Permissions

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

| `sudo *` | Elevated privileges |

1. **NEVER auto-allow RED** — `rm`, `sudo`, `kill`, `curl|sh`, `mix ecto.reset`, `git push --force`, `chmod 777`

| RED | `rm -rf`, `sudo`, `kill`, `curl|sh`,`mix ecto.reset/drop`,`git push --force`,`git reset --hard` | Never recommend |

| `curl * \| sh` | Remote code execution |

| `wget * \| sh` | Remote code execution |

| `curl * \| bash` | Remote code execution |

Audit 0.4.1 · source sha 492f17636999 · 18 Oct 2026Report an issue or request a re-scan

• Publisheroliver-kriska GitHub userOwner of the repository this skill is read from
• Source folderoliver-kriska/claude-elixir-phoenix/plugins/elixir-phoenix/skills/permissionsThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict492f17636999A new audit runs when the source changes
• Repository statusNot archivedLast push 2 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Recommend safe Bash permissions for Elixir mix commands in settings.json. Use when permission prompts slow workflow, "fix permissions", "reduce prompts", "auto-allow mix".

---
name: permissions
description: Recommend safe Bash permissions for Elixir mix commands in settings.json. Use when permission prompts slow workflow, "fix permissions", "reduce prompts", "auto-allow mix".
argument-hint: "[--days=14] [--dry-run]"
effort: low
---

# Permission Analyzer

Scan recent session transcripts to find Bash commands you keep approving,
cross-reference with current `settings.json`, and recommend adding the missing ones.

**Primary goal**: Discover MISSING permissions from actual usage.
**Secondary goal**: Clean up redundant/garbage entries.

## Usage

`/phx:permissions [--days=14] [--dry-run]` — Scans session JSONL files, finds uncovered Bash commands, classifies risk, and recommends `settings.json` changes. Use `--dry-run` to preview without writing.

## Arguments

`$ARGUMENTS` — `--days=N` (default: 14), `--dry-run` (preview only).

## Iron Laws

1. **NEVER auto-allow RED** — `rm`, `sudo`, `kill`, `curl|sh`, `mix ecto.reset`, `git push --force`, `chmod 777`
2. **Evidence-based only** — Only recommend commands actually approved in sessions
3. **Show before writing** — Present full diff, get explicit confirmation
4. **Preserve existing** — Merge, never overwrite

## Risk Classification

| Level | Examples | Action |
|-------|----------|--------|
| GREEN | `ls`, `cat`, `grep`, `tail`, `which`, `mkdir`, `cd`, `mix test/compile/credo/format`, `git status/log/diff` | Auto-recommend |
| YELLOW | `git add/commit/push`, `mix ecto.migrate`, `mix deps.get`, `npm install`, `docker build/run`, `source`, `mise exec` | Recommend with note |
| RED | `rm -rf`, `sudo`, `kill`, `curl|sh`,`mix ecto.reset/drop`,`git push --force`,`git reset --hard` | Never recommend |

## Workflow

### Step 1: Extract Bash Commands from Session JSONL Files

Run the extraction script from `${CLAUDE_SKILL_DIR}/references/extraction-script.md`.
This scans all project JSONL files from the last N days, checks each Bash command
against current `settings.json` patterns, and reports uncovered commands with counts.

Run this before any settings cleanup — missing permissions are the primary goal.

### Step 2: Classify and Recommend

For each uncovered command from Step 1 output:

1. **Classify** as GREEN / YELLOW / RED per table above
2. **Generate permission pattern**: normalize to `Bash(base_command *)` format
   (use SPACE before `*`, NOT colon — `:*` is deprecated)
   - `mkdir -p` (94x) → `Bash(mkdir *)`
   - `mise exec` (39x) → `Bash(mise *)`
   - `tail -5` (20x) → `Bash(tail *)`
3. **Check for redundancy**: skip if a broader existing pattern covers it
4. **Also scan for garbage** in current settings: `Bash(done)`, `Bash(fi)`,
   `Bash(__NEW_LINE_*)`, partial heredocs, entries covered by broader patterns
5. **Fix deprecated `:*` patterns** — replace any `Bash(name:*)` with `Bash(name *)`
   (space before `*`). The `:*` suffix is deprecated and may not match reliably

Present a combined table:

```
## Permission Recommendations (last N days)

### ADD — Missing permissions (from session scan)
| Pattern to Add | Times Used | Risk | Example |
|...

### REMOVE — Redundant/garbage entries
| Entry | Reason |
|...

### RED — Require manual approval (not adding)
| Command | Count | Risk |
|...
```

### Step 3: Interactive Triage (unless `--dry-run`)

Walk through findings interactively using `AskUserQuestion`. Present items
in batches by risk level, starting with GREEN (safest):

**Batch 1 — GREEN items** (read-only, tests, safe tools):
Use `AskUserQuestion` with options:

- "Add all GREEN" — approve entire batch
- "Pick individually" — show each one for yes/no
- "Skip GREEN" — move to YELLOW

**Batch 2 — YELLOW items** (write ops, need caution):
Always show individually — one `AskUserQuestion` per item with options:

- "Add" — include in settings
- "Skip" — keep requiring manual approval
- "Customize" — let user edit the pattern before adding

**Batch 3 — REMOVE candidates** (garbage/redundant):
Use `AskUserQuestion` with options:

- "Remove all" — clean up entire batch
- "Pick individually" — show each for yes/no
- "Keep all" — skip cleanup

Track approved items in a list. After triage, show final summary of
what will be added/removed and ask for confirmation.

### Step 4: Apply

Merge approved additions into `~/.claude/settings.json` under `permissions.allow`.
Remove approved garbage entries. Report final counts.

### Workflow-artifact permissions (always check)

The plugin's workflow writes to `.claude/plans/`, `.claude/solutions/`, and
`.claude/reviews/`. If these aren't covered, `/phx:compound` and review agents
get write-blocked mid-workflow. Recommend (GREEN):
`Write(.claude/plans/**)`, `Write(.claude/solutions/**)`, `Write(.claude/reviews/**)`.

## References

- `${CLAUDE_SKILL_DIR}/references/risk-classification.md` — Full classification rules
- `${CLAUDE_SKILL_DIR}/references/settings-format.md` — Permission pattern format

## Related

Long mix output flooding context? `/phx:mix-compression` installs rtk filters
that compress `mix test/credo/dialyzer/compile` output before it reaches the
transcript (5-15% token savings on mix-heavy sessions).

Excerpt, first 5,122 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-18
   ✓SAFE B 89 / 100

   first audit · source 492f17636999

Questions about Permissions

• github.com/oliver-kriska/claude-elixir-phoenix/tree/main/plugins — the audited source at commit 492f17636999 and every finding aboveObserved · 18 Oct 2026

Spotted something wrong? Report a correction · Methodology