Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/GetStream/agent-skillsnpx agentmods add skills/getstream/agent-skills/stream-feeds-migrationWrote 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/getstream/agent-skills/stream-feeds-migration)<a href="https://agentmods.dev/skills/getstream/agent-skills/stream-feeds-migration"><img src="https://agentmods.dev/badge/skills/getstream/agent-skills/stream-feeds-migration/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/getstream/agent-skills/stream-feeds-migration"><img src="https://agentmods.dev/badge/skills/getstream/agent-skills/stream-feeds-migration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium Excessive Agency · line 38 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 81 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 272 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00208 | $0.05218 |
| Opus 5.5 | $0.00083 | $0.02087 |
| Sonnet 5.5 | $0.00042 | $0.01044 |
| Haiku 4.5 | $0.00021 | $0.00522 |
Grade A, and why
stream-feeds-migration 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 today.
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 — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stream Feeds - v2 to v3 sync mapping
Read first (every session): Glob
../stream/SKILL.mdand Read../stream/RULES.md(both ship with this skill). The Secrets rule governs every step below: the app secret never enters the conversation. RULES.md also carries the Peer skills procedure for installing and invoking any other pack skill on demand.
Produce the mapping object for an app's v2 -> v3 sync configuration by looking
at what the app's v2 data actually contains, rather than at what anyone believes
it contains.
One mapping serves both migration paths - the live syncer and the bulk exporter read the same configuration. Getting it right once fixes both; getting it wrong breaks both in the same way.
Workflow
1. Get credentials into the environment
You need the v2 app's API key and secret. The secret signs an HS256 JWT
locally, stamped with iat/exp so it expires five minutes after it is minted.
The secret itself is never written to the sample file, never echoed back, and
never sent anywhere except as that signature.
Per ../stream/RULES.md > Secrets, do not ask the user
to paste the secret into the chat, and never cat, grep, or Read a .env
file to find it. Ask them to export it themselves so it stays out of the
transcript:
! export STREAM_API_KEY=<v2 app key> STREAM_API_SECRET=<v2 app secret>
The ! prefix runs the command in the user's own session, so the value lands in
the environment without passing through the conversation. Confirm it took with a
presence check that never prints the value:
test -n "$STREAM_API_SECRET" && echo SECRET_SET || echo SECRET_MISSING
Do not proceed without a real key and secret. There is no useful analysis to do against a made-up app, and a wrong secret only produces a 403.
2. Pick the target
Default to production - https://api.stream-io-api.com. Use it unless the
user names a different environment (EU, dedicated, staging), in which case pass
--base-url <that URL>.
What ships with it
5 files 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.
- today Changed · +4 lines 700370cd6663
- 2d ago Changed · +135 lines · +58 tokens per session ae03f3471790
- 1mo ago First seen · 279 lines · 150 tokens per session scan A eaef6f5a8165
stream-feeds-migration is a skill published in the GitHub repository GetStream/agent-skills (20 stars, last pushed today), licensed Apache-2.0. It adds 208 tokens to every session and 5,218 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
api-reference
Memoria REST API endpoints, request/response formats, auth, rate limits. Use when calling or implementing API endpoints.
openloomi-api
OpenLoomi ships a local-first HTTP API served from the desktop app (port 3414, fallback 3515). All auth, Memory, AI, RAG, Loop, and Audit data live in a local SQLite database — your data stays on your machine and the OpenLoomi app is the source of truth. The only externally-routed auth path is the Composio OAuth…
magicbase
Use when an HTML micro-app needs MagicBase persistence, window.Magic.db row operations, current-user context through window.Magic.getContext, creators, owners, assignees, permissions, CRUD, forms, surveys, todos, dashboards, filters, statistics, exports, or any saved user data.
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. Use when building or reviewing Node.js, Express, or Next.js API routes and their data access.
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…