manage-scope-iteratively

A set of development rules for delivering work in small increments, with a checkpoint after each commit. A commit is a saved unit of code changes.

In plain words
What is it for?
Breaking implementation into commit-sized tasks, running checks, and asking for direction before continuing.
Why use it?
It prevents long periods of unreviewed work and gives the user regular chances to provide feedback.

Cursor rule for Cursor

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/rethunk-ai/clodbridge/manage-scope-iteratively
Clone the repo
git clone --depth 1 https://github.com/Rethunk-AI/clodbridge

Made for: Cursor.

Per session 270 This file is loaded in full into every session.
When invoked 270 The same file — it is already loaded in full.
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 $0.00270 $0.00270
Opus 5 $0.00135 $0.00135
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 2d ago against content hash c4cafa4f80d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

manage-scope-iteratively 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/manage-scope-iteratively.mdc · 48 lines

What it actually says

Manage Scope Iteratively

Deliver incrementally. Check in with the user after each commit.

Increment = One Commit

After completing a commit-sized unit of work:

  1. Commit the code
  2. Check in: "X is done. Should I proceed with Y?"
  3. Wait for user feedback
  4. Continue based on feedback

When to Check In

After:

  • A new type definition + tests pass
  • A parsing function + tests pass
  • A major subsystem completes (server, tools, resources)
  • You're about to start something big (> 200 lines)
  • A decision point arises (should I implement X or Y?)

Example

✅ "Types and interfaces done. Next: parsing logic.
   Should I proceed?"

✅ "Parsing complete + tests pass. Next: discovery modules.
   Any feedback before I continue?"

✅ "Discovered design question: MCP resources (raw files, JSON index,
   or both)? What's your preference?"

Don't Do This

❌ Implement everything, commit it all, then ask "What do you think?"


For checkpoint patterns and detailed examples, see the manage-scope-iteratively skill.

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 · 48 lines · 270 tokens per session scan A c4cafa4f80d7

Subscribe to this mod's changes

manage-scope-iteratively is a cursor rule published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 270 tokens to every session, about $0.0014 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 2026-08-31.