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.
git clone --depth 1 https://github.com/fmflurry/settings-opencodeWrote 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/rules/fmflurry/settings-opencode/tool-budget)<a href="https://agentmods.dev/rules/fmflurry/settings-opencode/tool-budget"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/tool-budget/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/fmflurry/settings-opencode/tool-budget"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/tool-budget.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00681 | $0.00681 |
| Opus 5.5 | $0.00272 | $0.00272 |
| Sonnet 5.5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
tool-budget 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 8d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Budget (exploratory shell rate-limiting)
Bash Classification
VERIFICATION (uncapped, never counted, never nudged)
Never counted against budget; no L1/L2 steering applies. Runs:
- Build/typecheck/test/lint/format:
tsc,npm run *,pnpm run *,bun run *,yarn run *,cargo,go build,mypy,pyright,mvn,gradlew,dotnet build,dotnet test,dotnet format,eslint,ruff,clippy - Git state:
git status,git diff,git log,git stash,git show - Process & port checks:
lsof,netstat,ps,grepon process lists - Sequential command chains: any command whose output feeds the next command's input (genuine dependency)
EXPLORATORY (counted against budget)
Counted toward the 3-call limit unless the brief raises it:
- Directory listing:
ls,rtk ls,find,rtk find,tree - Content search:
grep,rtk grep,rg,ag - File inspection:
cat,head,tail,wc,file,stat - Targeting: source code or repo structure
Allowlist-First Principle
Unknown commands default to NOT counted. Under-enforce rather than block real work.
Exploratory Budget Rules
- Default: 3 calls per dispatched task unless the brief raises it.
- Pre-requisite: Before the 1st exploratory call, at least one code-memory call must have been made. Before the 4th, at least two code-memory calls.
- Target ratio: exploratory bash : edits ≤ 2 (proven achievable at 1.35).
Trip Levels (L1 and L2 ONLY)
L3 deny is deliberately deferred; conduct L1 steer + L2 justify only.
L1 Steer (at 3rd exploratory call with 0 edits)
Conductor nudges toward code-memory or Read: "Before the 4th exploratory bash, show progress: either code-memory topology tool or a Read to a targeted line range."
L2 Justify (when ratio > 3 at ≥5 edits)
Require a one-line justification in the next message: bash-budget: <why exploratory shell is still necessary>.
Anti-Displacement Rule
CRITICAL: Do NOT reroute a blocked exploratory call into a full-file Read. A 900-line Read costs more tokens than the grep it replaced.
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.
- 8d ago First seen · 58 lines · 681 tokens per session scan A 1792dbf2403d
tool-budget is a cursor rule published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 681 tokens to every session, about $0.0027 per session on Opus 5.5. 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 2026-10-08.
Other cursor rules, from other repositories
explorer-interface-brief
Use when asked to design the interface for an interactive 3D explorer, plan a UI for exploring a 3D model of a topic, or write an image-model prompt for a 3D learning app mock-up. Produces, from a topic, the UI design brief (audience, layout, panels, interactions, label style, colour palette, accessibility) and an…
reflection-basic
Basic reflection format for Level 2 Simple Enhancement tasks.
simplicity
Simplicity - smallest correct diff; reuse, platform, installed deps before new code; no speculative abstraction.
git-workflow
Rules for git operations, commit strategy, and GitHub CLI usage.
feedback-enhanced
Rules for an interactive feedback system that lets users and an AI agent discuss complex development work in real time. It includes guidance for recording decisions, tracking progress and handling detailed inputs such as code and diagrams.
kiss-ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.