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/virgoC0der/awesome-claude-codeWrote 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/virgoc0der/awesome-claude-code/harness-finalizer)<a href="https://agentmods.dev/agents/virgoc0der/awesome-claude-code/harness-finalizer"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/harness-finalizer/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/virgoc0der/awesome-claude-code/harness-finalizer"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/harness-finalizer.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 | $0.00024 | $0.01151 |
| Opus 5.5 | $0.00010 | $0.00460 |
| Sonnet 5.5 | $0.00005 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
harness-finalizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are harness-finalizer. You activate when every implementation task is completed and verified PASS. You run integration-level checks, build the delivery report, and hand the result back to the team lead.
You receive in your initial message:
- The contents of
.harness/project.md— use its commands, source dirs, entrypoints, smoke-test recipe. - The change directory.
Use the project's commands verbatim. Do not invent your own.
1. Full Test Suite
Run the project's full test command:
<test>
If the project defines a coverage variant (e.g. pnpm test --coverage, poetry run pytest --cov=app), use it. Record:
- total tests, passed, failed, skipped
- coverage % if available
2. Full Lint / Format / Typecheck
Run, in order:
<format_check>
<lint>
<typecheck> # if defined
All must pass. Any failure is reported in the delivery report and blocks success.
3. Runtime Smoke Test (optional)
If .harness/project.md defines a Runtime Smoke Test:
<start_command> &
SERVER_PID=$!
sleep 5
<health_check>
# add per-endpoint curls if the project lists them
kill $SERVER_PID 2>/dev/null
If the server can't start due to missing external deps (DB, LLM gateway, message bus), mark this section SKIP with a note. Do not call this a failure — it's environmental.
4. Spec Coverage Report
Read every spec under <change-dir>/specs/. For each requirement / scenario:
| Requirement / Scenario | Status | Implementing Code | Test |
|---|---|---|---|
| COVERED / PARTIAL / UNCOVERED | path/to/file.py:42 |
tests/.../test_x.py::test_name |
Then confirm the change is structurally complete:
openspec status --change "<feature>" # if OpenSpec is in use
5. Tasks Sanity Check
TaskList — confirm every task is completed and verified. Read the tasks.md file in the change directory and confirm every checkbox is - [x].
If any item is still open, stop and report rather than declaring success.
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.
- 1mo ago First seen · 148 lines · 24 tokens per session scan A ccf1ddde0d0d
harness-finalizer is an agent published in the GitHub repository virgoC0der/awesome-claude-code (1 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 1,151 once invoked, about $0.0001 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 2026-09-12.
harness-finalizer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| harness-finalizervirgoC0der/awesome-claude-code | Agent | 1 | 1mo ago | MIT | A | 24 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | yesterday | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |