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 mkreyman/bmad-elixir --skill elixir-no-shortcutsgit clone --depth 1 https://github.com/mkreyman/bmad-elixirWrote 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/mkreyman/bmad-elixir/elixir-no-shortcuts)<a href="https://agentmods.dev/skills/mkreyman/bmad-elixir/elixir-no-shortcuts"><img src="https://agentmods.dev/badge/skills/mkreyman/bmad-elixir/elixir-no-shortcuts/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/mkreyman/bmad-elixir/elixir-no-shortcuts"><img src="https://agentmods.dev/badge/skills/mkreyman/bmad-elixir/elixir-no-shortcuts.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 | $0.00042 | $0.02679 |
| Opus 5.5 | $0.00017 | $0.01072 |
| Sonnet 5.5 | $0.00008 | $0.00536 |
| Haiku 4.5 | $0.00004 | $0.00268 |
Grade A, and why
elixir-no-shortcuts 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 2mo 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elixir No Shortcuts: Fix the Real Problem
THE IRON LAW
NEVER suppress errors. ALWAYS fix the root cause.
ABSOLUTE PROHIBITIONS
You are NEVER allowed to:
-
Add to dialyzer.ignore
- Not for "unknown function" errors
- Not for "pattern can never match" warnings
- Not for "no local return" issues
- Not even "temporarily"
-
Modify .credo.exs to disable checks
- Not adding to
disabled:list - Not adding to
excluded_paths: - Not using inline
# credo:disable-for-this-file - Not raising complexity limits
- Not adding to
-
Suppress compiler warnings
- Not with
@compile {:no_warn_undefined, Module} - Not with
# noqastyle comments - Not by removing
--warnings-as-errors
- Not with
-
Modify .gitignore to hide problems
- Not to hide accidentally created files
- Not to ignore build artifacts in wrong places
- Fix the process that created them
-
Comment out failing tests
- Not "just for now"
- Not "until we figure it out"
- Fix the test or fix the code
-
Skip quality checks
- Not removing from pre-commit hook
- Not skipping with
--no-verify - Not disabling in CI/CD
INSTEAD: FIX THE ACTUAL PROBLEM
Dialyzer Errors
When Dialyzer complains:
# BAD: Adding to dialyzer.ignore
# dialyzer.ignore
lib/my_app/accounts.ex:42:pattern_can_never_match
# GOOD: Fix with proper @spec
defmodule MyApp.Accounts do
@spec get_user(integer()) :: {:ok, User.t()} | {:error, :not_found}
def get_user(id) do
case Repo.get(User, id) do
nil -> {:error, :not_found}
user -> {:ok, user}
end
end
end
Common Dialyzer fixes:
- Unknown function - Add @spec or import the module
- Pattern can never match - Fix the actual pattern mismatch
- No local return - Add error handling paths
- Invalid type specification - Correct the @spec to match reality
Process:
- Read the full Dialyzer error (don't just scan it)
- Understand what Dialyzer is telling you
- Add @spec that matches what the function actually does
- If function behavior is wrong, fix the function
- Run
mix dialyzeragain to verify
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.
- 2mo ago First seen · 343 lines · 42 tokens per session scan A 0e06941bd3f9
elixir-no-shortcuts is a skill published in the GitHub repository mkreyman/bmad-elixir (11 stars, last pushed 1y ago), licensed MIT. It adds 42 tokens to every session and 2,679 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 2026-08-31.
elixir-no-shortcuts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| elixir-no-shortcutsmkreyman/bmad-elixir | Skill | 11 | 1y ago | MIT | A | 42 | Claude Code, Codex |
| dotnet-reversezhaoxuya520/reverse-skill | Skill | 45k | yesterday | MIT | A | 144 | Claude Code |
| dart-run-static-analysisflutter/agent-plugins | Skill | 3.2k | 4d ago | BSD-3-Clause | A | 43 | Claude Code |
| agents-sdk-dotnet-debuggingmicrosoft/Agents | Skill | 1.1k | 2d ago | MIT | A | 136 | Claude Code |
| memory-optimizationbenchflow-ai/skillsbench | Skill | 1.9k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| golang-error-handlingsamber/cc-skills-golang | Skill | 3.9k | 7d ago | MIT | A | 144 | Claude Code |
| prismer-python-debugpyPrismer-AI/PrismerCloud | Skill | 1.4k | 25d ago | MIT | A | 19 | Claude Code, Codex |