrator or reviewer. Completion criterion: shared registries and final verdict have a single owner.

Read the full file on GitHub · 80 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 259 B

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 69b10ad57ebf
8d ago First seen · 79 lines · 40 tokens per session scan A 7d00c2a1120d

Subscribe to this mod's changes

feature-to-work-packets is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 944 once invoked, about $0.0002 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.

Planning agent-skills agentic-ai agentic-workflow codex-cli codex-plugin codex-skill

deep-discovery

Use when the user asks for deep discovery, 100-question brainstorming, idea interrogation, architecture stress testing, strategy vetting, weakness finding, hole-poking, exhaustive exploration, planning or auditing Codex plugins or skills, or pre-commitment review of a design, plan, strategy, architecture, product…

forsonny/deep-discovery · 76 tokens

feature-to-work-packets