atlas-ledger

atlas-ledger is a skill for Claude Code from Ghosteken/agent-harness. It costs 56 tokens per session (3,701 once invoked), scanned A, a copy of atlas-ledger, MIT.

A companion method that turns mistakes found during goal checks into reusable rules stored in a project’s Atlas.md file after confirmation.

In plain words
What is it for?
Use it after an agent drifts from the request or after a review identifies a lesson worth recording for future tasks.
Why use it?
It helps prevent the same kind of agent mistake from recurring in later work.

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 after an agent drifts from the request or after a review identifies a lesson worth recording for future tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ghosteken/agent-harness/atlas-ledger
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-ledger
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-ledger

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ghosteken/agent-harness/atlas-ledger"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/atlas-ledger.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 3,701 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 95% 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 $0.03701
Opus 5 $0.00028 $0.01851
Sonnet 5 $0.00011 $0.00740
Haiku 4.5 $0.00006 $0.00370

Measured 8d ago against content hash c62d03abf38f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

atlas-ledger 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

95% identical to atlas-ledger — 32 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-ledger/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atlas Ledger v2.2

Give the Atlas series a memory.

Contents

  1. Output Language
  2. When To Run
  3. Distillation (the core) — Steps 1–6
  4. Atlas.md format
  5. Clause maintenance
  6. Integration with atlas-contract
  7. Final Principle

Quick reference

caught drift (auto handoff from Final Audit / Post Review / Phase Check / user request)
 → Step 1  state facts, not motive
 → Step 2  draft WHEN / DON'T / INSTEAD
 → Step 3  four gates: Actionability → Replay → Generalization → Over-reach
 → Step 4  first occurrence = Observation [O#]; repeat or high-severity = Clause [L#]
 → Step 5  propose, ATLAS_STOP, write only after user confirms
 → Step 6  merge-first into Atlas.md; confirmed clauses ≤ 15

atlas-contract defends the goal within one conversation, but it starts from zero every time — it does not know where this project drifted before. atlas-ledger closes that gap: when a drift is caught, it distills the lesson into a permanent, project-local contract clause and (after the user confirms) writes it to Atlas.md. Next time atlas-contract builds a Goal Contract, it loads the relevant clauses, so the defense line thickens with each catch. That is the compounding effect.

It is a low-frequency, lightweight companion. It runs only after a drift is caught, and it stays small on purpose. Do not turn it into a second heavy governance skill — its only hard job is distillation quality.

Core idea

The job is not to keep a diary. A record of "what went wrong" is a memory; it changes nothing. The job is a translation:

turn this caught drift → into a clause that can enter a future contract and trigger a stop.

A diary says "I hid the feature." A ledger clause says "WHEN a backend requirement is blocked, DON'T hide the feature, INSTEAD stop and disclose." Only the second one catches it next time. The entire value of this skill is the quality of that translation — and since it is run by the same model that drifted, the mechanisms below exist to keep it honest rather than trusting it to be careful.

Read the full file on GitHub · 252 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 · 252 lines · 56 tokens per session scan A c62d03abf38f

Subscribe to this mod's changes

atlas-ledger 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 3,701 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to atlas-ledger, differing in 32 lines, and is treated as a copy.

Related

Other skills, from other repositories

recall-conversations

Read what was said in an earlier conversation — the parent's previous chats with Quill, or a child's conversation with the tutor inside an activity — from the platform's conversation logs.

manishiitg/coding-agent-loop · 40 tokens

agentic-identity-trust

Skill "agentic-identity-trust" from aimerdoux/wavex-os, covering agentic identity & trust architect, 🧠 your identity & memory, 🎯 your core mission, agent identity infrastructure and trust verification & scoring.

aimerdoux/wavex-os · 0 tokens

chief-of-staff

Skill "chief-of-staff" from aimerdoux/wavex-os, covering 🧭 chief of staff, 🧠 your identity & memory, 🎯 your core mission, 💭 your communication style and 🚨 critical rules you must follow.

aimerdoux/wavex-os · 0 tokens

whimsy-injector

Skill "whimsy-injector" from aimerdoux/wavex-os, covering whimsy injector agent personality, 🧠 your identity & memory, 🎯 your core mission, inject strategic personality and create memorable experiences.

aimerdoux/wavex-os · 0 tokens

codebase-onboarding-engineer

Skill "codebase-onboarding-engineer" from aimerdoux/wavex-os, covering codebase onboarding engineer agent, 🧠 your identity & memory, 🎯 your core mission, build fast, accurate mental models and trace real execution paths.

aimerdoux/wavex-os · 0 tokens

zk-steward

Skill "zk-steward" from aimerdoux/wavex-os, covering zk steward agent, 🧠 your identity & memory, 🎯 your core mission, build the knowledge network and domain thinking and expert switching.

aimerdoux/wavex-os · 0 tokens