AGENTS.md@rulesA
AGENTS.md@rules from ridelink0/claude-code-usage-limits is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add ridelink0/claude-code-usage-limits/rules/AGENTS.md@git:20260914.7b50d6cPins git:20260914.7b50d6c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- ridelink0/claude-code-usage-limits
- Path
rules/AGENTS.md- Versions recorded
- 2
- Latest version
- git:20260914.7b50d6c, committed Sep 14, 2026
- First version recorded
- Sep 11, 2026
- Size
- 2,030 bytes
- Repository stars
- 5
- License
- MIT
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Usage Limits These rules are always on. They are about how to spend a budget, not about whether to do the work. ## The rule that matters most A long list is not a reason to work in parallel. Spawning agents to take a list apart is the single most expensive thing an agent can do: a measured fan-out costs between two and a half and six times what the same work costs done in sequence, because every agent re-reads its own context from cold and none of them can report back until they all stop. Do a long list one item at a time, in this session, where the context is already paid for. ## Before starting - Read the budget line the plugin injects before each turn. It says which window binds, how much of it is gone, and roughly how many turns that leaves. - Plan the order, not the amount. Put the part that is most valuable and most likely to be wanted first, first. Scaling work down is the user's decision, never the agent's. - If a step is mechanical, it does not need the most expensive reasoning setting. Changing the setting mid-session has its own cost, so choose it at the start of a session rather than switching part-way through. ## While working …
Read the whole file at its exact version.
How to install
mdr add ridelink0/claude-code-usage-limits/rules/AGENTS.md@sha256:83711c4ee73959daThe line at the top of this page pins the label git:20260914.7b50d6c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_gx4juswtizayq4ar)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 11, 2026 and Sep 14, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260914.7b50d6c latest | 2026-09-14 | 7b50d6c | 2,030 B | A | view · diff |
| git:20260911.10606c1 | 2026-09-11 | 10606c1 | 262 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (2030 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ridelink0/claude-code-usage-limits · 5 stars · license MIT · pushed 2026-09-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gx4juswtizayq4ar GET https://markdownregistry.com/api/v1/resolve?ref=ridelink0/claude-code-usage-limits/rules/AGENTS.md GET https://markdownregistry.com/api/v1/blob/83711c4ee73959da4902e2afe859ba910da967f3cc20f950f6ccf825abd6fb71
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.
More from ridelink0/claude-code-usage-limits
Every file in ridelink0/claude-code-usage-limits