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 investigategit 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/investigate)<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/investigate"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/investigate/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/investigate"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/investigate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01373 |
| Opus 5.5 | $0.00020 | $0.00549 |
| Sonnet 5.5 | $0.00010 | $0.00275 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
investigate 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 26d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate Bug
Investigate bugs using the Ralph Wiggum approach: check the obvious, read errors literally.
Usage
/phx:investigate Users can't log in after password reset
/phx:investigate FunctionClauseError in UserController.show
/phx:investigate Complex auth bug --parallel
Arguments
$ARGUMENTS = Bug description or error message. Add --parallel
for deep 4-track investigation.
Mode Selection
Use parallel mode (spawn deep-bug-investigator) when:
bug mentions 3+ modules, spans multiple contexts, is intermittent
or involves concurrency, or user says --parallel/deep.
Before spawning it, determine the effective maximum nesting depth. Use an
explicit positive-integer CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH value first;
when it is unset, inspect claude --version (the default is 1 in 2.1.217–2.1.218
and 3 in 2.1.219+). If the version is unavailable, conservatively use 1. At
depth 3+, use the deep-bug-investigator orchestrator. At depth 1 or 2, keep
orchestration in this main session: spawn the four
focused tracks (reproduction, root cause, impact, fix strategy) directly in
one parallel batch, wait for all four, then synthesize their evidence. Never
spawn an orchestrator that cannot delegate.
Otherwise: Run the sequential workflow below.
Avoid confirmatory subagents: once Steps 3-4 identify the root cause with high confidence, present it directly — four subagents (~80K tokens) re-verifying a finding already made in this context add cost, not evidence.
Iron Laws
- Read the error message literally first — Most bugs tell you exactly what's wrong; resist the urge to theorize before reading what the system is saying
- Check the obvious before going deep — Compile errors, missing migrations, atom/string mismatches explain 80% of bugs; exhausting the Ralph Wiggum checklist saves hours
- Check changeset errors before UI debugging — Silent form saves are almost always
{:error, changeset}with validation failures, not viewport or JS issues - Consult compound docs before investigating fresh — A previously solved problem saves the entire investigation cycle; always search
.claude/solutions/first - NEVER guess at a fix before reproducing — Reproduce first, then identify root cause, then fix. Skipping steps causes wrong fixes
- DO NOT apply a fix without confirming root cause — Verify your hypothesis with evidence (logs, tests, IO.inspect) before changing code
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.
- 26d ago Changed · -1 lines 0cca36282769
- 1mo ago Changed · +11 tokens per session 450ab76aa0c6
- 1mo ago First seen · 139 lines · 40 tokens per session scan A fe90414d6672
investigate is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (570 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 1,373 once invoked, about $0.0002 per session on Opus 5.5. 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
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
bug-investigate
Use when someone wants to know WHY something is broken and has not asked for it to be fixed — "why is this happening", "what's causing this error", "find out what's wrong", "diagnose this before we decide". Also use before committing to a fix, when the cause is unknown and the decision depends on it. Not for fixing …
gurobi-advanced-features
When the user wants to use Gurobi beyond plain model building — callbacks for lazy constraints, user cuts, heuristic solution injection, and early termination; IIS computation for diagnosing an infeasible model; the solution pool; the multi-objective API; the matrix API (addMVar/addMConstr); MIP starts; and parameter…
audit-ppmplugin
Statically audit a built .ppmplugin before wrap testing. Checks archive layout, manifest compatibility, bundle consistency, Android DEX integrity and SDK leakage, iOS framework structure, native source-to-receiver alignment, and the PCF composite-key/sendAsync transport contract. Reports CRITICAL, WARNING, and INFO…
debug-extension
Diagnose and fix failures in a built third-party .ppmplugin control: crashes, silent no-ops, PCF error outputs, or incorrect behavior. Uses the reported symptom, shared/error-codes.md, and file-level evidence to trace the manifest, Android/iOS modules, PCF dispatch, and build configuration. Produces a ranked…
shiny-py-optimize
Diagnose and fix performance problems in Shiny for Python apps — slow startup, sluggish interactions, blocking operations, and apps that struggle beyond a handful of concurrent users. Use when a Shiny for Python app is slow, hangs, recomputes too much, times out, or must support more users; when the user asks to…