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 skills add oliver-kriska/claude-elixir-phoenix --skill phx-permissionsgit clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenixWrote 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/skills/oliver-kriska/claude-elixir-phoenix/phx-permissions)<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/phx-permissions"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/phx-permissions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/phx-permissions"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/phx-permissions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.01287 |
| Opus 5 | $0.00019 | $0.00643 |
| Sonnet 5 | $0.00008 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade D, and why
phx-permissions scanned grade D with 4 findings 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
1. **NEVER auto-allow RED** — `rm`, `sudo`, `kill`, `curl|sh`, `mix ecto.reset`, `git push --force`, `chmod 777` Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Merge approved additions into `~/.claude/settings.json` under `permissions.allow`. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| RED | `rm -rf`, `sudo`, `kill`, `curl|sh`,`mix ecto.reset/drop`,`git push --force`,`git reset --hard` | Never recommend | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **NEVER auto-allow RED** — `rm`, `sudo`, `kill`, `curl|sh`, `mix ecto.reset`, `git push --force`, `chmod 777` This is a copy
89% identical to permissions — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- NEVER auto-allow RED —
rm,sudo,kill,curl|sh,mix ecto.reset,git push --force,chmod 777 - Evidence-based only — Only recommend commands actually approved in sessions
- Show before writing — Present full diff, get explicit confirmation
- 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` |
Workflow
Step 1: Extract Bash Commands from Session JSONL Files
Run the extraction script from 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.
IMPORTANT: Run this FIRST. Do NOT skip to settings cleanup.
Step 2: Classify and Recommend
For each uncovered command from Step 1 output:
- Classify as GREEN / YELLOW / RED per table above
- 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 *)
- Check for redundancy: skip if a broader existing pattern covers it
- Also scan for garbage in current settings:
Bash(done),Bash(fi),Bash(__NEW_LINE_*), partial heredocs, entries covered by broader patterns - Fix deprecated
:*patterns — replace anyBash(name:*)withBash(name *)(space before*). The:*suffix is deprecated and may not match reliably
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 134 lines · 39 tokens per session scan D 275a0fdf5da8
phx-permissions is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (542 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 1,287 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 4 findings (asks for root, reads agent configuration directories, recursive force delete). It is 89% identical to permissions, differing in 20 lines, and is treated as a copy.
Other skills, from other repositories
craftcms
Craft CMS 5 plugin and module development — extending Craft with PHP. Covers elements, element queries, services, models, records, controllers, migrations, queue jobs, console commands, field types, native fields, events, behaviors, Twig extensions, widgets, filesystems, permissions, project config, GraphQL, testing…
craft-php-guidelines
Craft CMS 5 PHP coding standards and conventions. ALWAYS load when writing, editing, reviewing, or discussing any PHP in a Craft plugin or module — even small edits. Also when running ECS, PHPStan, or scaffolding with ddev craft make. Covers: PHPDoc blocks (@author, @since, @throws chains), section headers…
craft-pest
Testing Craft CMS 5 plugins and modules with Pest — test isolation, database safety, and the markhuot/craft-pest-core harness. ALWAYS load when writing, running, fixing, or reviewing tests for a Craft plugin or module, and whenever a suite touches a real Craft install. Covers why rollback is opt-in, tests/Pest.php +…
milp-modeling-gurobi
When the user wants to build, solve, and debug mixed-integer linear programs in Python with Gurobi — creating variables, writing constraint-builder functions, setting objectives and parameters, handling solver status, and extracting solutions safely. Also use when the user mentions "gurobipy," "build a MIP model,"…
numpy-vectorization-for-optimization
When the user wants to remove slow Python loops from metaheuristic or optimization code using NumPy — population-level operations, batch fitness evaluation, distance matrices, broadcasting, argsort/argpartition idioms, defaultrng, and memory layout. Also use when the user mentions "vectorize," "numpy broadcasting,"…
odoo-js
Use when writing, reviewing, or migrating any JavaScript, OWL component, QWeb/OWL template, or SCSS under static/src in an Odoo module — POS overrides, backend widgets, website/public widgets, services. Carries PSAE review-derived principles for OWL correctness, the patch() discipline, template conventions, frontend…