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 agents/miuuyy/clew/project_contextgit clone --depth 1 https://github.com/miuuyy/ClewWhat 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 | $0.00000 | $0.00418 |
| Opus 5 | $0.00000 | $0.00209 |
| Sonnet 5 | $0.00000 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
PROJECT_CONTEXT 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.
What it actually says
Project Context
This file is the shared truth layer for coding agents working on Clew.
One-sentence definition
Clew is a graph-first learning workspace with an AI agent layer for building, auditing, and evolving structured knowledge paths.
Product identity
Clew is not:
- a note app clone
- a checklist app with AI pasted on top
- a silent graph mutator
- a generic autonomous agent platform
Clew is:
- a graph workspace
- with explicit proposal review
- with rollbackable graph state
- with closure logic tied to actual topics
Core decisions
The most important long-lived decisions are:
- graph mutations must be reviewable and reversible
- the frontend stays graph-first instead of dashboard-first
- the public local edition and hosted surface stay separate
See:
Architecture in one screen
Frontend
- graph canvas
- workspace shell
- dialogs and settings
- local debug surfaces
Backend
- repository and snapshots
- chat orchestrator
- planner
- quiz service
- provider seam
Data
- local SQLite workspace
- graph state
- snapshots
- workspace config
- chat and quiz runtime state
Quality bar
Clew should feel like:
- a serious solo product
- a portfolio-grade graph workspace
- a public codebase that is readable and worth contributing to
It should not feel like:
- a prototype with hacks
- a dashboard with a graph widget
- a pile of AI features without a center
Docs split
docs/site_faq/= product-facing docs sourcedocs/= engineering docs
Agents should preserve that split.
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 · 84 lines · 0 tokens per session scan A 2f8178e38734
PROJECT_CONTEXT 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 418 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.
Other agents, from other repositories
brag-spotter
Proactively scans for achievements and wins that aren't in the brag doc yet. Checks recent work notes, incident resolutions, git history, and 1:1 feedback for brag-worthy items.
codex
Codex ist Vincents bevorzugte interaktive Arbeitsoberfläche im Demo. Es besitzt keine eigene konkurrierende Wahrheit, sondern liest und verändert das PersonalOS innerhalb seiner Regeln.
hermes
Hermes steht im Demo für einen dauerhaft verfügbaren Agenten. Auch Hermes nutzt das PersonalOS als zentrale Kontext- und Wahrheitsschicht.
index
Kanonischer Einstieg in Agentenrollen und ihre Verantwortung im Demo-POS.
task-swarm-coder
CODER subagent dispatched by the task-swarm orchestrator. Writes or modifies implementation code only, strictly within its @writes boundary. Never reviews, never scores, never accepts. Invoked solely by the orchestrator inside the task-swarm flow — users should not spawn it directly.
heavy-implementer
Implement large or uncertain changes that span multiple files or require debugging and trial-and-error. Use when the work is substantial enough that an isolated context with its own iteration loop pays off.