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 blackmo18/realm --skill realm-factsgit clone --depth 1 https://github.com/blackmo18/realmWrote 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/blackmo18/realm/realm-facts)<a href="https://agentmods.dev/skills/blackmo18/realm/realm-facts"><img src="https://agentmods.dev/badge/skills/blackmo18/realm/realm-facts/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/blackmo18/realm/realm-facts"><img src="https://agentmods.dev/badge/skills/blackmo18/realm/realm-facts.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 | $0.00127 | $0.01447 |
| Opus 5.5 | $0.00051 | $0.00579 |
| Sonnet 5.5 | $0.00025 | $0.00289 |
| Haiku 4.5 | $0.00013 | $0.00145 |
Grade A, and why
realm-facts 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 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.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
realm-facts
Team knowledge facts, GitLab-reviewed, Teams-notified, agent-ingestable. Script owns state; LLM interviews and judges.
Host invocation: Claude Code and Gemini use /realm-facts; Codex uses $realm-facts.
Resolve realmFactsSkillDir to the directory containing this SKILL.md; every
fragment uses <realmFactsSkillDir>/scripts/facts.py and never assumes a host-specific install root.
Syntax
/realm-facts forge # connect this repo to a central facts repo
/realm-facts new <domain> <id> # interactively author a draft fact
/realm-facts link <id> --related <id2> # relate two facts
/realm-facts submit <id> # branch + MR + Teams notify
/realm-facts review <id> [--approve | --request-changes "..."]
/realm-facts sync # pull latest approved facts
/realm-facts recall <query> # search facts
/realm-facts ingest <id> [--bundle impl|context|full] # FACT_BUNDLE for coding agents
When to Use
| Trigger | Example |
|---|---|
| First time in this repo | "connect facts", /realm-facts forge |
| Document a team decision/behavior | /realm-facts new platform jwt-token-rotation |
| Relate two facts | /realm-facts link jwt-token-rotation --related session-refresh-policy |
| Ready for team review | /realm-facts submit jwt-token-rotation |
| Asked to review a fact MR | /realm-facts review jwt-token-rotation |
| Pull latest after Teams approval notice | /realm-facts sync |
| "What do we know about X?" | /realm-facts recall jwt |
| Hand a fact to a coding agent | /realm-facts ingest jwt-token-rotation --bundle impl |
When NOT to Use
- Querying this project's own architecture/ADR history →
/realm-recall(different store: vault, not facts repo) - Investigating live code behavior →
/realm-fathom - No facts repo connected yet →
/realm-facts forgefirst (every other subskill guards on this)
Routing
What ships with it
14 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.
- agents/openai.yaml 237 B
- forge/PROCEDURE.md 2.2 KB
- ingest/PROCEDURE.md 1.3 KB
- link/PROCEDURE.md 1.4 KB
- new/PROCEDURE.md 2.6 KB
- recall/PROCEDURE.md 1.7 KB
- references/bundle-format.md 1.6 KB
- references/fact-schema.md 3.4 KB
- references/mr-flow.md 2.3 KB
- review/PROCEDURE.md 2.6 KB
- scripts/facts.py 23 KB runs code
- scripts/test_facts.py 14 KB runs code
- submit/PROCEDURE.md 1.6 KB
- sync/PROCEDURE.md 1.0 KB
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 · 115 lines · 127 tokens per session scan A 316c7a35ca19
realm-facts is a skill published in the GitHub repository blackmo18/realm (0 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 1,447 once invoked, about $0.0005 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 2026-10-02.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…