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 bzantium/meta-harness --skill update-harnessgit clone --depth 1 https://github.com/bzantium/meta-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/bzantium/meta-harness/update-harness)<a href="https://agentmods.dev/skills/bzantium/meta-harness/update-harness"><img src="https://agentmods.dev/badge/skills/bzantium/meta-harness/update-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/bzantium/meta-harness/update-harness"><img src="https://agentmods.dev/badge/skills/bzantium/meta-harness/update-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 | $0.00112 | $0.02121 |
| Opus 5.5 | $0.00045 | $0.00848 |
| Sonnet 5.5 | $0.00022 | $0.00424 |
| Haiku 4.5 | $0.00011 | $0.00212 |
Grade A, and why
update-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 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
update-harness — Harness Health Check & Updater
Analyzes an existing Claude Code harness against current official features, project evolution, and the pattern library. Produces actionable recommendations: what to remove, update, and add.
Workflow
Phase 1: Inventory
Scan the existing harness and catalog every component:
- Agents — Read all
.claude/agents/*.md: name, model, role, constraints - Skills — Read all
.claude/skills/*/SKILL.md: name, triggers, workflow - Hooks — Read
.claude/settings.jsonhooks section: events, matchers, scripts - Rules — Read
CLAUDE.md: delegation rules, conventions, agent catalog - MCP — Read
.mcp.jsonif present - Plugins — Read
.claude/settings.jsonenabled plugins
Produce an inventory list with component count. If no harness is found, inform the user and suggest using create-harness instead.
Phase 2: Official Features Delta
Check what the harness duplicates or could leverage from official features:
- Read
../create-harness/references/official-builtins.md - WebSearch "Claude Code changelog latest features" for anything newer than the reference
- For each harness component, evaluate:
- Redundant? — Does an official feature now do the same thing? (e.g., a custom explore agent when built-in Explore exists)
- Superseded? — Has a new official feature made this component unnecessary? (e.g., custom task tracking when TaskCreate is now built-in)
- Leverageable? — Could an official feature enhance this component? (e.g., a skill could use CronCreate instead of custom scheduling)
Phase 3: Project Evolution
Spawn scout to re-analyze the current project state:
Agent(
name: "scout",
prompt: "Analyze this project. Follow your investigation protocol and produce the structured analysis report.",
model: "sonnet"
)
Compare the scout's current findings against what the harness covers:
| Change | Implication |
|---|---|
| New modules/services added | Harness may need new agents or wider scope |
| Modules removed | Harness may reference dead code |
| Tech stack changed (new framework, build tool) | Hooks/skills may target wrong tools |
| Test framework changed | Verification hooks may be broken |
| Team size changed (solo to team or vice versa) | Harness scale may be wrong |
| New external integrations (APIs, databases) | May need safety hooks or specialized agents |
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 · 194 lines · 112 tokens per session scan A 08d2142011d8
update-harness is a skill published in the GitHub repository bzantium/meta-harness (3 stars, last pushed 7mo ago), licensed MIT. It adds 112 tokens to every session and 2,121 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
goal-loop
Drive a verifiable goal to done with factory-built agents, visible and held-out evidence, and a cross-provider judge.
second-opinion
GPT (GPT-6 Astra by default) as advisor, adversarial reviewer or judge through headless codex exec, always read-only; never an implementer. Modes: advise (independent read on a plan, diff or design, beside Claude's own view, with follow-ups), review (Codex's built-in reviewer on uncommitted work, a branch or a…
metaprompt
Generate a complete, ready-to-paste prompt engineered for a specific target model (Claude Fable 5.1 / Opus 5.5 / Sonnet 5 / Haiku 4.5, GPT-5.x) and harness (Claude Code CLAUDE.md or skill, Codex AGENTS.md, pi, Amp, eve, AI Gateway, Agent SDK, raw API, chat UI), using per-model and per-harness reference guides. Trigger…
file-todos
File-based TODO lifecycle in the project's todos/: one markdown file per review finding or tech-debt item, named {id}-{status}-{priority}-{description}.md, moving pending -> ready -> complete. Modes: create TODOs from findings; triage pending ones with the user (approve, skip, modify; no coding); resolve ready ones…
motion-design
Direct and produce code-driven videos that a person is proud to share: motion graphics, series openers, music and lyric videos, paper and data explainers, product demos, social clips. Runs end to end as a studio crew of parallel subagents coordinated through an ORCHESTRATION.md file: brief, writers' room, style…
managed-agents-wizard
Walk a person from an idea to a Claude Managed Agents agent that runs on its own, and stay with them through debugging. Explains each concept at the moment it matters (Agent, Environment, Session, Deployment, vault, memory store, outcome), asks the real decisions as illustrated AskUserQuestion choices, designs the…