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/OSideMedia/higgsfield-ai-prompt-skillnpx agentmods add commands/osidemedia/higgsfield-ai-prompt-skill/validateWrote 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/commands/osidemedia/higgsfield-ai-prompt-skill/validate)<a href="https://agentmods.dev/commands/osidemedia/higgsfield-ai-prompt-skill/validate"><img src="https://agentmods.dev/badge/commands/osidemedia/higgsfield-ai-prompt-skill/validate/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/commands/osidemedia/higgsfield-ai-prompt-skill/validate"><img src="https://agentmods.dev/badge/commands/osidemedia/higgsfield-ai-prompt-skill/validate.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 | $0.00022 | $0.00326 |
| Opus 5.5 | $0.00009 | $0.00130 |
| Sonnet 5.5 | $0.00004 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
validate 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- validate — 100% identical, 28 lines differ
What it actually says
"Release-ready" means the full release gate is green — never the plain
validate.py run, which lets optional-dependency SKIPs and stale generated
views pass (before v3.37.0 this command certified readiness from the
non-strict run while --strict was red).
Run all three, in order, and keep going after a failure so the report is complete:
python3 scripts/validate.py --strict
python3 -m pytest tests/ -q
python3 scripts/validate.py --evals
Report:
- For each command: PASS or FAIL, plus every failing check / test / eval case with its file path and what needs fixing (quote the checker's own line).
- Say release-ready ONLY when all three exited 0. If any failed, say "not release-ready" and list the blockers — do not soften it because the non-strict run would pass.
- If
--strictfails only on items the non-strict run would merely WARN or SKIP (stale snapshot, staledb/memory-summary.md/db/ledger/_global.json, missing fpdf2), name the fix command the failure line gives.
For a quick iteration check while editing (NOT a readiness verdict), the plain
python3 scripts/validate.py is fine — report it as "health check", never as
release-ready.
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 Changed · +20 lines · +8 tokens per session f5251dd87c2a
- 1mo ago First seen · 12 lines · 14 tokens per session scan A eba6a8f06728
validate is a command published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (800 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 326 once invoked, about $0.0001 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 commands, from other repositories
eval-autonomous-agent
Generate a test harness for hallucination, bias, scope creep, and reward misalignment per FINRA 2026 guidelines.
sm-swab
Run slop-mop's iterative development loop for this repository.
verify-render
Download a rendered Poppify reel, run ffprobe + frame extract, surface a verdict on whether the render matches what was requested.
pdca-do
Run only the DO phase of the PDCA framework (TDD implementation with active oversight).
red-team
description: "Red team AI system for vulnerabilities".
change-quiz
Generate a change report and a must-pass comprehension quiz before merging.