What is claude-harness-canary?

A compatibility check for the current version of Claude Code, run through real interactive sessions in tmux. It checks model switching, unattended prompts, and Monitor/Cron routines before releases or after upgrades.

Use it to run the three built-in compatibility checks and collect evidence from interactive Claude Code sessions.

It helps detect breaks in the agent environment before a release or tool upgrade reaches users.

claude-harness-canary — Skill for Claude Code and Codex by gtapps

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.

Any agent

npx skills add gtapps/hermitd --skill claude-harness-canary

Clone the repo

git clone --depth 1 https://github.com/gtapps/hermitd

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gtapps/hermitd/claude-harness-canary/github.svg)](https://agentmods.dev/skills/gtapps/hermitd/claude-harness-canary)

Your own site

<a href="https://agentmods.dev/skills/gtapps/hermitd/claude-harness-canary"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/claude-harness-canary/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gtapps/hermitd/claude-harness-canary"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/claude-harness-canary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,407 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00072	$0.04407
Opus 5.5	$0.00029	$0.01763
Sonnet 5.5	$0.00014	$0.00881
Haiku 4.5	$0.00007	$0.00441

Measured 11d ago against content hash 56b10d305270, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

claude-harness-canary scanned grade D with 2 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 11d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

"<project>/.claude/settings.local.json" permissions-sync

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Never use `rm -rf`.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

claude-harness-canary — 97% identical, 14 lines differ

.agents/skills/claude-harness-canary/SKILL.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Harness Canary

Run all three groups serially against the currently installed Claude Code. Take no arguments and do not offer group selectors. Target 5–8 minutes, but preserve bounded waits and evidence over that estimate.

Keep this canary core-only, current-Claude-only, interactive-tmux-only, and loaded through --plugin-dir. Never add it to CI, release commands, or $pre-release-review.

Shared probe prerequisite

Reuse the installed $probe lifecycle. Before creating canary state, read its active SKILL.md and require all of these properties:

real interactive Claude in tmux, never claude -p, Codex, or another PTY;
no interactive --no-session-persistence;
tmux pipe-pane starts before any input;
one bounded readiness phase that detects the trust dialog, accepts it only when present, handles only explicitly recognized startup onboarding, and waits for the normal prompt;
a unique output-only completion nonce whose complete value is never contiguous in the injected prompt;
completion accepted only from assistant output after the requested evidence, never prompt echo;
one bounded wait per canary action;
teardown with rm -r only after validating the exact scratch path.

If any property is absent, stop before preflight and report:

PREREQUISITE BLOCKED — update the local $probe protocol

Do not recreate generic tmux lifecycle rules locally or hand-roll a fallback. Extend the probe lifecycle only for the multi-action assertions below.

Preflight

Run from the repository root.

Resolve the absolute core path at plugins/hermitd.

Record bounded output from:

claude --version
claude --help
tmux -V
claude auth status --json

Require current help to expose --plugin-dir, --model, --permission-mode, and --session-id.
Require authentication through the default profile. Do not set CLAUDE_CONFIG_DIR.
Require these core files:
- .claude-plugin/plugin.json
- hooks/hooks.json
- scripts/lib/harness-command.ts
- scripts/stop-pipeline.ts
- scripts/hermitd-watchdog.ts
- scripts/ask-gate.ts
- scripts/apply-settings.ts
- scripts/routines.ts
- scripts/routine-monitor.sh
- skills/hermit-routines/SKILL.md

Read the full file on GitHub · 386 lines

Files

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.

agents/openai.yaml 273 B

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.

11d ago First seen · 386 lines · 72 tokens per session scan D 56b10d305270

Subscribe to this mod's changes

claude-harness-canary is a skill published in the GitHub repository gtapps/hermitd (79 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 4,407 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.

Claude Code Testing ai ai-agent anthropic claude claude-code-plugin

proof-e2e

Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to "write E2E tests", "end-to-end testing", "browser tests", "UI tests", or "Playwright tests".

tonone-ai/tonone · 63 tokens

proof-strategy

Produce a test strategy for a project or feature — risk map, test type decisions, coverage targets, CI config. Use when asked to "create test strategy", "what should we test", "testing plan", or "improve test coverage".

tonone-ai/tonone · 53 tokens

mean-tester

Mean test another agent when someone asks you to test, check or break it. Invoke on "test @agent", "mean test @agent", "check whether @agent works", on "continue " or "rerun " in a new message, or on "continue" in a thread where you already reported a campaign, and on "Judge this recorded exchange".

curie-eng/curie · 81 tokens

claude-harness-canary