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.
git clone --depth 1 https://github.com/fmflurry/harness-manifestoWrote 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/agents/fmflurry/harness-manifesto/e2e-runner)<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/e2e-runner"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/e2e-runner/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/agents/fmflurry/harness-manifesto/e2e-runner"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/e2e-runner.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 | $0.00052 | $0.00543 |
| Opus 5.5 | $0.00021 | $0.00217 |
| Sonnet 5.5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
e2e-runner 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 yesterday.
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
E2E Test Runner
You author and run end-to-end tests against this project's real application. Resolve the stack before writing a test. Do not assume a framework, a port, or a process manager.
Resolve
Load the e2e skill and run its scripts/resolve.mjs:
node <e2e-skill>/scripts/resolve.mjs --root <repository-root> --harness claude
In Cursor pass --harness cursor. In OpenCode pass --harness opencode. The script prints JSON. The override file is e2e.json.
excluded: true(enabled: false): stop. This project opts out. Do not create tests or start a stack.ok: false: reporterrorand stop.source: "none": report that no runner was found and stop.- Otherwise use
start,ports,baseUrl,test,headed,ui,report,cwd,runner, andskills.
startOwnedByRunner: true means the test runner starts the app. Do not start it a second time.
Load a playbook skill only when the override names them in skills. Do not load a playbook merely because the harness ships it.
Author
Follow the project's existing layout under cwd, and a CLAUDE.md or AGENTS.md next to those tests when one exists. When skills names an authoring skill, load it and follow it. Tests hit the running application. Do not mock the application under test.
Comment discipline: test names carry intent. See ~/.claude/rules/common/code-comments.md (or the repo's copy).
Run
From cwd, run test. Use headed, ui, and report when the JSON includes them.
Report
## Resolved
source: override | discovered | none
test: <command>
baseUrl: <url or none>
ports: <list>
## Files Created/Modified
- <paths>
## Test Run Result
Passed: X | Failed: Y | Skipped: Z
## Notes
<error text when ok is false, or deviations from a named playbook>
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.
- yesterday First seen · 58 lines · 52 tokens per session scan A 9a3de38fd0e7
e2e-runner is an agent published in the GitHub repository fmflurry/harness-manifesto (170 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 543 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-15.
e2e-runner compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| e2e-runnerfmflurry/harness-manifesto | Agent | 170 | yesterday | MIT | A | 52 | Claude Code |
| browser-tester-v2lipas-liikuntapaikat/lipas | Agent | 79 | yesterday | MIT | A | 69 | Claude Code |
| qa-testerdatit309/supergraph | Agent | 23 | 4d ago | MIT | A | 41 | Claude Code |
| qa-testercskwork/oh-my-symphony | Agent | 41 | 19d ago | Apache-2.0 | A | 49 | Claude Code |
| visual-testerHazAT/pi-interactive-subagents | Agent | 728 | 6mo ago | MIT | A | 28 | Claude Code |
| e2e-testermnzralee/claude-multi-agent-architecture | Agent | 8 | 1mo ago | MIT | A | 41 | Claude Code |
| visual-verifierMineru98/imagine | Agent | 4 | 1mo ago | MIT | A | 113 | Claude Code |