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 agentmods add skills/mkreyman/bmad-elixir/elixir-disciplinenpx skills add mkreyman/bmad-elixir --skill elixir-disciplinegit 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-discipline)<a href="https://agentmods.dev/skills/mkreyman/bmad-elixir/elixir-discipline"><img src="https://agentmods.dev/badge/skills/mkreyman/bmad-elixir/elixir-discipline.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.01088 |
| Opus 5 | $0.00019 | $0.00544 |
| Sonnet 5 | $0.00008 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
elixir-discipline 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 4d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elixir Discipline: Mandatory Skill Enforcement
ABSOLUTE REQUIREMENT
Before you respond to ANY request about Elixir/Phoenix code, you MUST complete this checklist.
This is NOT optional. This is NOT negotiable. You CANNOT rationalize your way out of this.
PRE-RESPONSE CHECKLIST
STOP. Before typing ANY response, ask yourself:
-
Is this about implementing a feature or fixing a bug? → USE
elixir-tdd-enforcementskill FIRST → NO CODE without failing test first -
Is this about debugging an error or issue? → USE
elixir-root-cause-onlyskill → NO quick fixes, trace to root cause first -
Did I claim something works? → USE
elixir-verification-gateskill → Run the actual command, read actual output -
Am I about to modify an ignore file (dialyzer.ignore, .credo.exs exclude)? → STOP IMMEDIATELY → USE
elixir-no-shortcutsskill → Fix the real problem -
Am I creating placeholder code or default values for required data? → STOP IMMEDIATELY → USE
elixir-no-placeholdersskill → Fail loud, fail fast, no silent failures -
Am I proposing to "just try" something? → STOP → Use systematic debugging instead
IF A SKILL APPLIES, YOU MUST USE IT
This means:
- Announce which skill you're using
- Follow it EXACTLY
- Do not skip steps
- Do not modify the process
IF YOU SKIP A SKILL WHEN IT APPLIES = TASK FAILURE
RATIONALIZATIONS THAT ARE WRONG
"This is just a simple question"
WRONG. Check the skills list anyway.
"I remember this skill, I don't need to read it"
WRONG. Read it every time. The details matter.
"The skill probably doesn't apply here"
WRONG. If there's even a 1% chance it applies, you MUST read it.
"I'll just do this quickly"
WRONG. Quick usually means wrong. Use the appropriate skill.
"The user just wants a simple answer"
WRONG. The user wants a CORRECT answer. Use skills to ensure correctness.
"This would take too long"
WRONG. Doing it wrong takes longer. Use the skills.
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.
- 4d ago First seen · 140 lines · 38 tokens per session scan A 10e90dd830cf
elixir-discipline is a skill published in the GitHub repository mkreyman/bmad-elixir (10 stars, last pushed 10mo ago), licensed MIT. It adds 38 tokens to every session and 1,088 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…