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 narrow-bare-rescuegit 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/narrow-bare-rescue)<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/narrow-bare-rescue"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/narrow-bare-rescue/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/narrow-bare-rescue"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/narrow-bare-rescue.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 | $0.00040 | $0.01436 |
| Opus 5 | $0.00020 | $0.00718 |
| Sonnet 5 | $0.00008 | $0.00287 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
narrow-bare-rescue 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 8d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narrow Bare Rescue
Turn rescue _ -> fallback into rescue _ in [ExceptionType1, ExceptionType2] -> fallback
so programmer bugs propagate while known failure modes stay handled.
Why this matters
Bare rescues (rescue _ ->, rescue e -> — any form without an in clause) swallow
every exception, including UndefinedFunctionError from typos, KeyError from
misspelled map keys, and CompileError from bad HEEx templates. The symptom isn't a stack
trace — it's a silent {:error, :generic} or a nil fallback. Bugs that should surface
in tests or error reporters become quiet degradations.
The Erlang Secure Coding Guide makes
the same case at the BEAM level — rule LNG-002 ("Do Not Use catch") warns that the
legacy catch-all form conflates normal returns, throws, and errors. Bare rescue in Elixir
is the direct analogue.
Iron Laws
- Never leave
rescue _ ->orrescue e ->without aninclause. Every rescue must list exact exception types. The Credo check enforces this after cleanup lands. - Cover every exception the code path can actually raise. Narrowing that drops a real exception is a behavioral regression — trace each call in the body before committing.
- Never include programmer-bug exceptions in the list.
UndefinedFunctionError,CompileError,BadFunctionError, andBadArityErrormust propagate. - Use
reraise e, __STACKTRACE__, neverreraise e, []. Preserve the original stack trace so Oban retry metadata and error reporters show the real origin. - Run
mix compile --warnings-as-errorsbefore committing. Typos in exception module names only surface at compile time — the code looks fine until it loads.
The core transform
# Before — masks programmer bugs
def parse(body) do
Jason.decode!(body)
rescue
_ -> %{}
end
# After — catches only what can actually fail here
def parse(body) do
Jason.decode!(body)
rescue
_ in [Jason.DecodeError, ArgumentError] -> %{}
end
What ships with it
2 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.
- 8d ago First seen · 143 lines · 40 tokens per session scan A c3f0d92655ea
narrow-bare-rescue is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (544 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,436 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
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 …
cige-product-defect-escalation
Use when cige-failure-classification identifies a Product Defect -- execution reached a healthy system with current steps, but the outcome contradicts Intent. Fetches specRef and buildRef to file a defect or, only with human approval, propose an Intent update.
cige-stale-execution-repair
Use when cige-failure-classification identifies Outdated Test Logic (repair Execution steps, Mode A) or a confirmed False Positive (add a stricter Guardrail, Mode B). Human approval required before committing either kind of repair.
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…
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.