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/punkadillo/figma-code-composer/verify-realitygit clone --depth 1 https://github.com/punkadillo/figma-code-composerWhat 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 | $0.00410 | $0.00410 |
| Opus 5 | $0.00205 | $0.00205 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
verify-reality 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.
What it actually says
Rule 7 — Verify against reality
When you need to know the state of the project, inspect it directly:
- Need to know if a file exists? →
GloborRead, do not trust an earlier turn. - Need to know what's on the working tree? →
git status/git diff. - Need to know if a token is emitted? → read the token output file, do not infer from a runner's claim.
- Need to know if a build passes? → run it.
Specific traps to avoid
- "An earlier turn said this component exists" — verify by reading the file.
- "The manifest says
existsOnDisk: true" — also verify byGlob-ingdiskPathbefore patching, because the manifest snapshot can lag the filesystem. - "The agent's final-report listed it as created" — confirm with
Globbefore treating the file as canonical (an agent report describes intent, not necessarily the outcome). - "A system-reminder mentioned X" — re-check the actual file; reminders can be stale.
In the figma pipeline specifically
- After a specialist finishes, do not chain "next" work based purely on its
componentsCreated[]/iconsCreated[]arrays. Glob the claimed paths first. - When auditing whether the coordinator should re-run a step, base the decision on what's actually on disk, not on a recalled "I already ran token-builder."
- Treat
manifest.jsonas a snapshot of when the fetcher ran — for anything time-sensitive (does this component exist NOW?), re-glob.
If a fresh check disagrees with what was claimed earlier — the fresh check wins. Surface the discrepancy as a flag.
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 · 30 lines · 410 tokens per session scan A 726f13139148
verify-reality is a cursor rule published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 14d ago), licensed MIT. It adds 410 tokens to every session, about $0.0020 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
testing
Testing rules for vitest suite.
development-phase
开发阶段：以新代码清晰合理为先，兼容仅在零代价时顺带.
cursorrules
Cursor rule "cursorrules" from evolution-foundation/evo-ai, covering evo ai - project rules and structure, main technologies, project structure, code standards and language requirements.
git-commits
description: "Reference and apply the git commits skill for Conventional Commit formatting and pre-push checks." alwaysApply: true.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.