Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/45ck/skill-harnessnpx agentmods add skills/45ck/skill-harness/demo-review-surfaceWrote 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/45ck/skill-harness/demo-review-surface)<a href="https://agentmods.dev/skills/45ck/skill-harness/demo-review-surface"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/demo-review-surface/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/45ck/skill-harness/demo-review-surface"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/demo-review-surface.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 | $0.00065 | $0.00491 |
| Opus 5.5 | $0.00026 | $0.00196 |
| Sonnet 5.5 | $0.00013 | $0.00098 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
demo-review-surface 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.
What it actually says
Demo Review Surface
Overview
Use this skill when a human needs to inspect demo media and its evidence together. Prefer generated HTML for desktop/app-browser review, and Markdown/TOON for CLI-only handoff.
Required Sections
- summary: what the demo proves and what it does not prove
- source:
.demo.yaml, QA flow, spec, issue, or source artifact - media: rendered video, raw capture, poster, frame strip, or slideshow output
- evidence: events, quality, verification, QA reports, screenshots, traces, analyzer bundles
- findings: failed checks, warnings, stale artifacts, missing evidence
- next action: approve, regenerate, cut down, fix source, or discard
HTML Constraints
- Use one self-contained static
.htmlfile. - Use inline CSS only.
- Do not load external scripts, fonts, images, media, analytics, or network resources.
- Do not include
<script>, iframe, object, embed, form, meta refresh, externalsrc, externalhref, or browser storage/network APIs. - Embed small images only when safe; prefer relative links to large local media.
- Link or name the canonical source artifact and issue.
Provenance
If the target repo has docs/artifacts/artifacts.manifest.json, add or update an entry with:
idtype: usuallyreview-dashboardorevidence-packsourcesourceHashwhen availablereviewSurfaceevidenceLinksstatus
Then run:
node scripts/check-artifact-manifest.mjs
node scripts/check-artifact-html-policy.mjs
Review Defaults
- Desktop agent apps: generate HTML under
generated/review/. - CLI/TUI: produce Markdown summary first; generate HTML only when useful.
- CI: produce JSON/Markdown evidence indexes and avoid large media unless promoted.
Output
Name the generated path, source path, evidence paths, checks run, and any missing evidence.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 58 lines · 65 tokens per session scan A dcd3e5e2abfe
demo-review-surface is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 491 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
do-it-verify
Use when selecting evidence for a delivery claim, regression fix, installation, or branch closeout.
vibe
Use when working in a vibe-coded repository, where the user never reads the code and only runs the product and gives feedback, or when the user wants to start building a project that way.
testing-bun
Use when writing or modifying tests in a Bun project.
testing-ink
Use when writing or modifying tests for Ink (terminal UI) components.
testing-react
Use when writing or modifying tests for React hooks.
instructions
Use at the start of any task, before taking action, to load the always-on workflow rules covering skill invocation, communication, skill scripts, and the conventions of the environment the session is running in.