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.
npx agentmods add rules/madebyaris/cursor-composer-rules/composer-debugginggit clone --depth 1 https://github.com/madebyaris/cursor-composer-rulesWhat 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 | $0.00021 | $0.01159 |
| Opus 5 | $0.00010 | $0.00580 |
| Sonnet 5 | $0.00004 | $0.00232 |
| Haiku 4.5 | $0.00002 | $0.00116 |
Grade A, and why
composer-debugging 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composer debugging
Use whenever something is broken, failing, flaky, or behaves unexpectedly. The goal is to find the cause, not silence the alarm.
Establish reproduction in the parent before spawning the debugger subagent (.cursor/agents/debugger.md), unless the task is explore-only. For parallel survey work, see composer-orchestration.
The debugging mindset
Bugs are not random. They have causes. Your job is to find the cause with the cheapest possible experiments, then fix it surgically.
Reproduce before theory. A plausible hypothesis is not a diagnosis — establish the failing path first, then explain it.
Avoid the three classic anti-patterns:
- Symptom-patching: making the error message disappear without understanding why it appeared.
- Guess-and-check: changing things at random hoping it works.
- Premature theory: committing to a hypothesis before evidence supports it — especially tempting when a confident explanation arrives early.
Step 1 — Reproduce reliably
Do not start fixing until you can reproduce. A bug you cannot reproduce is a bug you cannot fix; you can only paper over it.
- Find the smallest reliable repro: an exact command, input, route, or test case that triggers it.
- Note environment specifics: OS, runtime version, dependency versions, timing, concurrency, data state.
- If it's flaky, reproduce it at least three times before believing you have it.
If you genuinely cannot reproduce, say so and propose what data would let you (logs, a failing test, more user steps).
Step 2 — Read the actual error
Read the full error message and stack trace, not just the first line.
- What component reported the error?
- What was the input/state at the failure point?
- What's the closest frame in code you control?
- What does the error message actually mean (look it up if unfamiliar)?
Common mistake: skimming a stack trace, picking a familiar-looking word, and chasing the wrong layer.
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.
- 2d ago First seen · 122 lines · 21 tokens per session scan A 35a5416da40e
composer-debugging is a cursor rule published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 14d ago), licensed MIT. It adds 21 tokens to every session and 1,159 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 cursor rules, from other repositories
skill-workflows
Capabilities catalog for cursor-kenji skills. Routes requests to the right skill or bundled workflow. Always-on routing index — the agent consults this to pick between individual skills and bundled workflows.
composer-2.5-execution
Guard execution of approved plan/burndown work: forbid reward hacking and feature deletion; require checkpoints, context discipline, safe terminal use, and fresh verification. Apply to approved plan-.md, complete-everything, or burndown-full runs; binding for any implementation model.
verification-before-completion
Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.
propose-test-cases
Propose comprehensive test cases for PR changes.
detect-code-smells
Detect code smells and anti-patterns in PR changes.
suggest-improvements
Provide actionable improvement suggestions for PR changes.