A local-first command-line tool for answering questions from a project's stored recipes, specifications, concepts, and indexed documents. It can run offline with a local language model and use a remote AI only as a reviewer.

Use it to ask grounded questions about a repository or local files, search indexed documents, retrieve relevant excerpts, and identify or review gaps in the project's stored knowledge.

It keeps answers tied to the project's own documents instead of relying only on general AI knowledge, and it can work without a network connection.

form-cli — Skill for Claude Code and Codex by seeker71

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.

Any agent

npx skills add seeker71/Coherence-Network --skill form-cli

Clone the repo

git clone --depth 1 https://github.com/seeker71/Coherence-Network

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/seeker71/coherence-network/form-cli/github.svg)](https://agentmods.dev/skills/seeker71/coherence-network/form-cli)

Your own site

<a href="https://agentmods.dev/skills/seeker71/coherence-network/form-cli"><img src="https://agentmods.dev/badge/skills/seeker71/coherence-network/form-cli/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/seeker71/coherence-network/form-cli"><img src="https://agentmods.dev/badge/skills/seeker71/coherence-network/form-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,061 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00204	$0.01061
Opus 5.5	$0.00082	$0.00424
Sonnet 5.5	$0.00041	$0.00212
Haiku 4.5	$0.00020	$0.00106

Measured 1mo ago against content hash 9c21e909b0d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

form-cli scanned grade C with 2 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 1mo 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

"script": "curl -fsSL https://raw.githubusercontent.com/seeker71/Coherence-Network/main/install/form-cli-install.sh | bash",

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"script": "curl -fsSL https://raw.githubusercontent.com/seeker71/Coherence-Network/main/install/form-cli-install.sh | bash",

skills/form-cli/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

form-cli — the one door

form-cli is a local-first, Form-native organism on this Mac. It answers from its own body (recipes, specs, concepts) and any local documents you index, runs fully offline on a local LLM, and treats a remote oracle (Claude, codex, gemini, grok, cursor — whichever you installed) as a reviewer, never a requirement.

When to use this skill: any time the user wants an answer grounded in this repo or in their own local files, wants to work offline, wants to see/close the body's gaps, or wants the body's reasoning reviewed.

Answer a question (grounded, local, offline)

form-cli ask "how does the form-cli route between a local and a remote oracle?"
form-cli ask "what does rag-retrieve.fk do?" -m coder        # pick the local model

ask retrieves the nearest cells (Form-ranked by rag-retrieve.fk) and has a local model answer using only those excerpts, citing the doc ids. No network.

Question local documents

form-cli index --docs ~/Documents/notes --docs ~/projects/spec   # index your folders (once)
form-cli ask "what did my notes say about the Q3 plan?"          # then ask
form-cli search "deadline" -k 8                                  # retrieval only

Indexing embeds each document locally (nomic-embed-text); the index lives at ~/.coherence-network/rag-index/. Re-run index after the docs change.

See and close the body's gaps (offline)

form-cli gaps                                                    # what's open
form-cli close "lcm" "(lcm a b) = a*b / gcd(a,b)" "(lcm 4 6)" 12 "ollama run coder"

A local oracle drafts the missing recipe; the local kernel validates it against the assertion. Nothing leaves the machine.

Review the body's thinking against an oracle

form-cli review 2 "ollama run coder" "ollama run llama3.2:3b" "claude -p" 15

The body answers; an internal judge and the oracle both score the same answer; the Form metric reports how close the internal review is to the oracle's. As the gap closes, the oracle retires.

Read the full file on GitHub · 93 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.

1mo ago First seen · 93 lines · 204 tokens per session scan C 9c21e909b0d0

Subscribe to this mod's changes

form-cli is a skill published in the GitHub repository seeker71/Coherence-Network (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 204 tokens to every session and 1,061 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

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

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

form-cli