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 Fusion-Data-Company/bristol-os --skill knowledge-packsgit clone --depth 1 https://github.com/Fusion-Data-Company/bristol-osWrote 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/fusion-data-company/bristol-os/knowledge-packs)<a href="https://agentmods.dev/skills/fusion-data-company/bristol-os/knowledge-packs"><img src="https://agentmods.dev/badge/skills/fusion-data-company/bristol-os/knowledge-packs/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/fusion-data-company/bristol-os/knowledge-packs"><img src="https://agentmods.dev/badge/skills/fusion-data-company/bristol-os/knowledge-packs.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 | $0.00079 | $0.00816 |
| Opus 5 | $0.00039 | $0.00408 |
| Sonnet 5 | $0.00016 | $0.00163 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
knowledge-packs 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 10d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Packs — tools & repos
This play makes Bristol OS more powerful by connecting the right tools and pulling in the right open-source knowledge. Two reference files live in bristol-os/catalog/:
TOOL-CATALOG.md— every recommended connector, tiered and mapped to plays.GITHUB-PACK.md— verified GitHub repos (skills, MCP servers, RE/finance/maps data).
Core behavior: recommend before you struggle
If a task would be materially better with a tool the user doesn't have, say so and offer to set it up — don't silently do a weaker job. Example: asked for rent comps with only web search, deliver what you can, then: "If you connect Yardi Matrix or I help Rob set up the free Census data server, I can make this much sharper — want that?"
Match the user to the right path
- Basic user (Sam, David, staff): only ever recommend Tier 0 + one-click first-party connectors (Tavily, Exa, Google Drive, Yardi if subscribed). Walk them through
Settings → Connectorsin plain English. NEVER ask them to install a GitHub MCP server. - Technical user (Rob or a helper): offer the full GitHub pack, including community MCP servers (Census, SEC EDGAR, FRED, Maps, Firecrawl). Point them to the repo READMEs and the "full real estate power setup" list in
GITHUB-PACK.md.
Setting up a first-party connector (any user)
- Identify the connector from
TOOL-CATALOG.mdand say what it'll do for them. - Steps: Claude desktop → Settings → Connectors → find it → Connect → sign in once.
- If it needs an API key (Tavily/Exa), point them to the signup and where to paste the key (see
onboarding/connector-setup.md). - After they confirm, update their
CLAUDE.md"connected tools" line so future sessions know it's available, and start using it.
Pulling from the GitHub pack (when the user has file access)
- Knowledge/skills repos (e.g.,
anthropics/skills,hesreallyhim/awesome-claude-code): you maygit cloneor fetch specific files into a localknowledge/folder to learn patterns or reuse a skill (like the official docx/xlsx skills for deliverables). Pull only what's relevant; don't clone everything. - MCP server repos: these are installed, not read. For a basic user, don't attempt it — instead produce a short, plain "Ask Rob to set this up" note naming the repo and what it unlocks. For a technical user, walk the repo README setup.
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.
- 10d ago First seen · 36 lines · 79 tokens per session scan A 07d09f132833
knowledge-packs is a skill published in the GitHub repository Fusion-Data-Company/bristol-os (1 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 816 once invoked, about $0.0004 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
trade-idea-generation
Systematic trade idea generation framework, fundamental quantitative and qualitative screening pipeline, catalyst-driven trade structuring, macro-to-micro idea translation, 20-60 day long-short portfolio management process.
chart-patterns
Chart pattern recognition, price action patterns, candlestick signal bars, pullback bar counting H1/H2/H3/H4, trend channels, micro channels, trading ranges, breakouts, major trend reversals 5-step sequence, wedges, double tops and bottoms, triangles, head and shoulders, climaxes, measured moves, support and…
trade-execution
Trade execution using price action setups, major trend reversal trading top and bottom, MTR failure continuation, strong bull and bear breakout trading, strong and weak channel trading strategies, trading range strategies, opening range swings, integration with gold.technicalsetups for setup matching and execution…
challenge
Adversarial verification of research theses — cross-run/cross-thesis contradiction via the entity index, pre-mortem (Klarman/Kahneman: assume the loss already happened, reverse the path), inversion (Munger: invert, always invert), and wrongif falsifiability review. ≈50-finding cap sorted by severity; content-derived…
converge
Append-only gap closure and the cadence engine for research theses. Evaluates artifact CURRENT state (never git history, never task checkboxes) against current pins and wrongif falsifiers, then appends a Convergence section to tasks.md re-proposing the gaps. A clean run leaves tasks.md byte-identical. Deterministic…
constitution
Scaffold and amend the L1 Investment Constitution — [ALLCAPS] placeholder bootstrap, SemVer bump rules, Sync Impact Report, MINOR/MAJOR re-examination dispatch after the gate-5 budget confirm. Thesis creation stays refused until ratification (Q83).