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/angrysky56/local-repl-mcp/local-repl-cli-skillnpx skills add angrysky56/local-repl-mcp --skill local-repl-cli-skillgit clone --depth 1 https://github.com/angrysky56/local-repl-mcpWrote 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/angrysky56/local-repl-mcp/local-repl-cli-skill)<a href="https://agentmods.dev/skills/angrysky56/local-repl-mcp/local-repl-cli-skill"><img src="https://agentmods.dev/badge/skills/angrysky56/local-repl-mcp/local-repl-cli-skill.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 | $0.00150 | $0.02188 |
| Opus 5 | $0.00075 | $0.01094 |
| Sonnet 5 | $0.00030 | $0.00438 |
| Haiku 4.5 | $0.00015 | $0.00219 |
Grade A, and why
local-repl-cli 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 5d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
local-repl-cli: efficient shell orchestration via LocalREPL
This skill turns the LocalREPL shell bridge into a disciplined CLI orchestration layer. The tools themselves (ripgrep, fd, ast-grep, jq, tokei, delta, hyperfine, watchexec, just) are widely known; the value of this skill is knowing which one to reach for, what flags produce agent-friendly output, and which failure modes bite specifically in the MCP subprocess environment.
Read one of the reference files when you need depth:
reference/recipes.md— copy-paste multi-tool pipelines (codebase-first-touch, safe-refactor, benchmarking, reactive test loops)reference/ast-grep-patterns.md— correct pattern syntax with worked examples and anti-patternsreference/gotchas.md— environment quirks (sh vs bash, PATH inheritance, MCP JSON-string coercion, ripgrep stdin heuristic)
Prerequisites
These tools must be on $PATH. If a verify fails, the tool is missing — stop and ask the user to install it per ~/Repositories/ai_workspace/local-repl-mcp/README.md:
rg jq fd bat sd yq tokei eza dust procs delta hyperfine watchexec ast-grep just
Verify quickly: run_shell("for c in rg jq fd bat sd yq tokei eza dust procs delta hyperfine watchexec ast-grep just; do command -v $c >/dev/null && echo OK: $c || echo MISS: $c; done", repl_id, use_shell=True). For a fuller report with per-tool install hints, run bash scripts/check_tools.sh from the skill directory.
Core principles
1. Count before you enumerate
Before asking for contents, ask for a count. This is the single highest-leverage habit for token efficiency. A 30-second scan that dumps thousands of lines into context can almost always be replaced by a 20ms count that tells you whether the question is even worth pursuing.
Example from a real session: rg -c "def " --type py against a whole repo hung for 60 seconds and returned zero useful output. The scoped version rg -c "def " --type py local_repl/ returned per-file counts in 20ms. Even better, tokei --output json | jq '.Python.code' returned the single aggregate number in 7ms.
What ships with it
4 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.
- 5d ago First seen · 127 lines · 150 tokens per session scan A 0ce723b28446
local-repl-cli is a skill published in the GitHub repository angrysky56/local-repl-mcp (4 stars, last pushed 3mo ago), licensed MIT. It adds 150 tokens to every session and 2,188 once invoked, about $0.0007 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
voicemode
Voice interaction for Claude Code. Use when users mention voice mode, speak, talk, converse, voice status, or voice troubleshooting.
help-flow
Help about Rosetta: explains capabilities and usage.
external-lib-flow
Workflow for onboarding an external private library so AI can use it without source access.
memora
Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.
specimen-authoring
Workflow and hard-won TD patterns for authoring Embody Specimens (the transparent TDXN gallery networks). Load before building or persisting a Specimen.
externalize-operator
MUST READ before calling externalizeop or saveexternalization. Required workflow steps.