nah Claude Code permission guard
Hacker ApprovedPermission guard in Developer tools
Classifies Claude Code commands by what they actually do and blocks destructive ones, so you can skip most prompts. Critics say it cannot cover every context.
Classifies Claude Code commands by what they actually do and blocks destructive ones, so you can skip most prompts. Critics say it cannot cover every context.
11 people gave an opinion
- recommend it
- 10
- criticize it
- 1
- approval share
- 91%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 10 people recommend itNeeds 10 or more, met.
- 10 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Safety net for autonomous agent runs
“You get the same uninterrupted flow as --dangerously-skip-permissions but with nah as your safety net”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” “I feel better doing that more autonomously with nah as a safety net”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” “it's a guardrail for a trusted but mistake-prone agent”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” Catches destructive commands and secret reads
“blocks catastrophic agent actions like filesystem destruction, secrets exfiltration, and git disasters.”
Comment from 9 Aug 2026 in “Ask HN: What are you working on? (August 2026)” “nah does guard some of this - reading .env or ~/.aws/credentials gets flagged”
Comment from 13 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” “Even when buried in a longer chain, nah flags it.”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” - Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code”
Deterministic layer handles most inputs
“the deterministic layer handled about 95% of inputs with zero latency/tokens”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” “The deterministic layer first → LLM only for edge cases is the right call”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” Well-designed, no-dependency code
“Smart design, and the no-dependency stdlib approach is the right call for security tooling.”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” “Regardless, this looks like a well thought out project, and I love the name!”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” “nah was built with this method and I am very happy with the code quality”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code”
What people warn about
Each mark is one comment
Cannot cover every possible context
“it will just be a maintenance nightmare to account for _all_ possible contexts”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code” Not a complete fix for risk
“Won't close it 100% (a sandbox is the answer to that) but gets a lot better.”
Comment from 12 Mar 2026 in “Show HN: A context-aware permission guard for Claude Code”
What people recommend instead
The same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| nah Claude Code permission guardThis page | 10 | 1 | 91% | 5 | — | Approved |
| Claude Code permission guard | 7 | 4 | 64% | 1 | — | — |
What people said
24 of the 28 comments that mention it, newest first. Each links to the original comment.
“is resilient to an adversarial agent that tries to remove the guard”
“Love the vibe of the website!”
“blocks catastrophic agent actions like filesystem destruction, secrets exfiltration, and git disasters.”
“A better permissions layer for coding agents.”
“nah is a context aware permission layer that clasifies commands based on what they actually do”
“nah does guard some of this - reading .env or ~/.aws/credentials gets flagged”
“it's a guardrail for a trusted but mistake-prone agent”
“the semantic classification approach (what does this tool call actually do, not what is it named) is much more robust”
“The deterministic layer first → LLM only for edge cases is the right call”
“Smart design, and the no-dependency stdlib approach is the right call for security tooling.”
“the immutable log file fits well with nah”
“nah was built with this method and I am very happy with the code quality”
“the deterministic layer handled about 95% of inputs with zero latency/tokens”
“nah catches both of these out of the box.”
“the composition rules approach makes a lot of sense, will give it a try”
“Which is pretty great imo.”
“container handles OS boundaries, and nah adds the semantic layer”
“Won't close it 100% (a sandbox is the answer to that) but gets a lot better.”
“I feel better doing that more autonomously with nah as a safety net”
“nah guards this at multiple layers”
“Even when buried in a longer chain, nah flags it.”
“it will just be a maintenance nightmare to account for _all_ possible contexts”
“You get the same uninterrupted flow as --dangerously-skip-permissions but with nah as your safety net”
“Regardless, this looks like a well thought out project, and I love the name!”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.