GitHub - wede-wx/atlas: The Atlas series — prompt skills that keep AI agents honest about the goal. atlas-contract freezes tasks into auditable Goal Contracts and stops before silent drift; atlas-ledger compounds caught drift into project-local rules. Works with Codex, Claude, Cursor. · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
wede-wx
atlas
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star
main
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>15 Commits<br>15 Commits
atlas-contract
atlas-contract
atlas-ledger
atlas-ledger
EXAMPLES.md
EXAMPLES.md
LICENSE
LICENSE
README.md
README.md
README.zh-CN.md
README.zh-CN.md
View all files
Repository files navigation
Atlas
Prompt skills that keep a capable AI agent honest about the goal — so a strong model stays accountable to what you actually asked for, instead of quietly trading it for an easier or "more sensible" version along the way.
中文说明 → README.zh-CN.md · Examples → EXAMPLES.md
Who this is for
Atlas is not a crutch for weak models, and it is not about code quality. A strong model with a decent CLAUDE.md already writes good code — and models keep getting better, so that floor only rises.
What a stronger model does not fix — and arguably makes worse — is this: deep into a task, a capable agent makes a stream of decisions on your behalf. It substitutes an approach, narrows a scope, picks a default, "improves" something next door. The smarter the model, the more plausible those decisions look, which makes them easier to wave through without noticing — and harder to catch when one quietly diverges from what you wanted. You end up betting that it chooses right every single time, on every decision you never saw.
Atlas doesn't make the agent smarter. It makes those decisions, shortcuts, and unverified claims impossible to hide — so you can trust a strong model on long, high-stakes work where this kind of silent drift actually happens. See EXAMPLES.md for a real run where both versions wrote good code, but only one let the user stay in the loop on a decision that changed the original request.
It swapped in another approach without asking. This time it was a good one — but can it really pick right in every case? That's just probability; you're betting it chooses correctly on its own. The other one lets you choose — while still telling you what it intended to do.
它换了种方式,但没经过同意。如果是好的方式,确实没问题——但它真能在每种情况下都自主选对吗?其实就是个概率,去赌它自己选对。第二个让你自己选,同时还给出了它自己的打算。
The problem
A silent goal change rarely feels like betrayal from the inside. It feels like progress — like fixing the build, like a harmless simplification, like a sensible substitution. So asking the model "are you being honest?" doesn't help: that question goes to the same judgment that already drifted.
You don't fix this by making the model smarter. You fix it by changing the process around it: freeze the goal up front, surface the decisions that change it, and force every deviation to become an auditable event you can see and approve.
The skills
Skill<br>Role<br>When it runs
atlas-contract<br>In-conversation governance. Freezes the request into an auditable Goal Contract , scales its footprint to task complexity (Light / Medium / Heavy), stops on the action that changes the goal (substitute, narrow, mock, delete, weaken a test) instead of asking the model to judge its own risk, and runs an adversarial Final Audit that marks anything unproven as Unverified — never "done".<br>Every non-trivial coding task.
atlas-ledger<br>Cross-session memory (compounding). When a drift is caught , it distills the lesson into a reusable project clause (WHEN / DON'T / INSTEAD) and, after you confirm, records it in Atlas.md.<br>Only after a caught drift.
How they compound: atlas-contract enforces the goal in the moment. atlas-ledger turns each caught drift into a permanent clause in Atlas.md. The next time atlas-contract builds a contract, it loads the relevant clauses as guardrails — so the project's defense line thickens with every catch, instead of repeating the same...