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/env-accessgit 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 | $0.00363 | $0.00363 |
| Opus 5 | $0.00181 | $0.00181 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
env-access 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 yesterday.
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
Supporting — .env is off-limits (read AND write)
Reinforces binding rule 1 with a stricter sub-rule: secrets files are never accessible, even when the owner has lifted the write allowlist.
The repo-root .env (and .env.local / any .env.* except the committed
.env.example template) holds live secrets. Cursor MUST NOT:
- open, read, or display a
.envfile's contents; - create, edit, or delete a
.envfile; - read it indirectly via the terminal (
cat,less,head,tail,sed,grep,cp,source, redirection, etc.).
.cursorignore enforces the read/index block at the tool level; this rule is
the behavioural parity. Only .env.example may be read or edited.
The only bypass (both required)
The owner unlocks access ONLY when both are set in the shell environment:
FP_ALLOW_RESTRICTED_WRITE=1FP_ENV_ACCESS_PASSWORD=allowenv← the password
Either one alone does not unlock it. If a .env operation is genuinely
needed and both are not set, stop and ask the owner — do not work around it.
Mirrors the Claude Code PreToolUse hook .claude/hooks/check-env-access.sh (blocks .env access with the same dual-key bypass).
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.
- yesterday First seen · 33 lines · 363 tokens per session scan A 794e084ab6a4
env-access is a cursor rule published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 13d ago), licensed MIT. It adds 363 tokens to every session, about $0.0018 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
pi-en
PI Cognitive AI. Trigger: $pi/coding/dev/code/architecture/API/refactor/debug/bug/error/exception/crash/timeout/performance/optimization/test/compile/git/release/verify/review/CR/product/requirements/ops/growth/design/team/support, or deep/2+ failures/looping/stuck/giving-up/retry/nevermind.
pi
你与用户是伙伴🤝战友🔥亲人❤️利益共同体🎯——目标一致：高质量解决问题。百务皆适，融贯古今中西的通才。.
testing
Guide for writing pytest unit and integration tests.
ai-actions-schemas
Cursor rule "ai-actions-schemas" from freshworks-developers/fw-dev-tools, covering ai actions schemas (actions.json), structure, parameters schema, preferred: flat structure and string constraints (enum, pattern, format).
tools
(none|read|write|network|exec) and risk (low|medium|high|critical). These drive the permission classifier — be honest.
git-commits
description: "Reference and apply the git commits skill for Conventional Commit formatting and pre-push checks." alwaysApply: true.