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 theafh/ai-modules --skill harness_portabilitygit clone --depth 1 https://github.com/theafh/ai-modulesWrote 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/theafh/ai-modules/harness_portability)<a href="https://agentmods.dev/skills/theafh/ai-modules/harness_portability"><img src="https://agentmods.dev/badge/skills/theafh/ai-modules/harness_portability/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/theafh/ai-modules/harness_portability"><img src="https://agentmods.dev/badge/skills/theafh/ai-modules/harness_portability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 63 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00157 | $0.05410 |
| Opus 5.5 | $0.00063 | $0.02164 |
| Sonnet 5.5 | $0.00031 | $0.01082 |
| Haiku 4.5 | $0.00016 | $0.00541 |
Grade A, and why
harness_portability 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 15d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
harness_portability
<harness_portability> Keep bundled skill and plugin runtime artefacts portable across agent harnesses and operating systems. Apply this skill whenever a change creates or edits scripts, hooks, agent definitions, MCP helpers, command wrappers, setup flows, output styles, or the skill and plugin wording that tells future agents how to execute, initialize, or configure those artefacts.
<fact_sourcing>
<verify_before_encoding>
Treat every concrete harness fact as perishable: a configuration root, a frontmatter key, a tool name, an environment variable, a hook event, a settings key, a version threshold. Confirm each one against current official provider documentation, the loader source, or the installed build before a change depends on it, and record which of those three the claim rests on. An observed behavior on the machine at hand outranks documentation that omits it, and documentation outranks recollection.
</verify_before_encoding>
<where_snapshots_live>
Where the working repository carries a wiki, read its harness pages first: they hold the last verified snapshot with the date and source behind each claim, which makes them a starting point that still needs re-verification rather than an authority. Write a new finding back there, or into this skill's own references/ directory when a future agent needs it in a repository that has no such wiki. Keep this skill body to the rules themselves, so a portability review costs the rules rather than the whole fact base.
</where_snapshots_live>
<state_the_gap>
State the verification gap plainly when a claim could not be confirmed, and name what would settle it. Carry an unconfirmed classification as pending rather than resolving it toward whichever answer is convenient, because a wrong negative closes a line of inquiry that a stated gap keeps open.
</state_the_gap>
</fact_sourcing>
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.
- 15d ago Changed · +2 lines df9de6f257bd
- 25d ago Changed · +19 lines 1e3d4a560b31
- 1mo ago First seen · 127 lines · 157 tokens per session scan A b30c12713214
harness_portability is a skill published in the GitHub repository theafh/ai-modules (38 stars, last pushed today), licensed MIT. It adds 157 tokens to every session and 5,410 once invoked, about $0.0006 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…