loomweave-workflow

A codebase map that records functions, classes, files, imports, callers, and related structures, and makes them searchable through MCP. MCP is a standard way for an AI agent to use external tools.

In plain words
What is it for?
Use it to find where a symbol is defined, what calls it, what it depends on, which classes relate to it, or which subsystem contains it.
Why use it?
It helps answer structural questions in an unfamiliar or large codebase without repeatedly searching many files. It is not intended for editing code or reading full implementation details.

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/foundryside-dev/plainweave/loomweave-workflow
Any agent
npx skills add foundryside-dev/plainweave --skill loomweave-workflow
Clone the repo
git clone --depth 1 https://github.com/foundryside-dev/plainweave

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,695 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 $0.00104 $0.08695
Opus 5 $0.00052 $0.04347
Sonnet 5 $0.00021 $0.01739
Haiku 4.5 $0.00010 $0.00869

Measured yesterday against content hash 1075ef8c8551, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loomweave-workflow 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 yesterday.

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.

.agents/skills/loomweave-workflow/SKILL.md · 520 lines

How it starts

The opening of the file, as written. The whole thing — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loomweave Workflow

Overview

Loomweave pre-extracts a codebase into a queryable map — entities (functions, classes, modules, files), the call/reference/import edges between them, the relation edges (inherits_from/decorates/implements/derives), and subsystem clusters — and serves it over MCP. Ask Loomweave instead of re-exploring the tree. One entity_find + one entity_callers_list answers "what calls this?" — and one entity_relation_list answers "what subclasses this?" — without reading a single file.

When to use

  • You're dropped into a codebase and need to locate a symbol or trace its callers/callees.
  • You'd otherwise grep/read many files to answer a structural question.
  • You need a function's neighborhood, execution paths, or which subsystem it belongs to.

Not for: editing code, reading exact implementation bodies (use entity_summary_get or read the file once you have its path), or codebases with no .weft/loomweave/ index.

Entity IDs — the model

Every entity has an ID: {plugin}:{kind}:{qualified_name} (e.g. python:function:pkg.mod.func, python:class:pkg.mod.Cls, python:module:pkg.mod). Subsystems are core:subsystem:{hash}.

You almost never type IDs. Get one from entity_find / entity_at, then copy it verbatim into the next tool. Don't hand-construct or guess IDs.

id vs sei — which one to bind on

Every entity in a tool response now carries an sei field alongside its id. They are not interchangeable:

  • id is the entity's locator — a mutable address. It changes when the code is renamed or moved, and it's the right thing to feed into the next Loomweave tool call (above).
  • sei is the entity's durable, stable identity. It survives renames and moves. When you record a cross-tool binding — e.g. attaching a Filigree issue to a Loomweave entity — bind on the sei, not the id. A binding keyed on the mutable id silently breaks the first time the entity moves.

Read the full file on GitHub · 520 lines

Files

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.

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. yesterday First seen · 520 lines · 104 tokens per session scan A 1075ef8c8551

Subscribe to this mod's changes

loomweave-workflow is a skill published in the GitHub repository foundryside-dev/plainweave (0 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 8,695 once invoked, about $0.0005 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