agent-files

agent-files is a skill for Claude Code, Codex from zhouyou-gu/skill-marketplace-template. It costs 68 tokens per session (1,550 once invoked), scanned A, original, MIT.

A starter set of four AGENT files that gives a coding workspace separate places for rules, its long-term mission, reusable instructions, and current progress.

In plain words
What is it for?
Use it to create the four-file contract in a new workspace, including a mission and optionally a current objective.
Why use it?
It prevents important guidance, goals, and status from being mixed together or lost when work is handed from one coding agent to another.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create the four-file contract in a new workspace, including a mission and optionally a current objective.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zhouyou-gu/skill-marketplace-template/agent-files
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 zhouyou-gu/skill-marketplace-template --skill agent-files
Clone the repo
git clone --depth 1 https://github.com/zhouyou-gu/skill-marketplace-template

Made for: Claude Code, 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.

agentmods badge for agent-files

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhouyou-gu/skill-marketplace-template/agent-files/github.svg)](https://agentmods.dev/skills/zhouyou-gu/skill-marketplace-template/agent-files)
Your own site
<a href="https://agentmods.dev/skills/zhouyou-gu/skill-marketplace-template/agent-files"><img src="https://agentmods.dev/badge/skills/zhouyou-gu/skill-marketplace-template/agent-files/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 agent-files

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhouyou-gu/skill-marketplace-template/agent-files"><img src="https://agentmods.dev/badge/skills/zhouyou-gu/skill-marketplace-template/agent-files.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,550 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.01550
Opus 5 $0.00034 $0.00775
Sonnet 5 $0.00014 $0.00310
Haiku 4.5 $0.00007 $0.00155

Measured 11d ago against content hash d548d40ec6e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-files 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 11d ago.

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/agent-files/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Files Scaffold

Trigger

  • Use when a workspace needs the four-file AGENT contract (AGENT.md, AGENT_GOAL.md, AGENT_HARNESS.md, AGENT_PROGRESS.md) scaffolded from scratch with strict, non-overlapping functional boundaries.
  • Use when preparing a workspace to survive handoff between agents, where the caller wants a disciplined, recoverable contract on first read.
  • Do not use to curate or revise an existing AGENT_GOAL.md; goal curation is outside this scaffold's write surface.
  • Do not use when the caller explicitly asks for a domain-specific AGENT-file scaffolder or sidecar-aware workflow; this generic scaffold owns only the base four-file contract.
  • Do not use when only a task checklist is needed and no durable four-file contract is wanted.

Inputs

  • target_dir: directory where the four AGENT files will be scaffolded
  • mission: one- or two-sentence long-term mission statement written into AGENT_GOAL.md; required so the scaffolded contract is internally consistent on first read. It must not include reusable workflow rules, formatting preferences, current task state, next steps, or transient objectives.
  • objective: optional concrete in-flight objective written into AGENT_PROGRESS.md; it must be transient current work, not a second mission statement or permanent scope rule. When omitted, the ## Current Objective section is removed rather than left as a literal placeholder.
  • overwrite: when true, existing files in target_dir are replaced as an explicit control-contract overwrite; otherwise only compatible existing files are recorded in files_skipped

Workflow

  1. Receive target_dir and mission. Confirm the directory exists or create it. mission is required so the scaffolded contract is internally consistent the moment a later agent reads it; AGENT.md and AGENT_GOAL.md are agent-immutable after scaffold and cannot be filled in autonomously later.
  2. Classify the supplied mission and optional objective before writing:
    • mission-level purpose belongs in mission
    • transient current work belongs in objective
    • reusable workflow rules and preferences belong in future AGENT_HARNESS.md updates, not in mission
    • current repository state, blockers, and next steps belong in future AGENT_PROGRESS.md updates, not in mission
  3. Before partial adoption, inspect any existing AGENT.md, AGENT_GOAL.md, AGENT_HARNESS.md, or AGENT_PROGRESS.md in target_dir. If any of these files already exist and overwrite is false, proceed only when every existing file passes the hardened compatibility checklist below; otherwise stop and ask whether to use overwrite=true or choose a clean target directory. Do not mix boundary-aware files with incompatible older files.
    • AGENT.md must start with # Agent Control and contain the phrases agent-immutable control contract, control-contract replacement, migration, or scaffold overwrite, and Child skills and sidecars shall not patch this file; the higher-precedence caveat including venue; ## Boundary Audit Checklist; a precedence section; an update-routing or update-dispatcher section; and the dispatcher-maintenance terminal condition.
    • AGENT_GOAL.md must start with # Mission, contain the phrase agent-immutable, and preserve neutral scaffold entries such as Not yet specified by user rather than instructional placeholders.
    • AGENT_HARNESS.md must start with # Workspace Harness, contain the phrase reusable playbook, use ## Stable Operating Context, include ## Reusable Preferences, and preserve the neutral reusable-preference placeholder or real durable rules.
    • AGENT_PROGRESS.md must start with # Progress, contain the phrase live-state record, include the neutral completed-changes entry No completed changes recorded yet. or real factual progress, and contain no literal {{ objective }} placeholder.
  4. For each of AGENT.md, AGENT_GOAL.md, AGENT_HARNESS.md, AGENT_PROGRESS.md:
    • If the file already exists and overwrite is false, skip it and record the path in files_skipped.
    • Otherwise copy the corresponding template from examples/ into target_dir. Substitute mission for the {{ mission }} placeholder in AGENT_GOAL.md; the remaining goal sections render as explicit "not yet specified by user" entries rather than instructional placeholders, so they are not mistaken for user-approved scope. If objective is provided, substitute it for the {{ objective }} placeholder in AGENT_PROGRESS.md; if objective is omitted, remove the entire ## Current Objective section from AGENT_PROGRESS.md rather than leaving a literal placeholder, so the file remains internally consistent.
  5. Return target_dir, files_created, and files_skipped.

Read the full file on GitHub · 63 lines

Files

What ships with it

7 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.

  1. 11d ago First seen · 63 lines · 68 tokens per session scan A d548d40ec6e8

Subscribe to this mod's changes

agent-files is a skill published in the GitHub repository zhouyou-gu/skill-marketplace-template (5 stars, last pushed 18d ago), licensed MIT. It adds 68 tokens to every session and 1,550 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens