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/vinnie357/claude-skillsWrote 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/commands/vinnie357/claude-skills/harness)<a href="https://agentmods.dev/commands/vinnie357/claude-skills/harness"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/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/commands/vinnie357/claude-skills/harness"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/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 | $0.00016 | $0.00667 |
| Opus 5.5 | $0.00006 | $0.00267 |
| Sonnet 5.5 | $0.00003 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
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 2mo 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
Run altana harness to fan out many tasks, distributing them across configured harnesses, and present the results as a per-task table.
What it does:
- Parses the pipe-separated task list from the argument string.
- Invokes
altana harness "<t1>" "<t2>" ... [--map <idx>@<harness>]. - Runs in the background (multiple agents run concurrently).
- Receives a JSON array of result objects in task order.
- Presents a per-task results table with harness, status, duration, and a one-line answer excerpt.
Arguments:
<t1> | <t2> | ...— task strings separated by|(pipe with spaces). Each becomes one element in the harness call.--map idx@harness— pin a specific task index (0-based) to a named harness. Multiple--mapflags are accepted. Tasks without a pin are distributed in round-robin order across all configured harnesses.
Result table format:
# | Harness | Status | Duration | Answer excerpt
---|---------------|---------|----------|---------------
0 | claude-local | done | 9.4s | "Hello there, fr..."
1 | codex | done | 4.1s | "The fix requires..."
2 | claude-local | crash | 0.3s | (see log_path)
If altana is not installed:
Install altana (see its README — it is a Zig CLI built with zig 0.16). After building, place the binary on your PATH or invoke via mise exec -- zig-out/bin/altana.
Examples:
/harness explain the delegate subcommand | explain the council subcommand | explain the harness subcommand
/harness write a docstring for parse_config | write a docstring for run_delegate | write tests for council --map 0@opus-harness
/harness "audit error handling in src/delegate.zig" | "audit error handling in src/council.zig"
Task instructions:
Parse the argument: split on | to produce the task list. Extract any --map flags from the remaining tokens.
Reconstruct the altana call: altana harness "<t1>" "<t2>" ... [--map ...]
Run in background.
Once results arrive, parse the JSON array (index corresponds to task order). Build the results table:
- For
status == "done": extract the first non-empty line of## Answeras the excerpt. - For non-
donestatuses: show the status value and thelog_path.
Present the table. For any done entries where the full response is needed, show it on request.
Load /altana:altana for protocol and config reference before running.
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.
- 2mo ago First seen · 58 lines · 16 tokens per session scan A 3150b5f6e4b5
harness is a command published in the GitHub repository vinnie357/claude-skills (27 stars, last pushed 14d ago), licensed MIT. It adds 16 tokens to every session and 667 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 2026-09-03.
harness compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| harnessvinnie357/claude-skills | Command | 27 | 14d ago | MIT | A | 16 | Claude Code |
| checklistgithub/spec-kit | Command | 149k | today | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 149k | today | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 149k | today | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 149k | today | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 149k | today | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 149k | today | MIT | A | 14 | Claude Code |