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 leifericf/agentic-sdk --skill write-elixirgit clone --depth 1 https://github.com/leifericf/agentic-sdkWrote 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/leifericf/agentic-sdk/write-elixir)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/write-elixir"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/write-elixir.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 | $0.00050 | $0.01574 |
| Opus 5 | $0.00025 | $0.00787 |
| Sonnet 5 | $0.00010 | $0.00315 |
| Haiku 4.5 | $0.00005 | $0.00157 |
Grade A, and why
write-elixir 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-elixir
Write Elixir for the project. The standard is
skills/write-elixir/references/elixir-style.md (read it first). The
architecture it implements is Functional Core / Imperative Shell; the
Elixir expression of that split, and the native boundary contract, live
in skills/shared/references/architecture.md. Placement follows the
module map (the :architecture :modules entry in the descriptor). The
why behind the constraints is the ADR log: scan it before designing
against an unexplained rule.
The Elixir expression of the split maps cleanly onto OTP. The pure core
is pure functions in modules: they take data (maps, structs, tuples) and
return data, do no IO, send no messages, hold no state. Pattern matching
and the immutability guarantee do the work the GC does in C and the
allocator does in Zig. The imperative shell is GenServers and OTP:
processes that hold state, receive messages, talk to the disk and the
network. The shell calls the pure core from inside handle_call,
handle_cast, and handle_info, and applies the return as the new
process state plus any side effects.
Procedure
- Place it. Find the owning module from the module map. Pure logic goes in a plain module of functions; a process that holds state, receives messages, or touches the world goes in a GenServer (or the fitting OTP behaviour) under the shell. A function that needs a PID to make sense does not belong in the core.
- Elixir discipline. The load-bearing rules:
- Pure core has no process identity. A core function does not know the PID it runs in; it does not send or receive, it does not read or write the process dictionary, it does not consult the clock. Testing the core is calling it: data in, data out, no setup ceremony.
- GenServer and OTP are the shell. State, timers, IO, and messaging live in GenServers, Agents, Tasks, and the supervisors that own them. The shell calls the core from a callback and applies the return: the new state from the pure result, the side effects the result describes. The shell carries no logic of its own; it switches on the tagged tuple the core returns.
- Supervision trees own lifecycle. The shell is a tree of supervisors and workers; the restart strategy (one_for_one, one_for_all, rest_for_one) is explicit and chosen for what a crash invalidates. Pure functions never start or stop processes. A worker and its supervisor land together; a worker without a place in the tree is incomplete.
- Errors as tagged tuples in the core; let-it-crash at the edge.
The core returns
{:ok, value}or{:error, reason}tuples a caller branches on withwith; it does not raise. The shell raises on programmer error and lets the supervisor restart on runtime failure, because the supervision tree is the recovery strategy. - NIF boundary discipline. When a NIF calls C or Zig, the native
boundary contract in
skills/shared/references/architecture.mdapplies unchanged: data in, data out, opaque handles, explicit lifetime, errors as values. A NIF is the shell of last resort: only when the BEAM cannot meet the requirement, never as a default. A NIF that blocks the scheduler runs dirty, and that decision is written down next to the loader.
- Failure model. The core returns tagged tuples for expected failure and raises only for programmer error (a violated precondition the caller controls). The shell trusts the supervision tree for runtime failure: a crashed worker restarts into a known-good state, and the tree's restart intensity bounds a crash loop. Untrusted input (bytes from the network or disk, a payload that crosses the NIF edge) is validated before it reaches the core and rejected as data when malformed.
- Verify like the lanes. The project's cheap lanes from the
descriptor:
mix format --check-formatted,mix compile --warnings-as-errors,mix test. For NIF or native-edge code, run the integration lane that builds the native side, loads it, and calls it with both a known-good and a malformed input. If you wrote process or supervision code, run the suite that starts the tree and tears it down, so a leak or a missing child fails the test.
What ships with it
1 file 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.
- 4d ago First seen · 123 lines · 50 tokens per session scan A 424ff144da04
write-elixir is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 1,574 once invoked, about $0.0003 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.