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/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-runtime-durability-reviewnpx skills add ccarvalho-eng/codex-elixir-phoenix --skill elixir-phoenix-runtime-durability-reviewgit clone --depth 1 https://github.com/ccarvalho-eng/codex-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/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-runtime-durability-review)<a href="https://agentmods.dev/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-runtime-durability-review"><img src="https://agentmods.dev/badge/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-runtime-durability-review.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 5.1 | $0.00073 | $0.00778 |
| Opus 5 | $0.00036 | $0.00389 |
| Sonnet 5 | $0.00015 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
elixir-phoenix-runtime-durability-review 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 6d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Durability Review
Use this skill for changes that touch state transitions, runtime orchestration, durable execution history, job dispatch, retries, manual intervention, or restart semantics.
Required Output
- Produce an explicit findings list for the final diff, even if empty.
- Classify each finding as
blockingoroptional. - Do not treat green tests as a substitute for the review.
Review Checklist
1. Boundary Audit
- Confirm declarative workflow rules stay separate from runtime orchestration, persistence, and delivery adapters.
- Confirm side effects stay at boundaries and no new hidden coupling was introduced.
- Confirm public APIs return structured errors for stale, missing, or incompatible persisted state.
2. Concurrency And Locking
- Find every unlocked read that chooses a later mutation path.
- Eliminate it, revalidate it under the same lock, or prove it is safe by idempotent design.
- Check duplicate delivery, stale job, and terminal race behavior.
- Check
:noopor already-terminal paths for stranded attempts, step runs, or partial state.
3. Atomic Progression
- Check whether update plus dispatch, update plus retry scheduling, and pause or resume flows are atomic where they need to be.
- Look for crash windows between durable state changes and enqueuing successor work.
- Verify dispatch-failure behavior preserves a coherent run and step history.
4. Persisted Data Drift
- Check whether paused, retrying, delayed, or replayable runs depend on the current code definition when they should depend on persisted decisions.
- Check renamed or removed modules, changed transitions, changed mappings, and older rows missing newer fields.
- Prefer durable metadata plus compatibility fallbacks over recomputing semantics from the live definition.
5. Telemetry And Audit Ordering
- Check ordering between step terminal events, run transitions, and successor dispatch or start.
- Check that every started step has a matching terminal audit or telemetry event.
- Check cancelled, retried, resumed, and dispatch-failure paths for symmetry.
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.
- 6d ago First seen · 72 lines · 73 tokens per session scan A 7394b2ebe3ca
elixir-phoenix-runtime-durability-review is a skill published in the GitHub repository ccarvalho-eng/codex-elixir-phoenix (11 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 778 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
elixir-expert
Expert-level Elixir, Phoenix, OTP, and concurrent systems. Use when the user mentions Phoenix, OTP, Erlang, concurrent, or functional, or when the task involves Elixir Fundamentals or Phoenix Framework.
ash-framework
Use this skill working with Ash Framework or any of its extensions. Always consult this when making any domain changes, features or fixes.
phoenix-framework
Use this skill working with Phoenix Framework. Consult this when working with the web layer, controllers, views, liveviews etc.
phoenix
Use when building an Elixir web app with Phoenix — contexts, Ecto schemas, changesets and migrations, LiveView, channels and PubSub, the generators, and the boundary between domain logic and the web layer. Covers the classic LiveView over-rendering and Ecto N+1 traps. NOT pure OTP work with no web or Ecto layer …
writing-review-packets
Create or revise Reviews packet markdown for a code diff, including section strategy, prose, hunk references, validation, and pushing packet revisions with the Reviews CLI. Use when the user asks to write a review packet, organize a diff for review, add prose around hunk refs, update a packet for a new patchset, or…
code-review
Review code changes for regressions, correctness, and missing tests.