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 ruvnet/metaharness --skill diag-harnessgit clone --depth 1 https://github.com/ruvnet/metaharnessWrote 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/ruvnet/metaharness/diag-harness)<a href="https://agentmods.dev/skills/ruvnet/metaharness/diag-harness"><img src="https://agentmods.dev/badge/skills/ruvnet/metaharness/diag-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/ruvnet/metaharness/diag-harness"><img src="https://agentmods.dev/badge/skills/ruvnet/metaharness/diag-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.00871 |
| Opus 5.5 | $0.00034 | $0.00348 |
| Sonnet 5.5 | $0.00017 | $0.00174 |
| Haiku 4.5 | $0.00009 | $0.00087 |
Grade A, and why
diag-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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
diag-harness
Codex skill: kernel-version skew check for a scaffolded harness — the ADR-027 diagnostic UX loop.
What it does
Single-question check: does my local @metaharness/kernel match what this harness was scaffolded against? That's the cross-machine compatibility question almost every "this harness doesn't work" support ticket turns out to be.
Reads .harness/manifest.json:
| Field | Source | Meaning |
|---|---|---|
meta.surface |
iter 56 | Which surface produced the harness (cli or web-ui) |
meta.kernel_version |
iter 58 | The @metaharness/kernel version stamped at scaffold time |
Resolves the local @metaharness/kernel via createRequire rooted at the harness's own package.json (real Node resolution). Computes the skew verdict and prints a copy-pasteable next step.
| Verdict | Exit | Message |
|---|---|---|
match |
0 | PASS kernel versions match exactly |
patch-diff |
0 | WARN patch-level skew (usually safe; may include bugfixes) |
minor-diff |
1 | WARN minor-level skew (new kernel features may be missing) + Run: npm install @metaharness/[email protected] |
major-diff |
1 | FAIL MAJOR skew — APIs may have changed; expect breakage + Run: npm install @metaharness/[email protected] |
no .harness/manifest.json at path |
2 | FAIL no .harness/manifest.json found at this path |
Usage from Codex
/diag-harness # cwd
/diag-harness path=./my-harness
Equivalent CLI
harness diag # cwd
harness diag ./my-harness # explicit path
harness diag ./my-harness --json # machine-readable for CI
harness diag ./my-harness --bundle # support-ticket JSON (iter 90)
The --bundle form (iter 90) emits a single JSON snapshot of the diag report + sanitised manifest + @metaharness/* deps + Node/platform info — everything a maintainer needs to triage a bug report. Object keys matching secret|token|key|password|api_key are redacted so the bundle is safe to paste into a public GitHub issue.
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 · 86 lines · 85 tokens per session scan A f27cd48e7536
diag-harness is a skill published in the GitHub repository ruvnet/metaharness (716 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 871 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
agent-performance-optimizer
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer.
agent-refinement
Agent skill for refinement - invoke with $agent-refinement.
C31-debug
Investigate bugs through reproduction → trace → hypothesis → test-first fix → verify → archive. All active sessions are tracked in memory/.planning/debug/ for resumption and knowledge compounding.
C31-research
Unified research skill. Covers best practices, framework documentation, git history, community issues, institutional memory, and bug reproduction. All modes are read-only — does not write code.
gsd-map-codebase
A codebase mapping tool that studies an existing software project and records its structure, technologies, coding conventions, and possible problem areas in Markdown files.
C31-workflow-bug-reproduction
Read-only workflow agent. Systematically reproduces bugs: hypothesize causes → construct minimal reproduction → verify. Use when a bug report is vague, when regression tests are missing, or when separating environment bugs from code bugs.