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 abm9111/chamber --skill chamber-checkgit clone --depth 1 https://github.com/abm9111/chamberWrote 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/abm9111/chamber/chamber-check)<a href="https://agentmods.dev/skills/abm9111/chamber/chamber-check"><img src="https://agentmods.dev/badge/skills/abm9111/chamber/chamber-check/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/abm9111/chamber/chamber-check"><img src="https://agentmods.dev/badge/skills/abm9111/chamber/chamber-check.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 | $0.00070 | $0.00827 |
| Opus 5.5 | $0.00028 | $0.00331 |
| Sonnet 5.5 | $0.00014 | $0.00165 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
chamber-check 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 2d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check claims against the user's notes
Chamber confirms that every number, capitalised name, domain, file name and count in a claim occurs in the note it came from. The check runs on the user's machine, with no model and no network.
When
- Before you state a figure, name, date or file name you read in the user's notes.
- When the user asks "is that actually in my notes?" about something you said. Check the earlier answer claim by claim.
How
- Split the answer into single factual claims. One claim per sentence.
- Call
chamber_checkwith each claim and the note it came from: the absolute path you read, afile.md#p3ref, or a passage id. - Report each result by its label, and read the lines under it, which say why:
SUPPORTED: the recognised terms occur in that note.TERMS_ABSENT: the note lacks the terms listed. Do not state the claim as fact.NO_TERMS: the claim has nothing Chamber can check. Nothing was verified; do not call it supported.NOT_FOUND: a cited source could not be read. The line under it says why: outside the declared folders, excluded, too large, empty, or missing. Do not tell the user the note does not exist unless that line says so.STALE: the note on disk no longer matches the index. Not judged.NO_SOURCE: you cited nothing. Cite the note and check again.
What a pass does not prove
SUPPORTED is string matching. A negated or reversed sentence built from the
note's own words still passes. Lowercase names and ordinary words are not
checked. Do not tell the user a claim is "verified" or "true"; say its terms
occur in the note.
If the chamber_check tool is missing
Chamber is not connected. Tell the user, and do not imitate the check by reading the note yourself and calling it verified.
- If the user has not installed it (Claude Code 2.1.275 or later):
/plugin install chamber --marketplace abm9111/chamber - If the plugin is installed, its server failed to start. Common causes: Node
older than 22.5 (Chamber needs
node:sqlite), no notes folder set, or a notes folder that is not an absolute path (the plugin's launcher refuses it with a line that names the fix); run/plugin configure chamber@chamber./mcpshows the server's error. - If
chamber_checkis listed twice, a server added by hand withclaude mcp add chamberis running beside the plugin's. Use the plugin's, and tell the user to runclaude mcp remove chamber. - A plugin from a third-party marketplace is not updated by itself. To get a
newer Chamber, the user turns on auto-update for the chamber marketplace in
/plugin, or runsclaude plugin update chamber@chamber. - Outside Claude Code, any MCP host:
npx -y @bu7umaid/[email protected] mcp --notes /absolute/path/to/NotesIn Codex:codex mcp add chamber -- npx -y @bu7umaid/[email protected] mcp --notes /absolute/path/to/Notes
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.
- 2d ago First seen · 63 lines · 70 tokens per session scan A b66295e37e6c
chamber-check is a skill published in the GitHub repository abm9111/chamber (3 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 827 once invoked, about $0.0003 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 2026-10-26.
Other skills, from other repositories
enzyme-sqlite-source
Connect an unfamiliar SQLite database to Enzyme without changing the source data. Inspect the database, decide which query columns represent identity, people, time, content, and folders, show real examples for approval, save a workspace program in the Enzyme language, and verify init and refresh. Use for email…
enzyme-workspace-setup
Set up or check Enzyme in a Markdown workspace. Use for first setup, re-setup, diagnosis, or requested cleanup; existing Enzyme files do not prove setup is complete. Write settings from the user's own map of their notes, review them with the user, demonstrate an answer from real notes, and repair only an evidenced…
enzyme
Use Enzyme in an already activated Obsidian, Markdown, or Hermes workspace for working-memory retrieval, source-grounded exploration, search by keyword and meaning, runtime note-writing, and refresh. If the workspace is not initialized, follow the first-time setup section before normal retrieval.
llm-wiki
Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.
wiki-build
A tool for building or rebuilding a local wiki from all source files in a vault, which is a folder used to store source material. It creates structured pages, layered indexes, logs, and cross-links.
remotion
Molio's builtin skill for MAKING a video from any source — wiki notes, articles, scripts, product info, or a brief — and rendering it to MP4. Use whenever the user wants to create/produce a video: a product demo, promo, trailer, intro, explainer, motion graphic, kinetic typography, social clip, or animated logo — even…