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/harshanandak/forge/permissions-guidancegit clone --depth 1 https://github.com/harshanandak/forgeWrote 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/harshanandak/forge/permissions-guidance)<a href="https://agentmods.dev/rules/harshanandak/forge/permissions-guidance"><img src="https://agentmods.dev/badge/rules/harshanandak/forge/permissions-guidance.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.00394 |
| Opus 5 | $0.00005 | $0.00197 |
| Sonnet 5 | $0.00002 | $0.00079 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade C, and why
permissions-guidance scanned grade C 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 6d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Bash(rm -rf *), Bash(git push --force *), Bash(git push -f *) What it actually says
Cursor's allow/deny lists are configured in the IDE, not project files.
Enable YOLO mode: Cursor Settings → Features → Chat & Composer → Enable YOLO mode
Recommended Allow List (auto-run without prompt)
Bash(git status *), Bash(git log *), Bash(git diff *), Bash(git branch *)
Bash(git add *), Bash(git commit *), Bash(git push *), Bash(git stash *)
Bash(git checkout *), Bash(git switch *), Bash(git merge *), Bash(git worktree *)
Bash(bun *), Bash(bunx *), Bash(npm *), Bash(npx *), Bash(node *)
Bash(forge *), Bash(gh *), Bash(openspec *)
Bash(ls *), Bash(cat *), Bash(grep *), Bash(find *), Bash(pwd *), Bash(which *)
Bash(echo *), Bash(head *), Bash(tail *), Bash(sort *), Bash(wc *)
Bash(mkdir *), Bash(touch *), Bash(cp *), Bash(mv *)
Confirm Before Running (prompt each time)
Bash(git rebase *), Bash(git reset --hard *)
Recommended Deny List (always block)
Bash(rm -rf *), Bash(git push --force *), Bash(git push -f *)
See docs/research/agent-permissions.md for the full permission tier classification and rationale.
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.
- 6d ago First seen · 38 lines · 11 tokens per session scan C e7ce12513118
permissions-guidance is a cursor rule published in the GitHub repository harshanandak/forge (4 stars, last pushed 6d ago), licensed MIT. It adds 11 tokens to every session and 394 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.