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 agentmods add skills/contentful/skills/optimization-sdk-syncnpx skills add contentful/skills --skill optimization-sdk-syncgit clone --depth 1 https://github.com/contentful/skillsWhat 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 | $0.00064 | $0.01967 |
| Opus 5 | $0.00032 | $0.00983 |
| Sonnet 5 | $0.00013 | $0.00393 |
| Haiku 4.5 | $0.00006 | $0.00197 |
Grade A, and why
optimization-sdk-sync 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 2d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimization SDK Sync
Update the modern Optimization SDK knowledge in contentful-personalization from a verified upstream revision. Optimize the result for an agent solving implementation tasks: concise, explicit, runtime-specific, and grounded in public API and maintained examples.
Do not copy upstream guides wholesale. Treat this as a knowledge compilation workflow.
Scope
This skill owns modern @contentful/optimization* guidance. Preserve legacy @ninetailed/* guidance unless upstream evidence requires a compatibility correction.
Supported runtime references:
- shared concepts and behavior
- React Web
- Next.js App Router
- Next.js Pages Router
- browser Web
- Node.js
- React Native
Do not synthesize iOS or Android guidance until upstream provides equivalent knowledge-base facts, public API declarations, and guide blueprints.
Source resolution
Use the public repository by default:
https://github.com/contentful/optimization.git
Resolve sources in this order:
- An explicit local path supplied by the user.
- An existing reusable clone at
.docs/optimization-sdk-sync/repository. - A fresh clone of the official HTTPS repository into that cache.
The cache is repo-local working state for the sync process. It is not committed or distributed. Reusing it avoids cloning the public repository on every run while still allowing the skill to fetch and inspect an exact upstream commit.
For the default remote flow:
- Inspect the managed cache's origin and worktree status before checkout.
- Verify
originis exactly the official HTTPS repository before fetching. - If the origin differs or the cache has local changes, do not repoint, reset, delete, or clean it. Stop and report the conflict, or use a separately approved clean cache.
- Fetch the requested ref, defaulting to
main. - Resolve it to a full immutable commit SHA.
- Inspect a detached checkout of that SHA. Do not use
git pullor merge upstream history.
For an explicit local path:
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.
- 2d ago First seen · 227 lines · 64 tokens per session scan A e38de362a179
optimization-sdk-sync is a skill published in the GitHub repository contentful/skills (39 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 1,967 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
newsjack-detector
Monitor current news and reaction signals, then decide which are credible newsjacking opportunities for a client. Uses the local monitoring engine for evidence, but the skill owns PR judgment, brand safety, standing, decay, angle fit, and handoff.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
pr-calendar
Turn the Medialyst PR calendar feed into a brand-specific, lead-time-aware plan. Pull source-backed upcoming moments, keep only the few a brand has real standing to own, schedule backward from the event date, screen out tone-deaf hooks, and hand selected moments to angle and journalist prep ahead of time. The planned…
newsjack-triage
Consolidate freshness-gated newsjack signals and route them by client standing before angle generation. Collapses any remaining same-story duplicates, decides strong/partial/none standing with a journalist-shape sanity check, and sorts each story into pitchready, bigstory (always-surfaced suggestion), or watch. Never…
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…