canary-debug-flake

canary-debug-flake is a command for coding agents from bop-clocktower/canary. It costs 21 tokens per session (85 once invoked), scanned A, original, MIT.

A command for investigating tests that fail unpredictably, often called flaky tests. It uses the canary-flake-hunter agent to examine source code, continuous-integration logs, or a description of the failure.

In plain words
What is it for?
Use it to diagnose flaky tests from code or CI logs and propose a deterministic fix.
Why use it?
It helps distinguish an intermittent test problem from a real product bug and points toward a fix that produces repeatable results.

Command

Part of the canary plugin — 21 skills, 13 commands, 8 agents, 4 hooks, 3 MCP servers shipped together

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 commands/bop-clocktower/canary/canary-debug-flake
Clone the repo
git clone --depth 1 https://github.com/bop-clocktower/canary

Or install canary, the plugin that ships this one along with the rest of its 21 skills, 13 commands, 8 agents, 4 hooks, 3 MCP servers.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 85 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 $0.00021 $0.00085
Opus 5 $0.00010 $0.00043
Sonnet 5 $0.00004 $0.00017
Haiku 4.5 $0.00002 $0.00009

Measured 3d ago against content hash 8f6c0df8acee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

canary-debug-flake 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.

commands/canary-debug-flake.md · 12 lines

What it actually says

canary-debug-flake

Use the canary-flake-hunter agent to diagnose the following flaky test:

$ARGUMENTS

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. 3d ago First seen · 12 lines · 21 tokens per session scan A 8f6c0df8acee

Subscribe to this mod's changes

canary-debug-flake is a command published in the GitHub repository bop-clocktower/canary (4 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 85 once invoked, about $0.0001 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.