Borrowing it
Nothing to install: this file belongs to osauer/canary. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/osauer/canary/main/.agents/skills/canary-harness/SKILL.mdgit clone --depth 1 https://github.com/osauer/canaryWrote 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/skills/osauer/canary/canary-harness)<a href="https://agentmods.dev/skills/osauer/canary/canary-harness"><img src="https://agentmods.dev/badge/skills/osauer/canary/canary-harness/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.
<a href="https://agentmods.dev/skills/osauer/canary/canary-harness"><img src="https://agentmods.dev/badge/skills/osauer/canary/canary-harness.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00058 | $0.00487 |
| Opus 5 | $0.00029 | $0.00244 |
| Sonnet 5 | $0.00012 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
canary-harness 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 3d 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
Updated: 2026-09-05
Contract
Use the typed canary MCP tools for read-only brief, detailed regime and portfolio stress, Edge review, account, positions,
rulebook, named-symbol technical, proposal, opportunity, settings, trading,
health, and order-status/history work. Use canary ... --json when MCP is
unavailable, a CLI-only policy/reconciliation diagnostic is required, or the
project needs an exact reproducible CLI artifact.
The MCP surface cannot place, modify, cancel, exercise, liquidate, or transmit. An explicit current-turn broker-write request uses only the agent-origin gated CLI; trading readiness, route/account/client pins, preview tokens, broker WhatIf/eligibility, freeze state, journaling, and daemon authorization remain binding. A minted preview token is not submit authority. Settings/freeze changes, policy/reconciliation governance writes, and destructive daemon maintenance remain human-only.
Preserve typed evidence exactly: nil is unavailable rather than zero; report live/delayed/frozen data, freshness, stale reasons, session context, source health, and warning details when material. Local order history is intent and lifecycle evidence, not an IBKR statement or complete broker audit.
Canonical References
This is only the repo-development safety overlay. Detailed command selection, schemas, and domain authority stay in:
Project Workflow
Read the root AGENTS.md before editing. For daemon/CLI/MCP/trading semantic
changes, use .agents/docs/daemon-cli-trading-contract.md. For Canary SPA
changes, use .agents/docs/spa-authority-matrix.md.
After daemon or CLI edits, run the required tests and smoke tier, refresh the
installed daemon, and capture redacted canary status --json plus one command
that exercises the change. Report every skip and first failure explicitly.
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.
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.
- 3d ago Changed · +4 tokens per session b551ca4b24a8
- 9d ago First seen · 46 lines · 54 tokens per session scan A 80a806b742ad
canary-harness is a skill published in the GitHub repository osauer/canary (8 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 487 once invoked, about $0.0003 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 skills, from other repositories
ibkr
Interactive Brokers — global stocks/forex/futures via a LOCAL TWS/IB Gateway, not cloud. Covers stocks, ETFs, forex, futures; account, positions, orders, quotes, history, order placement. Use when the user wants to check or trade an Interactive Brokers account (e.g. "IBKR positions", "buy 10 AAPL on IBKR paper", "my…
tradingview-mcp
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and multi-market screener. Supports stocks, crypto, ETFs, indices, Turkish (BIST), and Egyptian (EGX) markets.
jsonbill
Generate a PDF invoice/statement files from JSON via JSONBill API.
Search and read the user's mail through the your-mail MCP server, a read-only mirror of their IMAP accounts indexed by notmuch. Use it to find messages, read threads, summarise and triage mail, and pull details (booking references, invoices, what someone promised) into other work. It cannot send, delete, move or…
tradegit
A trading journal stored in a private GitHub repository or entirely on a local computer. It records trades, imports broker statements, and calculates results such as profit and loss.
sai-perps
Query and reconcile Sai perps data across live Perp, Oracle, and SLP Vault contracts; Sai Keeper GraphQL; DexPal REST; sai-keeper Postgres; and referral records. Use for markets, open interest, fees, trades, vault health, oracle prices, REST statistics, database-backed metrics, referral ownership or history…