update-claude-md

update-claude-md is a cursor rule for Cursor from rajitsaha/100xprism. It costs 22 tokens per session (371 once invoked), scanned A, original, MIT.

A rule for keeping project corrections in CLAUDE.md, the file that records instructions for coding agents. After a user points out a mistake, it turns the lesson into a clear rule for future work.

In plain words
What is it for?
Use it after a correction to identify what went wrong, add a prevention rule, and confirm which instruction file was updated.
Why use it?
It reduces repeated mistakes by preserving project-specific feedback between coding sessions.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

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.

agentmods
npx agentmods add rules/rajitsaha/100xprism/update-claude-md
Clone the repo
git clone --depth 1 https://github.com/rajitsaha/100xprism

Made for: Cursor.

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 update-claude-md

README.md
[![agentmods](https://agentmods.dev/badge/rules/rajitsaha/100xprism/update-claude-md.svg)](https://agentmods.dev/rules/rajitsaha/100xprism/update-claude-md)
Your own site
<a href="https://agentmods.dev/rules/rajitsaha/100xprism/update-claude-md"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/update-claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00371
Opus 5 $0.00011 $0.00186
Sonnet 5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 2d ago against content hash 15dfa0a425d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

update-claude-md 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 2d 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.

.cursor/rules/update-claude-md.mdc · 52 lines

What it actually says

Suggested model tier: fast / low-cost (mechanical task)

Update-Claude — CLAUDE.md Rule Writer

After any correction, update CLAUDE.md with a rule to prevent the same mistake recurring.

How to use

  • /update-claude — after a correction, write a rule to CLAUDE.md

Phase 1 — Identify the pattern

What went wrong? What should have been done instead? Be specific — one clear pattern, not a vague note.


Phase 2 — Write a rule

Formulate as a clear, actionable rule:

- [Rule]: [What to do / not to do]. Why: [brief context].

Short rules stick. Long paragraphs get ignored.


Phase 3 — Update CLAUDE.md

PROJECT_ROOT=$(git rev-parse --show-toplevel)
INSTRUCTION_FILE=$(for f in CLAUDE.md AGENTS.md .cursorrules; do [ -f "$PROJECT_ROOT/$f" ] && echo "$PROJECT_ROOT/$f" && break; done)

Append the rule under a ## Rules or ## Corrections section in the project's instruction file. If no instruction file exists, create CLAUDE.md in the project root.


Phase 4 — Confirm

Tell the user: "Updated [file] with: [rule summary]"

If the rule isn't reducing mistakes after 2–3 sessions: rewrite it — be more specific or more prominent.

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. 2d ago First seen · 52 lines · 22 tokens per session scan A 15dfa0a425d6

Subscribe to this mod's changes

update-claude-md is a cursor rule published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 6d ago), licensed MIT. It adds 22 tokens to every session and 371 once invoked, about $0.0001 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 2026-09-03.