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 PostHog/posthog-foss --skill announcing-behavior-changesgit clone --depth 1 https://github.com/PostHog/posthog-fossWrote 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/posthog/posthog-foss/announcing-behavior-changes)<a href="https://agentmods.dev/skills/posthog/posthog-foss/announcing-behavior-changes"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/announcing-behavior-changes/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/posthog/posthog-foss/announcing-behavior-changes"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/announcing-behavior-changes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 120 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Prompt Injection · line 34 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 37 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 38 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 39 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00197 | $0.02164 |
| Opus 5.5 | $0.00079 | $0.00866 |
| Sonnet 5.5 | $0.00039 | $0.00433 |
| Haiku 4.5 | $0.00020 | $0.00216 |
Grade A, and why
announcing-behavior-changes 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Announcing behavior changes
Some fixes correct wrong behavior but change what a user sees. The number moves, the chart shifts, the count drops. Nothing is broken, but from the user's side it is indistinguishable from a regression, and they have no way to find out why.
An in-app change notice closes that gap: it appears where the user sees the different result, says what changed, and then goes away.
The reference implementation is frontend/src/queries/nodes/DataVisualization/Components/SqlInsightDateFilterNotice.tsx, shipped in commit 76f2905222a alongside the backend change it explains. Read it before writing a new one — it is 60 lines and it is the whole pattern.
First: does this change need a notice?
Most changes do not. A notice that fires for people it does not concern is worse than no notice, because it teaches everyone to dismiss banners without reading them. Ship one only when all four hold.
- A user who does nothing sees something different. Not a new feature, not a change they opted into behind a flag.
- They cannot work out why from the screen. If the UI already explains it, the UI is the notice.
- The difference is big enough to notice. A rounding change in the fourth decimal is not.
- You can identify who is affected, in code. See below — this is the one that usually fails.
The narrowing test
Write the predicate first. If you cannot express "this user is affected" as a function of state the client already has, you are about to show a banner to everyone about something that concerns a minority.
When that happens, pick a different mechanism instead of widening the blast radius:
| Situation | Use instead |
|---|---|
| Only the backend can tell who is affected | A per-object field on the API response, rendered where that object is shown. Action.selector_warning (#80653) is the model. |
| The condition is permanent, not a one-time transition | Same — a computed warning, not a time-boxed notice. |
| Everyone is affected but the change is minor | Changelog only. |
| The old behavior was plainly broken and the new one is self-evidently right | Nothing. An error that stops happening needs no announcement. |
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 9bcd7305ff98
- 1mo ago First seen · 139 lines · 197 tokens per session scan A 3115c30871c6
announcing-behavior-changes is a skill published in the GitHub repository PostHog/posthog-foss (724 stars, last pushed today), licensed MIT. It adds 197 tokens to every session and 2,164 once invoked, about $0.0008 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…