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 EditorialOS/pinterest-marketing-strategist --skill client-contextgit clone --depth 1 https://github.com/EditorialOS/pinterest-marketing-strategistWrote 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/editorialos/pinterest-marketing-strategist/client-context)<a href="https://agentmods.dev/skills/editorialos/pinterest-marketing-strategist/client-context"><img src="https://agentmods.dev/badge/skills/editorialos/pinterest-marketing-strategist/client-context/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/editorialos/pinterest-marketing-strategist/client-context"><img src="https://agentmods.dev/badge/skills/editorialos/pinterest-marketing-strategist/client-context.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 | $0.00047 | $0.02610 |
| Opus 5 | $0.00023 | $0.01305 |
| Sonnet 5 | $0.00009 | $0.00522 |
| Haiku 4.5 | $0.00005 | $0.00261 |
Grade A, and why
client-context 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 11d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Client Context — Pinterest Intelligence Layer
Purpose
Read the client's real documents and images to build the context layer that makes every composed pin client-specific. Pinterest is a visual search engine — context here means images and search terms as much as voice and audience. The image library inventory is the foundation of composed pin output.
Core Principle
This skill exists so that /create produces pins from real brand assets, not generic templates. Without context, pins are generic. Without images, pins are incomplete. Without learnings, pins don't improve. This skill loads all three.
When This Activates
Every /create and /track command starts here. Load context silently — show a one-line status header and move to the command's work. Don't narrate the loading process.
Priority Documents
Read the ~~docs folder. Look for these in priority order:
| Priority | Document Type | What to Extract | If Missing |
|---|---|---|---|
| 1 | Image library | Available images — from ~~images (Cloudinary) or ~~docs images/ folder. Filenames, dimensions, orientation, categories, tags, visual descriptions. This is the most critical asset. | Cannot produce composed pins. Flag: "No images found. Add brand images to create composed pins." |
| 2 | Brand guide / style guide | Visual identity, voice for descriptions, vocabulary rules, banned words | Ask for brand name and 2-3 adjectives |
| 3 | Product / service catalog | Names, descriptions, prices, destination URLs, categories | Ask what they sell and where it links |
| 4 | Audience personas | Demographics, interests, Pinterest search behavior, planning patterns | Ask who the target Pinterest user is |
| 5 | Board structure | Board names, descriptions, themes, goals | Recommend boards based on brand vertical |
| 6 | Pin learning files | pin-log.md, pin-learnings.md, pin-baselines.md from /track | First batch — no learning history |
| 7 | Pinterest config | pinterest-config.md from /setup | Run /setup first or proceed with defaults |
| 8 | Content strategy | Goals, pillars, seasonal calendar, pin queue | Ask for primary goal |
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.
- 11d ago First seen · 218 lines · 47 tokens per session scan A 6eaa3e24b4d6
client-context is a skill published in the GitHub repository EditorialOS/pinterest-marketing-strategist (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 2,610 once invoked, about $0.0002 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
self-improve
The deliberate self-improvement loop for the maintainer — step back from fixing issues and improve Heimdall's OWN capability. Ports karpathy/autoresearch to Heimdall's routing/planning: collect evidence from metrics.jsonl + queue dead/done stats → form testable hypotheses → run a bounded routing experiment → evaluate…
stacks
Load stack-specific knowledge (conventions, exact lint/test/build commands, common failure patterns) onto the current role agent for the project's detected tech stack(s) — Next.js, React Native, Spring Boot, FastAPI, Django, Rust, etc. Use at the start of any task in an unfamiliar or newly-onboarded repo, or whenever…
transmute
Comprehend an existing feature, then PORT it to another app (optionally upgrading it) or INTEGRATE/transform it in place — including swapping the vendor behind the scenes while preserving the exact UX. Use for "port/re-implement/clone this feature into ", "swap/migrate the vendor behind but keep the UX", "figure out…
divine
Thorough, research-grounded code review of a change, PR, or MR — multi-lens (correctness, security, simplification, tests), severity-ranked with impact + fix, configurable depth, optional PR comments. Use when asked to review code, "do a code review", "review this PR/MR", "review my changes/diff/branch", or audit a…
confluence
Work with Confluence over its REST API (no MCP) — read/search (CQL), summarize pages, find docs, create/update/comment/label. Use for any read/search/create/update on Confluence pages, or references to a remembered space, page, or doc.
conjure
Structured design dialogue with a visual companion — produces an approved spec and design artifacts before any implementation begins. Use at the start of a feature, before writing code.