Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
Manages attention and evidence in long agent sessions. An agent skill from jamditis/claude-skills-journalism.
Install Context Engineering Fundamentals
$ npx skills add jamditis/claude-skills-journalism --skill context-engineering-fundamentals -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jamditis/claude-skills-journalism context-engineering-fundamentals --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .claude/skills && cp -r skills-src/dev-toolkit/skills/context-engineering-fundamentals .claude/skills/context-engineering-fundamentals && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "context-engineering-fundamentals" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/context-engineering-fundamentals into .claude/skills/context-engineering-fundamentals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-fundamentals", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/context-engineering-fundamentalsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jamditis/claude-skills-journalism --skill context-engineering-fundamentals -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jamditis/claude-skills-journalism context-engineering-fundamentals --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .agents/skills && cp -r skills-src/dev-toolkit/skills/context-engineering-fundamentals .agents/skills/context-engineering-fundamentals && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "context-engineering-fundamentals" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/context-engineering-fundamentals into .agents/skills/context-engineering-fundamentals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-fundamentals", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jamditis/claude-skills-journalism --skill context-engineering-fundamentals -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jamditis/claude-skills-journalism context-engineering-fundamentals --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/dev-toolkit/skills/context-engineering-fundamentals .cursor/skills/context-engineering-fundamentals && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "context-engineering-fundamentals" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/context-engineering-fundamentals into .cursor/skills/context-engineering-fundamentals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-fundamentals", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jamditis/claude-skills-journalism.git --path dev-toolkit/skills/context-engineering-fundamentals--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jamditis/claude-skills-journalism --skill context-engineering-fundamentals -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jamditis/claude-skills-journalism context-engineering-fundamentals --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/dev-toolkit/skills/context-engineering-fundamentals .gemini/skills/context-engineering-fundamentals && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "context-engineering-fundamentals" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/context-engineering-fundamentals into .gemini/skills/context-engineering-fundamentals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-fundamentals", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jamditis/claude-skills-journalism context-engineering-fundamentalsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jamditis/claude-skills-journalism --skill context-engineering-fundamentals -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .github/skills && cp -r skills-src/dev-toolkit/skills/context-engineering-fundamentals .github/skills/context-engineering-fundamentals && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "context-engineering-fundamentals" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/context-engineering-fundamentals into .github/skills/context-engineering-fundamentals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-fundamentals", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jamditis/claude-skills-journalism --skill context-engineering-fundamentals -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jamditis/claude-skills-journalism context-engineering-fundamentals --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/dev-toolkit/skills/context-engineering-fundamentals .opencode/skills/context-engineering-fundamentals && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "context-engineering-fundamentals" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/context-engineering-fundamentals into .opencode/skills/context-engineering-fundamentals/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-fundamentals", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
context-engineering-fundamentals- GitHub stars
- 417
- Token cost
- ~1k tokens
- SKILL.md length
- 455 words
- Files
- 2
- Skills in repo
- 53
- Repo updated
- First seen
- Licence
- MIT
At a glance
Manages attention and evidence in long agent sessions. An agent skill from jamditis/claude-skills-journalism.
- Works in 5 steps: Lost-in-middle → Context poisoning → Context distraction → …
- Lost instructions
- SKILL.md covers Core concept, The lost-in-middle effect, Context degradation patterns and Measure before compressing, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Context Engineering Fundamentals is an agent skill from jamditis/claude-skills-journalism. Manages attention and evidence in long agent sessions. Use for lost instructions, dropped evidence, or large multi-agent contexts.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Agent Workflows, covering Context engineering. The repository describes itself as: Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more. The licence is MIT.
When your agent uses it
- Lost instructions
- Dropped evidence
- Large multi-agent contexts
Example prompts
- “Use the context-engineering-fundamentals skill to manage attention and evidence in long agent sessions. An agent skill from…”
- “/context-engineering-fundamentals”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e3e2172. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Context Engineering Fundamentals loads about 1k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 455 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from jamditis/claude-skills-journalism at commit e3e2172, republished under its MIT licence (© jamditis). 455 words, ~1,040 tokens.
Download SKILL.mdSave it as
.claude/skills/context-engineering-fundamentals/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- context-engineering-fundamentals
- description
- Manages attention and evidence in long agent sessions. Use for lost instructions, dropped evidence, or large multi-agent contexts.
Context engineering fundamentals
Context engineering is the practice of managing an LLM's limited attention budget. Use this skill to keep instructions, evidence, and state available during long work.
Core concept
Context windows are constrained by attention mechanics, not only token capacity. A large context limit does not guarantee equal use of every item.
The lost-in-middle effect
The "Lost in the Middle" experiments show that retrieval quality can change with information position. The result depends on the model, task, context length, and number of documents.
| Position | Common test result |
|---|---|
| Beginning | Often easier to retrieve |
| Middle | Can be harder to retrieve |
| End | Often benefits from recency |
Implication: Keep critical constraints easy to find and repeat them near the decision that uses them. Do not assume position alone predicts recall.
Context degradation patterns
1. Lost-in-middle
Information in the middle of long context gets lower attention weight.
Mitigation: Structure with explicit sections. Put critical constraints at start AND end.
2. Context poisoning
Errors compound when incorrect information enters context (from tool outputs, summaries, or earlier mistakes).
Mitigation: Validate intermediate outputs. Don't blindly trust previous responses.
3. Context distraction
Irrelevant information forces attention allocation away from relevant content. Models can't "skip" irrelevant context.
Mitigation: Be selective about what goes into context. More isn't better.
4. Context confusion
Multiple task types or conflicting instructions create ambiguous responses.
Mitigation: One task per interaction when possible. Clear task boundaries.
5. Context clash
Contradictory information from multiple sources causes derailing conflicts.
Mitigation: Resolve contradictions explicitly before asking Claude to use the information.
Show full SKILL.md (202 more words)Show less
Measure before compressing
Do not use a fixed token threshold to decide when context is reliable. Measure retrieval and reasoning quality on your own model and task. Test representative evidence at several positions, then compare the result before and after summarization.
Compress only when the measured result or the agent's behavior shows a problem. Preserve exact constraints, decisions, source links, unresolved questions, and verification evidence.
Mitigation strategies
Write externally
Do not rely on the agent to remember across turns. Write important state to files, but agree the path with the user first. Prefer a gitignored workspace so you never overwrite project-owned content:
With the user's approval, after each major step write progress to an agreed scratch file (for example a gitignored PROGRESS.md or a path they choose)
Before starting, read that file back to restore contextSelect carefully
Filter irrelevant context before loading:
Instead of: "Here are all 50 files, find the bug"
Do: "Here are the 3 files involved in the error"Compress strategically
Summarize while maintaining signal:
Instead of: Full 1000-line file
Do: Key functions and their signatures, with context on the specific areaIsolate contexts
For complex tasks, use subagents with focused contexts rather than one agent with everything.
Signs of context degradation
| Symptom | Likely cause |
|---|---|
| Ignores earlier instructions | Lost-in-middle or context too long |
| Contradicts itself | Context confusion or clash |
| Repeats information you gave | Attention not reaching that content |
| Misses obvious details | Context distraction |
| Gets progressively worse | Context poisoning from errors |
References
- "Lost in the Middle" (Liu et al., 2023) - Position effects in long context
- "Needle in a Haystack" benchmark - Context retrieval testing
- RULER benchmark - Multi-hop reasoning over long context
© jamditis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in dev-toolkit/skills/context-engineering-fundamentals of jamditis/claude-skills-journalism.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit e3e2172
Compare with similar skills
Context Engineering Fundamentals next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Context Engineering Fundamentals this skilljamditis/claude-skills-journalism | 417 | — | ~1k | Automated safety check: Pass | MIT | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence | |
| Memori Long-Term MemoryMemoriLabs/Memori | 17k | — | ~2k | Automated safety check: Notes | Custom licence | |
| Picoclaw Skill Creatorsipeed/picoclaw | 30k | — | ~4.4k | Automated safety check: Pass | MIT | |
| ccc Semantic Code Searchcocoindex-io/cocoindex-code | 2.8k | — | ~938 | Automated safety check: Pass | Apache-2.0 | |
| Context Mode for Antigravity CLImksglu/context-mode | 26k | — | ~850 | Automated safety check: Pass | Custom licence |
Similar skills
Memori Long-Term Memory
MemoriLabs/Memori
Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.
Picoclaw Skill Creator
sipeed/picoclaw
Guidance for creating, updating and reviewing Picoclaw skills, from the SKILL.md structure to organizing bundled scripts, references and assets.
ccc Semantic Code Search
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
Context Mode for Antigravity CLI
mksglu/context-mode
Routing rules for using context-mode MCP tools in Antigravity CLI: sandboxed code runs, file analysis, indexed search and web fetches that keep large output out of the conversation.
Token Optimizer
alexgreensh/token-optimizer
Audit a Claude Code or Codex setup for context-window waste, then fix it and measure the savings.
More from jamditis/claude-skills-journalism
All 53 skills in this repoWeb Design Picker
jamditis/claude-skills-journalism
A skill your agent uses when creating distinct website directions, a client review picker, asset catalog, previews, and Cloudflare-ready handoffs.
Okf Wiki
jamditis/claude-skills-journalism
Builds an Open Knowledge Format (OKF) knowledge base from existing docs, notes, or a repo.
Private Secret Scanning
jamditis/claude-skills-journalism
Local Gitleaks scans for staged changes, push ranges, and full history in private repos, with redacted reports.
Data Journalism
jamditis/claude-skills-journalism
Acquire, clean, analyze, verify, visualize, and explain data for journalism.
Document Design
jamditis/claude-skills-journalism
Creates print-ready HTML that exports to PDF. An agent skill from jamditis/claude-skills-journalism.
Using Superjawn
jamditis/claude-skills-journalism
Establishes how to find and use skills, requiring Skill tool invocation before any response.
Related
Categories
Questions about Context Engineering Fundamentals
What does Context Engineering Fundamentals do?
Manages attention and evidence in long agent sessions. An agent skill from jamditis/claude-skills-journalism. Context Engineering Fundamentals is an agent skill from jamditis/claude-skills-journalism. Manages attention and evidence in long agent sessions.
When should I use Context Engineering Fundamentals?
Context Engineering Fundamentals fits situations like: lost instructions; dropped evidence; large multi-agent contexts.
How do I install Context Engineering Fundamentals in Claude Code?
Run `npx skills add jamditis/claude-skills-journalism --skill context-engineering-fundamentals -a claude-code`. Or copy the skill folder (dev-toolkit/skills/context-engineering-fundamentals in jamditis/claude-skills-journalism) into .claude/skills/context-engineering-fundamentals in your project. Claude Code loads it when a task matches its description.
How do I install Context Engineering Fundamentals in Codex?
Run `npx skills add jamditis/claude-skills-journalism --skill context-engineering-fundamentals -a codex`. Or copy the skill folder (dev-toolkit/skills/context-engineering-fundamentals in jamditis/claude-skills-journalism) into .agents/skills/context-engineering-fundamentals in your project. Codex loads it when a task matches its description.
Can I use Context Engineering Fundamentals in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jamditis/claude-skills-journalism --skill context-engineering-fundamentals -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-engineering-fundamentals, .gemini/skills/context-engineering-fundamentals, .github/skills/context-engineering-fundamentals and .opencode/skills/context-engineering-fundamentals in your project.
What does Context Engineering Fundamentals need to run?
SKILL.md names no scripts, command-line tools or credentials: Context Engineering Fundamentals is instructions for the agent only.
Does Context Engineering Fundamentals access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Context Engineering Fundamentals safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Context Engineering Fundamentals use?
Context Engineering Fundamentals is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Context Engineering Fundamentals use?
About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Context Engineering Fundamentals?
Skills that share tags, products or a category with Context Engineering Fundamentals: Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Memori Long-Term Memory (MemoriLabs/Memori, 17k stars), Picoclaw Skill Creator (sipeed/picoclaw, 30k stars) and ccc Semantic Code Search (cocoindex-io/cocoindex-code, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Context Engineering Fundamentals?
jamditis (a GitHub user) maintains it in jamditis/claude-skills-journalism, which has 417 GitHub stars. The repository holds 53 skills in this directory. The repository was last updated on October 4, 2026.
Source: jamditis/claude-skills-journalism on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.