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.
npx skills add vasuag09/harness-claude --skill harnessgit clone --depth 1 https://github.com/vasuag09/harness-claudeWrote 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/skills/vasuag09/harness-claude/harness)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/harness"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/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/skills/vasuag09/harness-claude/harness"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/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 | $0.00055 | $0.00556 |
| Opus 5 | $0.00028 | $0.00278 |
| Sonnet 5 | $0.00011 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00056 |
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 9d 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
/harness — the full pipeline
The top-level orchestrator. It walks all four phases by invoking the phase orchestrators in order, pausing at every phase boundary for your go-ahead. It is a convenience wrapper — it adds checkpoints and a running summary, nothing the phase skills don't already do.
Flow
/harness-claude:harness-plan ──▶ [checkpoint] ──▶ /harness-claude:harness-implement ──▶ [checkpoint]
──▶ /harness-claude:harness-verify ──▶ [checkpoint] ──▶ /harness-claude:harness-maintain (optional)
-
Plan — run
/harness-claude:harness-plan. At its HALTs, get the user's answers/approvals. → CHECKPOINT: show the approved spec + plan (+ ADR). Wait for "go" before coding. -
Implement — run
/harness-claude:harness-implementagainst the approved plan. → CHECKPOINT: report what was built and test status. Wait for "go" before verify. -
Verify — run
/harness-claude:harness-verify. Halt on Critical/High; stop at the git boundary. → CHECKPOINT: show review/security verdicts, coverage, observed-working evidence. -
Maintain — offer
/harness-claude:harness-maintain. Run it only if the user wants cleanup now.
Rules
- Honor every HALT and CHECKPOINT — this is a guided pipeline, not an autonomous run.
- Delegate heavy work to subagents;
/harness-claude:save-sessionat each checkpoint so a long feature survives compaction or a new session. - Never commit or push without an explicit user ask — branch creation happens automatically
at first write in the Implement phase (
rules/git.md)./harness-claude:harness-verifyends at "ready to commit/PR." - For a small change, a single phase orchestrator (or atomic skill) is lighter —
/harness-claude:harnessis for full features.
Output
A phase-by-phase rollup ending in "merge-ready (awaiting your git go-ahead)."
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.
- 9d ago First seen · 43 lines · 55 tokens per session scan A f256055f654f
harness is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 556 once invoked, about $0.0003 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.
Other skills, from other repositories
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.