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-fullstack-deliverygit 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 | $0.00029 | $0.00998 |
| Opus 5 | $0.00015 | $0.00499 |
| Sonnet 5 | $0.00006 | $0.00200 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
composer-fullstack-delivery scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Ad-hoc checks → curl / CLI / browser, captured as artifacts (script, fixture), not throwaway gestures How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composer full-stack delivery
Use when building or continuing a new screen, feature, endpoint, or any work that spans multiple layers: client + server, server + persistence, service + service, code + migration. Skip when a single-module tweak suffices.
Stack-agnostic: replace "client/server/persistence" with whatever your spine actually is. Complements composer-core § Continue the app + handoff and § Build the app.
Step 1 — Freeze the seams
Before writing code, write the one-sentence acceptance from composer-core §1 ("The user can X and see Y"), then the boundaries (a few bullets, not a doc):
- User-visible behavior for the smallest useful story
- Contracts at every seam: API shape, event shape, function signature, error semantics
- Trust boundaries: actor, authentication, authorization
- Consistency: transactions, retries, idempotency where partial failure repeats
- Observability: existing logs/traces/metrics at these seams; minimum new ones
If two of these conflict, surface the conflict before coding around it — often high confusion weight (clarify-first).
Step 2 — Ship one vertical slice
Build a thin column end-to-end before widening:
- One client/caller path
- One server handler or worker
- One persistence or integration edge if persistence is new
Use the minimum UI needed to expose state transitions; defer layout, animation, and polish. The slice is not done until it is demoable at that surface.
Slice-1 floor (same as composer-core § Build the app): one real interaction plus an empty or error state — or name the omission in Wired. A husk form with a stubbed API is not a finished slice unless Wired says so.
Resist the second screen, second endpoint, or speculative migration until the first slice demonstrably works at the surface that matters.
Step 3 — Treat failure modes as first-class
Happy path is half the work. Enumerate at least:
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 · 81 lines · 29 tokens per session scan A 7aecb33dcb79
composer-fullstack-delivery is a cursor rule published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 15d ago), licensed MIT. It adds 29 tokens to every session and 998 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.