Agents Best Practices
DenisSergeevitch/agents-best-practices
A skill your agent uses when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain.
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself.
Install Context Engineering Review
$ npx skills add mohitagw15856/pm-claude-skills --skill context-engineering-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills context-engineering-review --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/context-engineering-review .claude/skills/context-engineering-review && 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-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/context-engineering-review into .claude/skills/context-engineering-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-review", 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/mohitagw15856/pm-claude-skills/tree/main/skills/context-engineering-reviewType 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 mohitagw15856/pm-claude-skills --skill context-engineering-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills context-engineering-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/context-engineering-review .agents/skills/context-engineering-review && 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-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/context-engineering-review into .agents/skills/context-engineering-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-review", 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 mohitagw15856/pm-claude-skills --skill context-engineering-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills context-engineering-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/context-engineering-review .cursor/skills/context-engineering-review && 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-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/context-engineering-review into .cursor/skills/context-engineering-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-review", 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/mohitagw15856/pm-claude-skills.git --path skills/context-engineering-review--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 mohitagw15856/pm-claude-skills --skill context-engineering-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills context-engineering-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/context-engineering-review .gemini/skills/context-engineering-review && 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-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/context-engineering-review into .gemini/skills/context-engineering-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-review", 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 mohitagw15856/pm-claude-skills context-engineering-reviewInstalls 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 mohitagw15856/pm-claude-skills --skill context-engineering-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/context-engineering-review .github/skills/context-engineering-review && 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-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/context-engineering-review into .github/skills/context-engineering-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-review", 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 mohitagw15856/pm-claude-skills --skill context-engineering-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills context-engineering-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/context-engineering-review .opencode/skills/context-engineering-review && 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-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/context-engineering-review into .opencode/skills/context-engineering-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-engineering-review", 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-review- GitHub stars
- 1.4k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 682 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself.
- Asked to review a system prompt and context assembly
- SKILL.md covers What This Skill Produces, Required Inputs, Review Method and Output Format, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Cut token usage without losing quality
What it does
Context Engineering Review is an agent skill from mohitagw15856/pm-claude-skills. Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut token usage without losing quality, debug an agent that ignores instructions, or audit how retrieval results, history, and tool definitions are packed into the window. Produces a context inventory with a keep/cut/restructure verdict per component, ordering and caching fixes, and a token budget. For wording-level prompt…
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Context engineering, Prompt engineering and LLM cost and token optimization. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Asked to review a system prompt and context assembly
- Cut token usage without losing quality
- Debug an agent that ignores instructions
- Audit how retrieval results
Example prompts
- “/context-engineering-review”
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. 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 Review loads about 1.4k tokens when it runs. Until then it costs about 143 tokens; SKILL.md has 682 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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 682 words, ~1,373 tokens.
Download SKILL.mdSave it as
.claude/skills/context-engineering-review/SKILL.md (or your agent's skills folder).- name
- context-engineering-review
- description
- Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut token usage without losing quality, debug an agent that ignores instructions, or audit how retrieval results, history, and tool definitions are packed into the window. Produces a context inventory with a keep/cut/restructure verdict per component, ordering and caching fixes, and a token budget. For wording-level prompt tuning use prompt-optimizer.
Context Engineering Review Skill
Most agent failures aren't model failures — they're context failures: instructions buried under retrieval dumps, stale history contradicting fresh facts, twelve tool definitions the task never needed. This skill audits the assembled window, not just the prompt text.
What This Skill Produces
- A context inventory: every component in the window, its size, and who put it there
- A keep / cut / restructure verdict per component, with the reasoning
- Ordering and cache-alignment fixes (stable prefix first, volatile content last)
- A token budget per component with an enforcement point
Required Inputs
Ask for (if not already provided):
- A real assembled context — an actual logged request (system prompt + messages + tools), not the template. If only the template exists, review that but flag that dynamic bloat is invisible
- The failure or goal — ignoring instructions? too expensive? inconsistent? slow?
- What varies per request (retrieval, history, user data) vs. what is static
- The model and its context limit, and current typical request size
Review Method
1. Inventory. List every component in window order: system prompt sections, tool definitions, retrieved documents, conversation history, few-shot examples, injected state. For each: token count (estimate if unlogged), static vs. dynamic, and owner.
2. Interrogate each component:
- Earning its tokens? Would removing it change outputs on real traffic? The honest test is ablation, not intuition.
- Right form? Raw dumps (full HTML, whole files, unabridged history) almost always beat down to summaries, excerpts, or references the agent can expand via a tool.
- Right position? Instructions that must win go in the system prompt; volatile data goes late; nothing critical hides in the middle of a long window.
- Fighting anything? Contradictions between sections (persona says terse, examples are verbose; old history asserts what retrieval now refutes) are the classic "ignores instructions" root cause.
3. Check the structural patterns:
- Cache alignment — a byte-stable prefix (system prompt, tools) with per-request content after it; anything dynamic inside the prefix (timestamps, user names) breaks caching every request.
- Tool sprawl — tools the task can't need this turn dilute selection accuracy; load narrow toolsets per task or defer rarely-used schemas.
- History policy — unbounded transcripts are the top silent cost driver; define truncation/summarisation and what must survive it.
- Retrieval discipline — cap chunks by relevance score, not by k; label each chunk's source so the model can weigh it.
4. Budget. Assign each component a token ceiling that sums comfortably under the limit at p95, and name where it's enforced (the assembly code, not hope).
Output Format
Show full SKILL.md (274 more words)Show less
Context Engineering Review: [feature/agent]
Reviewed: [a real request from date / the template]. Current size: [n] tokens typical, [n] p95, limit [n].
| # | Component | Tokens | Static? | Verdict | Fix |
|---|---|---|---|---|---|
| 1 | [system: persona] | ✓ | Keep | — | |
| 2 | [12 tool defs] | ✓ | Restructure | [narrow per task] | |
| 3 | [retrieval, k=20] | dyn | Cut to k≤8 by score |
Conflicts found: [each contradiction and which side should win]
Ordering / caching: [the reordered layout; what moves out of the stable prefix]
Token budget: [component → ceiling; enforcement point]. Projected size: [n] (−[x]%).
Verify: re-run [the eval suite / golden cases] after changes — cuts must be validated, not assumed safe (see prompt-regression-suite).
Quality Checks
- The review used at least one real assembled request, or explicitly flags it could not
- Every verdict has a reason tied to the stated failure/goal, not generic advice
- Cache-breaking dynamic content in the stable prefix is called out with its cost
- The token budget sums under the model limit at p95 including output headroom
- Recommended cuts come with a validation step before they ship
Anti-Patterns
- Do not review the prompt template and call it a context review — the bloat lives in the dynamic parts
- Do not recommend "shorten everything" — cutting the wrong 200 tokens costs more than keeping 2,000 idle ones
- Do not leave contradictions in place because each section "is fine alone" — the window is read as one document
- Do not treat more retrieval as more grounding — irrelevant chunks actively mislead
- Do not propose structure the assembly code can't enforce — a budget without an enforcement point is a wish
Example Trigger Phrases
- "Review a system prompt and context assembly."
- "Cut token usage without losing quality."
- "Debug an agent that ignores instructions."
- "Audit how retrieval results."
© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/context-engineering-review of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Context Engineering Review 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 Review this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Agents Best PracticesDenisSergeevitch/agents-best-practices | 2.4k | — | ~7.4k | Automated safety check: Pass | MIT | |
| Senior Prompt Engineeralirezarezvani/claude-skills | 28k | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Agent Experiencesingula-ai/alego | 109 | 1 repos | ~531 | Automated safety check: Pass | MIT | |
| SDK CoreVectorSpaceLab/AREX-Skill | 331 | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| Prompt EngineerJeffallan/claude-skills | 12k | — | ~1.5k | Automated safety check: Pass | MIT |
Similar skills
Senior Prompt Engineer
alirezarezvani/claude-skills
A skill your agent uses when the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent/tool configurations…
Agent Experience
singula-ai/alego
A skill your agent uses when writing or changing a model-facing tool definition (name, description, parameter schema, or its system-prompt section), and when designing skills, context loading, or…
SDK Core
VectorSpaceLab/AREX-Skill
A skill your agent uses for direct LiteLLM Python SDK work: chat/text completions, async calls, streaming, embeddings, structured outputs, tools, token/cost checks, caching, callbacks, import/smoke…
Prompt Engineer
Jeffallan/claude-skills
Designs, tests and refines LLM prompts: zero-shot, few-shot and chain-of-thought patterns, system prompts, structured output schemas and evaluation test suites.
Context Audit
undefined-ui/second-brain-os
Audit an agent's context layout against the four places: system prompt, tools, history, tail.
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Exit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Related
Categories
Questions about Context Engineering Review
What does Context Engineering Review do?
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Context Engineering Review is an agent skill from mohitagw15856/pm-claude-skills. Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself.
When should I use Context Engineering Review?
Context Engineering Review fits situations like: asked to review a system prompt and context assembly; cut token usage without losing quality; debug an agent that ignores instructions; audit how retrieval results.
How do I install Context Engineering Review in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill context-engineering-review -a claude-code`. Or copy the skill folder (skills/context-engineering-review in mohitagw15856/pm-claude-skills) into .claude/skills/context-engineering-review in your project. Claude Code loads it when a task matches its description.
How do I install Context Engineering Review in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill context-engineering-review -a codex`. Or copy the skill folder (skills/context-engineering-review in mohitagw15856/pm-claude-skills) into .agents/skills/context-engineering-review in your project. Codex loads it when a task matches its description.
Can I use Context Engineering Review 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 mohitagw15856/pm-claude-skills --skill context-engineering-review -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-review, .gemini/skills/context-engineering-review, .github/skills/context-engineering-review and .opencode/skills/context-engineering-review in your project.
What does Context Engineering Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Context Engineering Review is instructions for the agent only.
Does Context Engineering Review 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 Review 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 Review use?
Context Engineering Review 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 Review use?
About 1.4k tokens (SKILL.md is roughly 5.5k 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 Review?
Skills that share tags, products or a category with Context Engineering Review: Agents Best Practices (DenisSergeevitch/agents-best-practices, 2.4k stars), Senior Prompt Engineer (alirezarezvani/claude-skills, 28k stars), Agent Experience (singula-ai/alego, 109 stars) and SDK Core (VectorSpaceLab/AREX-Skill, 331 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Context Engineering Review?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.