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 anhnguyen0905/codex-mcp --skill creative-briefgit clone --depth 1 https://github.com/anhnguyen0905/codex-mcpWrote 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/anhnguyen0905/codex-mcp/creative-brief)<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/creative-brief"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/creative-brief/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/anhnguyen0905/codex-mcp/creative-brief"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/creative-brief.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 | $0.00089 | $0.01186 |
| Opus 5 | $0.00044 | $0.00593 |
| Sonnet 5 | $0.00018 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
creative-brief 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 9d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Brief (what must be fixed before creative work starts)
The brief fixes decisions, not craft
A brief locks what creatives must not have to guess and leaves everything else open. Prescribe the execution and it is a script; leave the message open and it is a wish list. Nine things must be settled before anyone opens a design file:
1 Objective the business change wanted + the KPI that proves it moved
2 Audience who, behaviourally — not demographics alone
3 Insight the tension in that audience's life the work speaks to
4 Single message ONE proposition, one sentence, per asset
5 Reason to believe the evidence that makes the message credible
6 Mandatories logo, legal, claims, disclaimers, brand and platform rules
7 Deliverables exact list: format, ratio, duration, language, placement, master + cutdowns
8 Timeline briefing, review dates, capped revision rounds, final handover
9 Budget + approval production budget, one named decision-maker, sign-off order
Everything else is the creative team's territory: a brief that also supplies the headline, palette and shot list has replaced the work it commissioned. The brief states problem and constraints; the script or storyboard is one proposed answer to it, authored by the creative side and judged against the brief. Keep them in separate documents — merged, every review argues execution and the strategy is never tested.
One message per asset
Messages compete for the same few seconds. Two propositions in one film do not double recall; they split it and usually leave neither. Five stakeholder messages means five assets or a ranked funnel sequence, not one crowded film. Write it as a plain declarative sentence a stranger could repeat after one viewing.
Writing the insight
An insight is not a fact, a feature, or a restatement of the target — it is a tension the product can resolve. Test it: does the audience recognise itself, and does the product genuinely answer it? Source from research, reviews, support tickets, playtests or sales calls, and cite each source.
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.
- 9d ago First seen · 98 lines · 89 tokens per session scan A d73dbf598494
creative-brief is a skill published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 1,186 once invoked, about $0.0004 per session on Opus 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.