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/iwillig/clojure-system-prompt/clojure-repl-devnpx skills add iwillig/clojure-system-prompt --skill clojure-repl-devgit clone --depth 1 https://github.com/iwillig/clojure-system-promptWhat 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 | $0.00067 | $0.01621 |
| Opus 5 | $0.00034 | $0.00811 |
| Sonnet 5 | $0.00013 | $0.00324 |
| Haiku 4.5 | $0.00007 | $0.00162 |
Grade A, and why
clojure-repl-dev 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.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clojure REPL-Driven Development
Core Workflow
Never write code without REPL validation.
Every coding task follows this loop:
- Gather context
- Take action
- Verify output
Before modifying any file:
- Read existing code - Use
readto examine target file and related files - Verify nREPL connection - Test:
clj-nrepl-eval -p 7889 "(+ 1 1)" - If connection fails, discover ports -
clj-nrepl-eval --discover-ports - Initialize dev environment if available -
clj-nrepl-eval -p 7889 "(fast-dev)" - Explore unfamiliar functions -
clj-nrepl-eval -p 7889 "(clojure.repl/doc function-name)" - Test in REPL - Define and validate functions before saving
- Check edge cases - nil, empty collections, invalid inputs
- Save only after validation - Use
editorwrite - Reload before verifying edits -
clj-nrepl-eval -p 7889 "(require '[project.core] :reload)" - Do not report success before verification - changed functions and relevant tests must pass
If nREPL fails, first run clj-nrepl-eval --discover-ports to find existing servers. Only ask the user to start a server if none are found.
If fast-dev is unavailable, continue without it.
Agent Loop
Use this loop for every coding task:
- Gather context - Read the target file, related code, call sites, dependencies, and tests
- Take action - Make the smallest focused change that solves the task; avoid unrelated refactors
- Verify output - Reload affected namespaces, test changed functions, validate edge cases, and run relevant tests
If verification fails, return to gather/action and fix the problem before reporting success.
Failure Recovery
If REPL evaluation, test execution, or namespace loading fails:
- Read the exact error message
- Isolate the failing expression or function
- Fix the root cause
- Reload affected namespaces
- Rerun verification
If delimiter errors occur, use clj-paren-repair instead of manual repair.
Task Communication
What ships with it
2 files 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.
- 2d ago First seen · 211 lines · 67 tokens per session scan A 98bf834fa1c4
clojure-repl-dev is a skill published in the GitHub repository iwillig/clojure-system-prompt (43 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,621 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…