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 phenomenoner/ai-agent-thinkroom --skill thinkroom-installgit clone --depth 1 https://github.com/phenomenoner/ai-agent-thinkroomWrote 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/phenomenoner/ai-agent-thinkroom/thinkroom-install)<a href="https://agentmods.dev/skills/phenomenoner/ai-agent-thinkroom/thinkroom-install"><img src="https://agentmods.dev/badge/skills/phenomenoner/ai-agent-thinkroom/thinkroom-install/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/phenomenoner/ai-agent-thinkroom/thinkroom-install"><img src="https://agentmods.dev/badge/skills/phenomenoner/ai-agent-thinkroom/thinkroom-install.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 | $0.00010 | $0.00559 |
| Opus 5 | $0.00005 | $0.00280 |
| Sonnet 5 | $0.00002 | $0.00112 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
thinkroom-install 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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinkroom install
Use this skill when installing, checking, or removing Thinkroom's managed Agent Skills bundle.
Install
Use the host profile when available:
# Codex App / CLI / IDE
thinkroom skills install --profile codex
thinkroom skills status --profile codex
# Hermes Agent default profile; pair with `hermes --profile default ...`
unset HERMES_HOME
thinkroom skills install --profile hermes
thinkroom skills status --profile hermes
Codex resolves to $HOME/.agents/skills. Hermes resolves to $HERMES_HOME/skills, defaulting to
~/.hermes/skills. For a named Hermes profile, set the non-empty absolute
HERMES_HOME="$HOME/.hermes/profiles/<profile-name>" for every Thinkroom command and use
hermes --profile <profile-name> ... for MCP registration and verification. Never rely on sticky
profile state. For another Agent Skills-compatible host, use exactly one explicit target:
thinkroom skills install --target <skill-root>
thinkroom skills status --target <skill-root>
The managed projection contains:
thinkroom-triggerthinkroom-operatethinkroom-install
Safety contract
- Installation is idempotent: managed files that still match are classified
EXACT. - New managed files are classified
ADD. - Exact files owned by the allowlisted pre-profile v0.2 receipt are classified
UPDATEwhen the current bundle replaces them. The installer migrates only that known receipt and exact payload set. - Existing unmanaged, missing-after-receipt, or modified managed files are
DIVERGED. - Never overwrite a
DIVERGEDtarget. Inspect and reconcile it outside the installer. - Keep the generated
.thinkroom/skills-receipt-v1.json; status and uninstall use it to verify ownership and hashes.
Remove
Check status first, then remove only the exact managed projection:
thinkroom skills status --target <skill-root>
thinkroom skills uninstall --target <skill-root>
The equivalent profile commands are supported for Codex and Hermes. Do not pass --profile and
--target together.
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.
- 4d ago Changed · +1 lines e2c1575a1f54
- 9d ago First seen · 70 lines · 10 tokens per session scan A 74d1900deb32
thinkroom-install is a skill published in the GitHub repository phenomenoner/ai-agent-thinkroom (2 stars, last pushed 3d ago), licensed MIT. It adds 10 tokens to every session and 559 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
hunt-fastapi
Hunt FastAPI-specific vulnerabilities: dependency injection gaps, Pydantic coercion, and OpenAPI mining.
research-intelligence
Use when a Hermes agent must perform public-source research, source scouting, evidence grading, competitor/tool comparison, community-signal analysis, or decision-ready brief writing without private data or credentials.
youtube-research-pack
Use when a Hermes researcher must search public YouTube, inspect videos/channels/playlists, collect subtitles, analyze public signals, or run a bounded YouTube intelligence workflow without cookies or private data.
markitdown-document-ingestion
Convert public research documents and mixed file formats into Markdown before evidence review. Use for PDF, DOCX, PPTX, XLSX, HTML, CSV/JSON/XML, EPUB, ZIP bundles, and document intake before summaries, source ledgers, or research briefs.
codeflow-adoption-router
Route the current job to the right Codeflow surface without overclaiming hosted, write-capable MCP, or published plugin support.
link-curator-dashboard
Maintain and debug the link-curator web dashboard (port 8090). Separate process from the official Hermes dashboard.