fewer-permission-prompts
Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.
- License 许可
- CC0-1.0
- 最近更新
- 2026-11-14
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- fewer-permission-prompts
- description
- Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.
03 SKILL.md 正文
Fewer Permission Prompts
Look through my transcripts' MCP and bash tool calls, and based on those, make a prioritized list of patterns that I should add to my permission allowlist to reduce permission prompts. Focus on read-only commands.
The format for permissions is: Bash(foo*), Bash(foo), Bash(foo bar *), mcp__slack__slack_read_thread, etc.
Then, add these to the project .claude/settings.json under permissions.allow.
Steps
-
Locate transcripts. Session transcripts live at
~/.claude/projects/<sanitized-cwd>/*.jsonl. Each line is a JSON object. Tool calls appear asassistantmessages withmessage.content[]entries oftype: "tool_use". Thenamefield identifies the tool (e.g."Bash","mcp__slack__slack_read_thread"); for Bash,input.commandis the shell string.Scan the recent transcripts across the user's projects dir — not just the current project — so the allowlist reflects their actual usage. Cap the scan at a reasonable number of recent sessions (e.g. 50 most-recently-modified JSONL files) so this stays fast.
-
Extract tool-call frequencies.
- For
Bashcalls: parseinput.command, take the leading command token (handlingsudo,timeout, pipes,&&, env-var prefixes). Record the command + first subcommand pair (e.g.git status,gh pr view,ls,cat). - For MCP calls: record the full tool name (e.g.
mcp__slack__slack_read_thread). - Count occurrences across the scanned transcripts.
- For
-
Filter to read-only. Keep only commands that don't mutate state. Examples of read-only:
ls,cat,pwd,git status,git log,git diff,git show,git branch,rg,grep,find,head,tail,wc,file,which,echo,date,gh pr view,gh pr list,gh pr diff,gh issue view,gh issue list,gh run list,gh run view,gh api(GET),bun run typecheck,bun run lint,bun run test(for tests that don't mutate),docker ps,docker logs,kubectl get,kubectl describe,ps,top,df,du,env,printenv, any MCP tool withread/get/list/search/viewin its name.Drop anything that writes, deletes, renames, pushes, merges, installs, or runs a build/test that has side effects. When in doubt, leave it out.
Never allowlist a pattern that grants arbitrary code execution. A wildcard rule for any of these (e.g.
Bash(python3:*)) is equivalent to allowing arbitrary code execution. This list is not exhaustive — apply the same rule to anything in the same category:- Interpreters:
python/python3,node,bun,deno,ruby,perl,php,lua, etc. - Shells:
bash,sh,zsh,fish,eval,exec,ssh, etc. - Package runners:
npx,bunx,uvx,uv run, etc. - Task-runner wildcards:
npm run *,yarn run *,pnpm run *,bun run *,make *,just *,cargo run *,go run *, etc. — an exactBash(bun run typecheck)is fine,Bash(bun run *)is not - Tools that start an interpreter in the working directory:
pyrightin any form (it runspython3there, which imports from that directory first), and similar gh api *,docker run/exec,kubectl exec,sudo, and similar
- Interpreters:
-
Drop commands Claude Code already auto-allows. These don't need an allowlist entry — they never prompt. If you see any of these in the transcripts, skip them; don't suggest them to the user.
- Always auto-allowed (any args):
cal,uptime,cat,head,tail,wc,stat,strings,hexdump,od,nl,id,uname,free,df,du,locale,groups,nproc,basename,dirname,realpath,cut,paste,tr,column,tac,rev,fold,expand,unexpand,fmt,comm,cmp,numfmt,readlink,diff,true,false,sleep,type,expr,seq,tsort,pr,echo,ls,cd. - Auto-allowed with zero args only:
pwd,whoami,alias. - Auto-allowed exact forms:
claude -h,claude --help,node -v,node --version,python --version,python3 --version,ip addr. - Auto-allowed with safe flags only (validated):
xargs,file,sed(read-only expressions),sort,man,help,netstat,ps,base64,grep,egrep,fgrep,sha256sum,sha1sum,md5sum,tree,date,hostname,which,lsof,pgrep,tput,ss,fd,fdfind,aki,rg,jq,uniq,history,arch,ifconfig,find(blocks-delete/-exec/-execdir/-ok/-okdir/-fprint*/-fls/-files0-from),printf(blocks any-flag),test(blocks-v/-R/-a/-o). - All git read-only subcommands:
git status,git log,git diff,git show,git blame,git branch,git tag,git remote,git ls-files,git ls-remote,git config --get,git rev-parse,git describe,git stash list,git reflog,git shortlog,git cat-file,git for-each-ref,git worktree list, etc. - All gh read-only subcommands:
gh pr view,gh pr list,gh pr diff,gh pr checks,gh pr status,gh issue view,gh issue list,gh issue status,gh run view,gh run list,gh workflow list,gh workflow view,gh repo view,gh release view,gh release list,gh api(GET),gh auth status, etc. - Docker read-only subcommands:
docker ps,docker images,docker logs,docker inspect.
Source of truth:
src/tools/BashTool/readOnlyValidation.ts(READONLY_COMMANDS,READONLY_NOARGS,READONLY_EXACT,COMMAND_ALLOWLIST) andsrc/utils/shell/readOnlyCommandValidation.ts(GIT_READ_ONLY_COMMANDS,GH_READ_ONLY_COMMANDS,DOCKER_READ_ONLY_COMMANDS,RIPGREP_READ_ONLY_COMMANDS). If the user is in this repo and you're unsure whether a command is covered, grep these files rather than guessing. - Always auto-allowed (any args):
-
Pick the pattern form. Use the narrowest pattern that still covers the observed usage:
- If the user runs many variants (
git log,git log --oneline,git log main..HEAD): useBash(git log *)— note the space before*, which is required for prefix matching to work correctly. - If a single exact invocation is common: use
Bash(foo)with no wildcard. - For MCP: use the full tool name verbatim (no wildcard needed; they're already specific).
- Never widen a pattern to the point that it conflicts with the rules above (no arbitrary code execution, no mutation/side effects).
- If the user runs many variants (
-
Prioritize. Rank by count descending. Drop anything that appeared fewer than ~3 times — not worth the allowlist entry. Cap the list at the top ~20 so the user can skim it.
-
Present the prioritized list to the user as a markdown table with columns: rank, pattern, count, one-line description. Example:
# Pattern Count Notes 1 Bash(git status *)142 repo status checks 2 Bash(gh pr view *)87 PR inspection 3 mcp__slack__slack_read_thread54 Slack thread reads -
Merge into
.claude/settings.jsonin the current project (not~/.claude/settings.json, not.claude/settings.local.json). Create the file if it doesn't exist. Preserve existing keys and existing entries inpermissions.allow; de-duplicate against what's already there; don't remove anything; don't reorder unrelated fields. -
Report back. Tell the user what you added (count + a few examples), what was already in the allowlist, and what you skipped and why (e.g. "dropped
rmandgit push— not read-only; droppedcat/ls/git status— already auto-allowed, no rule needed").
Do not add anything to permissions.deny or permissions.ask. Do not touch any other settings field.
04 同仓库更多 Skills
model-council
暂无简介
writing-style
Draft or edit writing in the user's voice for the person who will read it and where it will appear. Use for messages, emails, documents or slides written on their behalf, not for your own replies.
write-page
Create or edit requested Page/Space content, or use for prose you have already decided to save as a standalone Markdown file, only if the user did not explicitly request a Markdown file. Honor established formats, destinations, and repository documentation. A selected Page alone does not authorize a write.
software-engineering
For use only in threads for this proactive personal assistant. Investigate software issues; inspect, write, review, or test code; work on a repository or local engineering file; or create, fix, or monitor a pull request or CI run. Use for actual engineering or product QA work, not a general programming explanation.
slides-artifact
Use when the user asks to create, edit, or review slides or a presentation (PowerPoint or Google Slides), including when the task clearly calls for an audience-ready slide deck. Also use to answer questions that require inspecting an existing deck; not for general presentation advice or a chat-only outline.
slack
Use when reading Slack conversations, deciding when to respond, or sending messages, files, and reactions in Slack.