atlas-contract

atlas-contract is a skill for Claude Code from Ghosteken/agent-harness. It costs 56 tokens per session (9,507 once invoked), scanned A, a copy of atlas-contract, MIT.

A goal-tracking method for coding agents that records the requested outcome and checks work against it during implementation.

In plain words
What is it for?
Use it when changing backend code, APIs, stored data, tests, or several related parts of a project.
Why use it?
It reduces silent scope changes, missed requirements, and rework on multi-step coding tasks.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the agent-harness plugin — 173 skills, 13 commands, 12 agents shipped together

Good fit Use it when changing backend code, APIs, stored data, tests, or several related parts of a project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ghosteken/agent-harness/atlas-contract
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 Ghosteken/agent-harness --skill atlas-contract
Clone the repo
git clone --depth 1 https://github.com/Ghosteken/agent-harness

Made for: Claude Code.

Or install agent-harness, the plugin that ships this one along with the rest of its 173 skills, 13 commands, 12 agents.

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 atlas-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/ghosteken/agent-harness/atlas-contract/github.svg)](https://agentmods.dev/skills/ghosteken/agent-harness/atlas-contract)
Your own site
<a href="https://agentmods.dev/skills/ghosteken/agent-harness/atlas-contract"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/atlas-contract/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 atlas-contract

Your own site · 80×15
<a href="https://agentmods.dev/skills/ghosteken/agent-harness/atlas-contract"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/atlas-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,507 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 94% copy Near-identical to another mod 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 $0.00056 $0.09507
Opus 5 $0.00028 $0.04754
Sonnet 5 $0.00011 $0.01901
Haiku 4.5 $0.00006 $0.00951

Measured 8d ago against content hash b5aa4f6aee24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

atlas-contract 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 8d 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.

Origin

This is a copy

94% identical to atlas-contract — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

archive/skills-community/atlas-contract/SKILL.md · 651 lines

How it starts

The opening of the file, as written. The whole thing — 651 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atlas Contract v6.2

Keep the agent aligned with the user's original goal during execution.

Contents

  1. Output Language
  2. When To Use Atlas, and How Much
  3. Footprints
  4. Anti-Drift Defaults 5–7. Goal Contract: build, format, confirmation gate
  5. Phases (Heavy footprint) 9–11. Deviation Notices, Phase Checks, escalation
  6. Final Audit — includes automatic atlas-ledger handoff
  7. Post Review
  8. Final Principle

Quick reference

Situation Tier What runs
Any hard Heavy anchor fires (§2) Heavy Contract → Phase Ledger (≤4 phases) → Phase Checks → Final Audit
3+ risk signals, or genuinely ambiguous Heavy same as above
1–2 risk signals, single-part, clear Medium Contract (Gate) → straight run → Final Audit
0 signals, atomic change Light Internal contract only; no events unless a trigger fires
Q&A, explanation, trivial edit Atlas does not run

Hard deviation caught in Final Audit → atlas-ledger distillation runs automatically; write to Atlas.md still requires user confirmation.

Atlas does not make the agent smarter. Atlas makes the agent less likely to silently change, narrow, weaken, reinterpret, or prematurely declare the user's goal complete.

Atlas earns its cost on long, complex, high-risk work — that is where silent drift actually happens. On small, low-risk tasks it should stay nearly invisible. The agent's footprint must scale with task complexity (see §2). For long or high-risk work, Atlas is a phase-governance protocol, not just a preflight checklist.

Core Rule

Challenge the user's goal when necessary. Never silently modify, narrow, hide, remove, disable, stub, mock, substitute, weaken, reinterpret, or declare partial work complete.

If a requirement must change, disclose the change before acting. If uncertainty may affect the user's goal, stop and ask.

Read the full file on GitHub · 651 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. 8d ago First seen · 651 lines · 56 tokens per session scan A b5aa4f6aee24

Subscribe to this mod's changes

atlas-contract is a skill published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 9,507 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to atlas-contract, differing in 22 lines, and is treated as a copy.