Borrowing it
Nothing to install: this file belongs to Rethunk-AI/clodbridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Rethunk-AI/clodbridge/main/.cursor/skills/manage-scope-iteratively/SKILL.mdgit clone --depth 1 https://github.com/Rethunk-AI/clodbridgeWrote 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.
[](https://agentmods.dev/skills/rethunk-ai/clodbridge/manage-scope-iteratively)<a href="https://agentmods.dev/skills/rethunk-ai/clodbridge/manage-scope-iteratively"><img src="https://agentmods.dev/badge/skills/rethunk-ai/clodbridge/manage-scope-iteratively.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.01217 |
| Opus 5 | $0.00012 | $0.00609 |
| Sonnet 5 | $0.00005 | $0.00243 |
| Haiku 4.5 | $0.00002 | $0.00122 |
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Scope Iteratively
The Principle
Deliver incrementally. Each commit is a checkpoint for user feedback.
Increment = One Commit
An "increment" is exactly one commit's worth of work:
Increment = 1 commit = 1-5 files = < 500 lines = 1 feature/fix
After completing an increment:
- Commit the code
- Check in with the user ("X is done. Should I proceed?")
- Wait for feedback
- Continue based on guidance
When to Check In
After completing:
| Milestone | Check In? | What to Say |
|---|---|---|
| New type definition + tests pass | YES | "Types done. Should I proceed with parsing?" |
| Parsing function + tests pass | YES | "Parsing works. Ready for discovery modules?" |
| Major subsystem (server, tools, resources) | YES | "Server core done. Ready for tools?" |
| You're about to start something big (> 200 LOC) | YES | "About to implement MCP resources. Proceed?" |
| A design decision arises | YES | "Found a design question: MCP Resources schema?" |
| You hit a blocker | YES | "Can't install npm. Options: ..." |
| Integration point between systems | YES | "Reader + server wired. Proceed with tools?" |
Checkpoint Template
After a commit:
✅ "{Feature description} is complete.
{Optional: What was done}
- Implemented {module}
- Wrote {N} tests
- All tests pass
{Optional: What's next}
Next: {next milestone}
Should I proceed?"
Examples:
Example 1:
✅ "Types and interfaces are defined.
- RuleMode type (4 modes)
- CursorRule, CursorSkill, CursorAgent interfaces
- CursorReader facade
Next: Implement parsing with gray-matter.
Should I proceed?"
Example 2:
✅ "Parsing works with all tests passing.
- parseRuleFile, parseSkillFile, parseAgentFile
- RuleMode derivation (always/auto-attached/agent-requested)
- 15 tests, all passing
Next: Implement discovery modules (rules, skills, agents).
Any feedback before I continue?"
Example 3:
⚠️ "Design question: How should MCP Resources expose data?
Options:
A) Raw file content only (cursor://rules/{name} returns .mdc text)
B) JSON indices only (cursor://rules returns structured list)
C) Both raw and JSON
D) Skip resources; tools are sufficient
What's your preference?"
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.
- 6d ago First seen · 204 lines · 23 tokens per session scan A 0732a1b8a528
manage-scope-iteratively is a skill published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,217 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 2026-08-31.
Other skills, from other repositories
init-workspace-flow
Workflow for initializing or upgrading a workspace: context, discovery, documentation, etc.
arrange-workspace-flow
Workflow for arranging a workspace: layout, reference source code, business/technical context, ecosystem setup.
testgen-flow
Workflow for generating test cases from requirements (Issue Tracker / Wiki sources), exporting to a Test Management System, etc.
backlog
To validate story readiness for a sprint or to break work into a human WBS.
dmfaster
Inspect and safely operate a user's live DM Faster sales workspace through the official Agent 1.0 MCP tools or CLI. Use when the user explicitly asks for current workspace priorities, campaign planning, exact audience previews, private list or campaign preparation, human-approved launch or pause, campaign performance…
capture
Capture a feature idea into Sprintra with stories, acceptance criteria, and decisions. Use when the user describes something they want to build, a feature request, or says "let's plan" or "I want to build".