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-workgit 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-work)<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/phx-work"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/phx-work.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 65 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Excessive Agency · line 38 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00043 | $0.02015 |
| Opus 5 | $0.00022 | $0.01007 |
| Sonnet 5 | $0.00009 | $0.00403 |
| Haiku 4.5 | $0.00004 | $0.00201 |
Grade A, and why
phx-work scanned grade A with 0 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 5d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work
Execute tasks from a plan file with checkpoint tracking and verification.
Usage
phx-work .claude/plans/user-auth/plan.md
phx-work .claude/plans/user-auth/plan.md --from P2-T3
phx-work --skip-blockers
phx-work # Resumes most recent plan
Arguments
<plan-file>-- Path to plan file (optional, auto-detects recent)--from <task-id>-- Resume from specific task (e.g.,P2-T3)--skip-blockers-- Continue past blocked tasks--continue-- Resume IN_PROGRESS plan from checkboxes
Iron Laws (NON-NEGOTIABLE)
- NEVER auto-proceed to phx-review or any next workflow phase -- always ask the user what to do next
- AUTO-CONTINUE between plan phases -- when Phase N completes, immediately start Phase N+1. Do NOT stop or ask for permission between phases. Only stop at BLOCKERS or when ALL phases are done.
- Plan checkboxes ARE the state --
[x]= done;[ ]= pending unless the row is visibly tagged[BLOCKED]. No separate JSON state files. Resume by reading the plan. - Verify after EVERY task -- never skip verification
- Max 3 retries then BLOCKER -- don't keep retrying forever
- Stage specific files -- never use
git add -Aorgit add . - Read scratchpad BEFORE implementing -- scratchpad has dead-ends and decisions that prevent rework. Step 2 is not optional.
- Clarify ambiguous tasks -- ask the user rather than guessing when a plan task's intent is unclear
Step 1: Research Decision
Ask the user for plans with >3 tasks:
This plan has {count} remaining tasks across {count} phases.
- Start working -- Begin immediately (familiar patterns)
- Quick research -- Read source files first (~10 min)
- Extensive research -- Web search + docs (~30 min)
Skip for plans with 3 or fewer simple tasks -- just start.
Split warning: Plans with >10 tasks risk 2-3 context compactions. Suggest splitting via
phx-planif not already.
Step 2: Check Context (MANDATORY)
What ships with it
5 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.
- 5d ago First seen · 182 lines · 43 tokens per session scan A ba15c7b63039
phx-work is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (541 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 2,015 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
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 +…
cige-test-authoring
Use this skill when writing, reviewing, or refactoring AI agent test cases. It enforces the CIGE standard — a structured format that separates stable test intent from adaptive execution, enabling self-healing agentic tests.
cige-failure-classification
Use this skill immediately after any CIGE test run completes — pass or fail — and before any repair action is taken. It classifies the outcome and names which skill, if any, is allowed to act on it. Classification is not optional and not skippable: no agent may repair a test it has not been dispatched to.
solution-validation-testing
When the user wants to verify optimization code: independent feasibility checkers, objective recomputation separate from the solver, unit tests for constraint builders and operators, known-optimum regression tests, and exact-vs-heuristic cross-validation on small instances. Also use when the user mentions "validate…
cige-product-defect-escalation
Invoked by cige-failure-classification when a run is classified as a Product Defect: execution reached the system under test, the environment is healthy, execution steps are current — but the outcome does not match Intent.
cige-stale-execution-repair
Invoked by cige-failure-classification in two situations: Outdated Test Logic (Mode A — repair Execution[]) and a confirmed False Positive (Mode B — strengthen Guardrails). These are different repairs with different targets; do not conflate them.