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 reatlat/fullstory-claude-plugin --skill annotation-opsgit clone --depth 1 https://github.com/reatlat/fullstory-claude-pluginWrote 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/reatlat/fullstory-claude-plugin/annotation-ops)<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/annotation-ops"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/annotation-ops/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/reatlat/fullstory-claude-plugin/annotation-ops"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/annotation-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00848 |
| Opus 5 | $0.00025 | $0.00424 |
| Sonnet 5 | $0.00010 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
annotation-ops 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 10d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Annotation Ops
Create and manage annotations on the Fullstory timeline so you can see how deploys, experiments, and incidents correlate with changes in user behavior.
When This Runs
Invoked automatically when the user asks:
- "Mark the 3pm deploy on the timeline"
- "Add an annotation for the experiment we started yesterday"
- "Tag the incident window from 2-4pm today"
- "Show me annotatons from the last deploy"
The skill is user-invocable: false — it runs when general-analysis or weekly-digest references an annotation, or when the user explicitly asks to mark something.
What Annotations Are
Annotations are labeled time ranges on the Fullstory timeline. They're markers you set so that when viewing metrics, you can see: "Oh, the conversion drop started right when we deployed the new checkout."
Common annotation types:
- Deploy marker: A point in time when code was released
- Experiment start/end: The window an A/B test ran
- Incident window: The time range of a production issue
- Feature flag toggle: When a feature was turned on or off
- Marketing campaign: When an email blast or promotion ran
Workflow
Step 1: Clarify the annotation
When the user says "mark the deploy" or "tag the incident", ask or infer:
- Label: What should it say? (e.g., "v2.3.0 deploy", "Checkout experiment start", "API incident")
- Time: When did it start? (e.g., "3pm today", "yesterday at 2pm", "July 15 10:00 UTC")
- End time: For events with duration (incidents, experiments) — when did it end? For point-in-time events (deploys) — no end time or use start == end.
- Description (optional): Any extra context — what changed, who deployed, incident ticket link.
Step 2: Create the annotation
Call fullstory:create_annotation:
label: Human-readable namestart_time: ISO 8601 timestampend_time: ISO 8601 timestamp (omit for point-in-time events)description: Optional context
The tool creates the annotation on the Fullstory timeline and returns an annotation ID. Confirm to the user: "Annotation 'v2.3.0 deploy' created at July 15 15:00 UTC."
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.
- 10d ago First seen · 69 lines · 50 tokens per session scan A 50522268a6b7
annotation-ops is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 28d ago), licensed MIT. It adds 50 tokens to every session and 848 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
roblox-input
Use when handling Roblox keyboard, mouse, gamepad, touch, motion input, or cross-platform action binding.
roblox-lighting
Use for Roblox lighting, atmosphere, day/night, or post-processing effects.
roblox-performance
Use when profiling Roblox performance or diagnosing FPS, memory, network, mobile, or hot-path problems.
roblox-growth-design
Use for growth diagnosis, discovery, retention, onboarding, experiments, LiveOps, and packaging.
roblox-data
Use when implementing player data persistence with DataStore, session ownership, schemas, migrations, or save and load flows.
roblox-networking
Use when validating RemoteEvent or RemoteFunction arguments, adding rate limits, designing server-authoritative systems, or preventing exploits.