develop-at-repl

A development method based on an interactive programming session: write a small piece of code, run it, inspect the result, and adjust it. It covers tools such as nREPL for Clojure and IEx for Elixir, plus quick test harnesses for C and Zig.

In plain words
What is it for?
Use it to develop and reload code in a live session, evaluate small forms, and run short harnesses when the project has no interactive session.
Why use it?
It provides quick feedback while code is being shaped, so problems can be found without repeatedly restarting the whole development setup.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/leifericf/agentic-sdk/develop-at-repl
Any agent
npx skills add leifericf/agentic-sdk --skill develop-at-repl
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,476 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01476
Opus 5 $0.00016 $0.00738
Sonnet 5 $0.00007 $0.00295
Haiku 4.5 $0.00003 $0.00148

Measured 2d ago against content hash ae8cfd0331e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

develop-at-repl 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 2d 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.

skills/develop-at-repl/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

develop-at-repl

The interactive eval loop is the primary development rhythm, not a debugging aside. Write a form, evaluate it, read the returned value, adjust: data in, data out, no setup ceremony. Batch test runs are the exception, reached for at landing boundaries (see "When to leave the loop"), not the rhythm.

The host depends on the language: nREPL for Clojure, IEx for Elixir. C and Zig have no eval loop; their fast inner cycle is a small throwaway harness built and run in seconds (see run-spike). The code standard is the relevant write-<lang> recipe; the boundary contract is references/architecture.md; the module layout and dev loop live in the descriptor's module map.

Connect once

Start the host (nREPL, IEx) and attach the editor's client. One long-lived session; do not restart it per change. The running image is the unit of work. Require the namespace you are shaping; reload it (:reload, IEx recompile, or a fresh harness run) after edits to a dependency.

If the project has no live host yet (a C or Zig unit, or a Clojure or Elixir project before the dev alias is wired), say so and fall back to reasoning over the source plus a fast harness. Do not fabricate a running image.

Procedure

  1. Evaluate one small form. Send the smallest form that answers the next question: a constructor call, a query against a literal input, a pure transform over a hand-built value. Read the returned value.
  2. Inspect the data, do not re-run a suite. The pure core takes data and returns data; the answer is the value at the prompt. Drill with the host's tools (pretty-print on a deep structure, an inspector tap, keys and get-in, or a harness printf). Do not boot the whole application to see one function's output.
  3. Adjust and re-evaluate. Edit the form or the source, re-eval, read again. The cycle is seconds, not a test-suite wait. Let the shape of the data drive the next form.

Hold the loop to pure data wherever the work allows. The pure core is built for this: no clock, no atom, no IO, so a literal input fully determines the output and the value at the prompt is the whole truth.

Read the full file on GitHub · 136 lines

Changes

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.

  1. 2d ago First seen · 136 lines · 33 tokens per session scan A ae8cfd0331e6

Subscribe to this mod's changes

develop-at-repl is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 33 tokens to every session and 1,476 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

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.

microsoft/vscode · 62 tokens