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 uppifyagency/claude-harness --skill harness-statusgit clone --depth 1 https://github.com/uppifyagency/claude-harnessWrote 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/uppifyagency/claude-harness/harness-status)<a href="https://agentmods.dev/skills/uppifyagency/claude-harness/harness-status"><img src="https://agentmods.dev/badge/skills/uppifyagency/claude-harness/harness-status/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/uppifyagency/claude-harness/harness-status"><img src="https://agentmods.dev/badge/skills/uppifyagency/claude-harness/harness-status.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 | $0.00068 | $0.00562 |
| Opus 5 | $0.00034 | $0.00281 |
| Sonnet 5 | $0.00014 | $0.00112 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
harness-status 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 12d 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 Status — State Inspector
Overview
Inspect the current state of a harness run. Reads .harness/state.json and related files to present a clear progress report.
Execution
Step 1: Check for Harness Workspace
Look for .harness/ directory in the current project. If not found, inform the user that no harness run exists in this project.
Step 2: Read State
Read .harness/state.json and extract:
- Current phase (planning / building / evaluating / complete)
- Current round number
- Max rounds configured
- Active components (planner, evaluator)
- Brief (what was requested)
Step 3: Gather Artifacts
Scan .harness/ for all artifact files:
spec.md— exists? When created?build-summary-*.md— how many rounds completed?eval-report-*.md— how many evaluations done? Latest verdict?config.json— any disabled components?simplification-log.md— any simplification tests run?
Step 4: Present Report
Harness Status
==============
Brief: [user's original brief]
Phase: [current phase]
Round: [N] / [maxRounds]
Components:
Planner: [enabled/disabled]
Evaluator: [enabled/disabled]
Artifacts:
spec.md [exists/missing]
build-summary-1.md [exists]
build-summary-2.md [exists]
eval-report-1.md [ITERATE]
eval-report-2.md [PASS]
Latest Eval: [verdict summary or "No evaluations yet"]
Next Action: [What should happen next based on state]
Step 5: Suggest Next Action
Based on state, suggest what to do:
planning+ no spec → "Run/harnessto start planning"building+ no build summary for current round → "Generator is in progress or interrupted. Resume with/harness resume"evaluating+ no eval report → "Evaluator is in progress or interrupted"evaluating+ ITERATE verdict → "Run next build round or accept current state"complete→ "Harness run is finished. Review results in.harness/"
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.
- 12d ago First seen · 70 lines · 68 tokens per session scan A d0fa163d355c
harness-status is a skill published in the GitHub repository uppifyagency/claude-harness (5 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 562 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
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
test-run
Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
magic-compact
Compact this Claude Code session.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.