WORKFLOW

A set of working rules for coding agents inside the Clew project. It tells agents how to protect the product’s identity and architecture while making changes.

In plain words
What is it for?
Guiding code, product-interface, provider, and documentation work. It helps agents choose what to read, what to preserve, how to implement changes, and how to verify them.
Why use it?
It reduces changes that technically work but weaken the product, its trustworthiness, or its underlying design. It also keeps checks and explanations tied to the affected area.

Agent

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 agents/miuuyy/clew/workflow
Clone the repo
git clone --depth 1 https://github.com/miuuyy/Clew
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 318 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 $0.00000 $0.00318
Opus 5 $0.00000 $0.00159
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 2d ago against content hash 310a03921394, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

docs/agents/WORKFLOW.md · 58 lines

What it actually says

Agent Workflow

This file describes how coding agents should work inside Clew.

Primary rule

Protect product truth first.

If a change makes the codebase easier to grow but weakens the product identity, trust surface, or architecture invariants, it is the wrong change.

Implementation workflow

  1. Read the latest request carefully.
  2. Read only the docs and code needed for that request.
  3. Identify the product or architecture invariant that matters.
  4. Implement the change without hidden fallback behavior.
  5. Run targeted verification.
  6. Explain the result in product terms, not only code terms.

Agent behavior rules

For product and UI work

  • keep the graph central
  • prefer high-signal UI over generic chrome
  • avoid admin-panel drift

For agent and provider work

  • trust the selected model as the decision engine
  • improve role, context, schema, or validation
  • do not add keyword routers or semantic overrides

For docs work

  • explain what the repo or product is for quickly
  • make onboarding obvious
  • preserve the split between product docs and engineering docs

Verification rule

For code changes, agents should run the checks relevant to the area touched.

Common commands:

cd frontend && npm run typecheck && npm run build
PYTHONPATH=backend ./.venv/bin/python -m unittest discover -s backend/tests -v

Failure rule

If something cannot be implemented cleanly:

  • fail explicitly
  • say what blocks it
  • do not simulate success with a workaround
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 · 58 lines · 0 tokens per session scan A 310a03921394

Subscribe to this mod's changes

WORKFLOW is an agent published in the GitHub repository miuuyy/Clew (163 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 318 tokens. 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.

Related

Other agents, from other repositories

explainer

You are a code explanation specialist focused on teaching and learning. Your role is to analyze any code — AI-generated or legacy — and explain it in a way that helps developers truly understand it, not just accept it.

mohi-devhub/antivibe · 0 tokens

exam-generator

Generates printable exam papers with answer keys in PDF format. Searches for real exam examples online. Triggered by "/generate-exam" command.

hluaguo/learn-faster-kit · 32 tokens

d3-expert

Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data…

andisab/swe-marketplace · 448 tokens

analyst

Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.

kv0906/pm-kit · 32 tokens

note-organizer

Organize and restructure vault notes. Fix broken links, consolidate duplicates, suggest connections, and maintain vault hygiene. Use when managing vault organization or cleaning up notes.

ballred/obsidian-claude-pkm · 36 tokens

canvas-composer

Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas archetypes. Follows the 15-30 visible nodes per viewport principle. Content is scannable: headers, bullets, bold. Max 200 words per text node. Context: /canvas generate needs slide content…

AgriciDaniel/claude-canvas · 125 tokens