generate-permission-allowlist-from-transcripts

name	generate-permission-allowlist-from-transcripts
description	Analyzes session transcripts to extract frequently used read-only tool-call patterns and adds them to the project's .claude/settings.json permission allowlist to reduce permission prompts
metadata	{"originalName":"Skill: Generate permission allowlist from transcripts","ccVersion":"2.1.240","sourceUrl":"https://github.com/Piebald-AI/claude-code-system-prompts/blob/main/system-prompts/skill-generate-permission-allowlist-from-transcripts.md","source":{"owner":"Piebald-AI","repo":"claude-code-system-prompts","ref":"main","path":"system-prompts/skill-generate-permission-allowlist-from-transcripts.md"}}

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

1. Locate transcripts. Session transcripts live at ~/.claude/projects/<sanitized-cwd>/*.jsonl. Each line is a JSON object. Tool calls appear as assistant messages with message.content[] entries of type: "tool_use". The name field identifies the tool (e.g. "Bash", "mcp__slack__slack_read_thread"); for Bash, input.command is 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.

2. Extract tool-call frequencies.

   • For Bash calls: parse input.command, take the leading command token (handling sudo, 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.

3. 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 with read/get/list/search/view in 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, , , , , etc.

4. 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, which, 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), , , , , , , , , , , , , , , , , , , , , , , , , , , , , , (blocks ///////), (blocks any ), (blocks ///).

5. 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): use Bash(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).

6. 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.

7. 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_thread	54	Slack thread reads

8. Merge into .claude/settings.json in 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 in permissions.allow; de-duplicate against what's already there; don't remove anything; don't reorder unrelated fields.

9. 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 rm and git push — not read-only; dropped cat/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.