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 LucasSantana-Dev/sharekit --skill streamer-modegit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWrote 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/lucassantana-dev/sharekit/streamer-mode)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/streamer-mode"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/streamer-mode/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/lucassantana-dev/sharekit/streamer-mode"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/streamer-mode.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 | $0.00106 | $0.01338 |
| Opus 5.5 | $0.00042 | $0.00535 |
| Sonnet 5.5 | $0.00021 | $0.00268 |
| Haiku 4.5 | $0.00011 | $0.00134 |
Grade B, and why
streamer-mode scanned grade B with 3 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Default: silent defer.** Append the finding to `~/.claude/streamer-findings/<YYYY-MM-DD>.md` via redirected shell write (never Write-tool preview, never echo the content), keeping finding details masked per rule 5. A Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
2. **Never open sensitive files on screen.** Read/cat output is visible. Patterns: `.env*`, `*.pem`, `*.key`, `id_rsa*`, `.pgpass`, `.netrc`, `.npmrc`, `.aws/credentials`, `kubeconfig`, anything named `secret*`/`credenti Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Never run commands that print secrets or network identity.** Full table with safe alternatives: `references/dangerous-commands.md`. Headline bans: `env`, `printenv`, `echo $ANY_SECRET`, `cat .env*`, `git remote -v`, How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Streamer Mode
Everything the agent prints — tool output, file reads, command results, error messages — is visible to a live audience. Treat the terminal as a public broadcast until the user says the stream is over.
Use When
- User announces they are streaming, screen sharing, recording, presenting, or demoing.
- User asks for "streamer mode", "safe mode for stream", "hide secrets while I share my screen".
Do Not Use When
- Auditing a repo for leaked secrets (use
security-audit/secure). - Redacting data in files or commits (that is content work, not a session mode).
Activation
- Confirm mode is ON in one short line. Stays on until user says "stop streamer mode" / "stream over" / "done streaming".
- Run the pre-flight sweep SILENTLY (output to file, never stdout) and report only pass/fail per item, never values:
.env*or credential-pattern files in cwd? (lscheck only — never open them)- Git remotes with embedded tokens? (
git config --get-regexp 'remote\..*\.url' | grep -q 'https://.*@': report "1 remote has an embedded token, fix after stream"; never print or store the URL) - Shell prompt / OS notifications likely exposing hostname or messages? Remind once: enable OS Do-Not-Disturb, Discord streamer mode.
Core Rules (while ON)
- Never run commands that print secrets or network identity. Full table with safe alternatives:
references/dangerous-commands.md. Headline bans:env,printenv,echo $ANY_SECRET,cat .env*,git remote -v,curl -v,docker inspect(unfiltered),kubectl get/describe secret,aws configure list,aws sts get-caller-identity(unfiltered; the exit-code-only check with both streams suppressed is the documented exception),gcloud auth list,history,ps aux,ifconfig/ipconfig/netstat(IPs). - Never open sensitive files on screen. Read/cat output is visible. Patterns:
.env*,*.pem,*.key,id_rsa*,.pgpass,.netrc,.npmrc,.aws/credentials,kubeconfig, anything namedsecret*/credential*. Existence checks (test -f) and counts (grep -c) are fine. - Check existence, not value:
test -n "$VAR" && echo setinstead ofecho $VAR. - Redirect verbose output to file, grep narrowly:
cmd > /tmp/out 2>&1then extract only the non-sensitive line needed. - Mask anything sensitive you must mention:
sk-ab***,<server-ip>,<internal-host>,<client>. Applies to IPs (public AND private), hostnames, MAC addresses, email addresses, cloud account IDs, DB connection strings, JWT contents, client names in file paths. - Error output is a leak vector. If a command fails, summarize the error in your own words; do not paste raw traces that contain hosts, paths with client names, or tokens.
- Prefer SSH-style references and placeholders in examples — never real remotes, real accounts, real endpoints.
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.
- 1mo ago First seen · 78 lines · 106 tokens per session scan B 873d25c1e198
streamer-mode is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 1,338 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 3 findings (asks for root, reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
loongsuite-pilot-insight
A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.