Borrowing it
Nothing to install: this file belongs to jacob-dietle/context-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jacob-dietle/context-os/main/.claude/skills/epistemic-context-grounding/SKILL.mdgit clone --depth 1 https://github.com/jacob-dietle/context-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/jacob-dietle/context-os/epistemic-context-grounding)<a href="https://agentmods.dev/skills/jacob-dietle/context-os/epistemic-context-grounding"><img src="https://agentmods.dev/badge/skills/jacob-dietle/context-os/epistemic-context-grounding/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/jacob-dietle/context-os/epistemic-context-grounding"><img src="https://agentmods.dev/badge/skills/jacob-dietle/context-os/epistemic-context-grounding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 109 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 298 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 300 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 492 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00050 | $0.03427 |
| Opus 5 | $0.00025 | $0.01714 |
| Sonnet 5 | $0.00010 | $0.00685 |
| Haiku 4.5 | $0.00005 | $0.00343 |
Grade A, and why
epistemic-context-grounding 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 11d 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 — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epistemic Context Grounding
Methodology for grounding implementation decisions in domain knowledge through context sensitivity assessment, assumption enumeration, and falsifiability checking.
Why This Matters
The most common cause of wasted effort in AI-assisted work isn't bad code - it's building the wrong thing because you didn't check what documentation already describes the domain. A 2-5 minute grounding check prevents hours of rework.
When to Use This Skill
Apply this skill when:
- Starting implementation work on unfamiliar domain
- Task involves parsing, data models, or external integrations
- About to design a solution (BEFORE context-gap-analysis)
- Uncertainty exists about what documentation describes the domain
Do NOT use for:
- Simple bug fixes with obvious root cause
- Tasks where domain is already loaded in context
- Pure exploration/research (no implementation planned)
- When canonical docs were already read this session
Core Principles
1. Context Sensitivity Assessment
Classify task before designing:
LOW CONTEXT SENSITIVITY:
- Task is bounded, clear outcome
- Domain well-known (basic CRUD, standard patterns)
- Example: "Add a button to the UI"
HIGH CONTEXT SENSITIVITY:
- Task involves parsing, data formats, integrations
- Domain has canonical specs/docs
- Example: "Fix data pipeline" -> needs format knowledge
The formula: (Model : Scenario) * Context -> Output
Where:
- Model = Claude's capabilities
- Scenario = The specific task
- Context = Domain knowledge provided
- Output = Quality of solution
For HIGH context sensitivity tasks, missing context dramatically reduces output quality. For LOW context sensitivity tasks, context has minimal impact.
See references/context-sensitivity-model.md for full framework.
2. Domain Knowledge Query (Graph Traversal)
Search for specs, not just code:
SEARCH ORDER (adapt to your context OS structure):
1. specs/canonical/*.md - Blessed architecture docs
2. specs/{project}/*.md - Project-specific specs
3. **/CLAUDE.md - Navigation guides
4. **/README.md - Component documentation
5. knowledge_base/**/*.md - Knowledge graph nodes
What ships with it
3 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.
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.
- 11d ago First seen · 507 lines · 50 tokens per session scan A 37d2e9b1b124
epistemic-context-grounding is a skill published in the GitHub repository jacob-dietle/context-os (108 stars, last pushed 28d ago), licensed MIT. It adds 50 tokens to every session and 3,427 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…