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 instructions/yusenzhang0601/context-canopy/agents-mdgit clone --depth 1 https://github.com/YusenZhang0601/context-canopyWrote 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/instructions/yusenzhang0601/context-canopy/agents-md)<a href="https://agentmods.dev/instructions/yusenzhang0601/context-canopy/agents-md"><img src="https://agentmods.dev/badge/instructions/yusenzhang0601/context-canopy/agents-md.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 | $0.00586 | $0.00586 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
context-canopy AGENTS.md 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 4d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ContextCanopy Agent Entry
This repository is the public ContextCanopy distribution. It is not a user's personalized authority.
Route before acting
- For setup or migration, read
README.mdandskills/second-brain-attach/SKILL.md; finish withsecond-brain-doctorin a fresh host session. - For Vault reads or writes, work from
vault/and readvault/AGENTS.mdcompletely before acting. - For MCP code or tests, work from
mcp/and readmcp/AGENTS.mdcompletely before acting. - For documentation changes, keep
README.mdandREADME.zh-CN.mdsemantically aligned. Do not translate code, paths, commands, or compatibility identifiers. - The installable
skills/second-brain-*directories and theirvault/90-System/Personal-AI/SKILLS/mirrors express the same public contract. Update both and verify byte equality; do not let them become competing owners.
Privacy and authority boundary
- Before writing real personal context, have the user choose
local-onlyorprivate-remoteauthority. - The public ContextCanopy remote is distribution-only. Never push a personalized Vault, raw conversations, credentials, private repository URLs, unpublished research, or sensitive evidence to it.
- A
private-remotesetup must use a separate repository whose private visibility and writable identity were verified live. A public fork is not a personal Vault. - Keep common user context separate from each Agent's role. A new Agent should recognize the same person without becoming a clone of another Agent.
Portability claims
- ContextCanopy moves user-owned durable context, Skills, and host projections. It does not move model weights, hidden provider memory, credentials, permissions, or active runtime state.
- Selected accessible conversations and exports can be migrated through the guided Distill workflow. Do not claim a universal one-click provider-memory importer unless one has been implemented and verified.
- Configuration-file presence is not installation proof. Attach and Sync complete only after the target host passes a fresh-session Doctor check.
- Active rule files express the current effective state, not an append-only learning log. Preserve superseded evidence in Git and release history, remove retired behavior from active templates, and verify both the new behavior and the old behavior's exit.
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.
- 4d ago First seen · 44 lines · 586 tokens per session scan A fca4cced8dbe
context-canopy AGENTS.md is an instructions file published in the GitHub repository YusenZhang0601/context-canopy (2 stars, last pushed 12d ago), licensed MIT. It adds 586 tokens to every session, about $0.0029 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 instructions, from other repositories
dakera-cli CLAUDE.md
Instructions for Dakera-AI/dakera-cli, covering dakera-cli, key commands, architecture and conventions.
pos CLAUDE.md
Instructions for xcota/pos, covering personal os, rules, memory, budget and hard rules.
pos AGENTS.md
Instructions for xcota/pos, covering agents.md — workspace boot rules, session boot, memory, safety and language.
cli AGENTS.md
Instructions for konteks/cli, covering agent instructions, project overview, tech stack, repository layout and common commands.
graph-memory CLAUDE.md
Instructions for stevepridemore/graph-memory, covering graph memory, when to consult the graph, how to use it, writing to the graph during conversation and when to write (call graphrelate).
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.