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.
A skill your agent uses when an agent prompt, tool schema, policy, or handoff needs to get clearer, safer, easier to trigger, cheaper in context, or measurable against real behavior.
Install Octocode Prompt Optimizer
$ npx skills add bgauryy/octocode --skill octocode-prompt-optimizer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bgauryy/octocode octocode-prompt-optimizer --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/bgauryy/octocode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/octocode-prompt-optimizer .claude/skills/octocode-prompt-optimizer && 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 "octocode-prompt-optimizer" agent skill from https://github.com/bgauryy/octocode/tree/main/skills/octocode-prompt-optimizer into .claude/skills/octocode-prompt-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "octocode-prompt-optimizer", 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/bgauryy/octocode/tree/main/skills/octocode-prompt-optimizerType 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 bgauryy/octocode --skill octocode-prompt-optimizer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bgauryy/octocode octocode-prompt-optimizer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bgauryy/octocode.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/octocode-prompt-optimizer .agents/skills/octocode-prompt-optimizer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "octocode-prompt-optimizer" agent skill from https://github.com/bgauryy/octocode/tree/main/skills/octocode-prompt-optimizer into .agents/skills/octocode-prompt-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "octocode-prompt-optimizer", 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 bgauryy/octocode --skill octocode-prompt-optimizer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bgauryy/octocode octocode-prompt-optimizer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bgauryy/octocode.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/octocode-prompt-optimizer .cursor/skills/octocode-prompt-optimizer && 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 "octocode-prompt-optimizer" agent skill from https://github.com/bgauryy/octocode/tree/main/skills/octocode-prompt-optimizer into .cursor/skills/octocode-prompt-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "octocode-prompt-optimizer", 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/bgauryy/octocode.git --path skills/octocode-prompt-optimizer--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 bgauryy/octocode --skill octocode-prompt-optimizer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bgauryy/octocode octocode-prompt-optimizer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bgauryy/octocode.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/octocode-prompt-optimizer .gemini/skills/octocode-prompt-optimizer && 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 "octocode-prompt-optimizer" agent skill from https://github.com/bgauryy/octocode/tree/main/skills/octocode-prompt-optimizer into .gemini/skills/octocode-prompt-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "octocode-prompt-optimizer", 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 bgauryy/octocode octocode-prompt-optimizerInstalls 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 bgauryy/octocode --skill octocode-prompt-optimizer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bgauryy/octocode.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/octocode-prompt-optimizer .github/skills/octocode-prompt-optimizer && 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 "octocode-prompt-optimizer" agent skill from https://github.com/bgauryy/octocode/tree/main/skills/octocode-prompt-optimizer into .github/skills/octocode-prompt-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "octocode-prompt-optimizer", 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 bgauryy/octocode --skill octocode-prompt-optimizer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bgauryy/octocode octocode-prompt-optimizer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bgauryy/octocode.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/octocode-prompt-optimizer .opencode/skills/octocode-prompt-optimizer && 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 "octocode-prompt-optimizer" agent skill from https://github.com/bgauryy/octocode/tree/main/skills/octocode-prompt-optimizer into .opencode/skills/octocode-prompt-optimizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "octocode-prompt-optimizer", 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
octocode-prompt-optimizer- GitHub stars
- 949
- Token cost
- ~1k tokens
- SKILL.md length
- 474 words
- Files
- 19 (incl. references)
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when an agent prompt, tool schema, policy, or handoff needs to get clearer, safer, easier to trigger, cheaper in context, or measurable against real behavior.
- An agent prompt
- SKILL.md covers Lobby rules and gates, Smart routes — load only what…, Related routes and Done gate
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Handoff needs to get clearer
What it does
Octocode Prompt Optimizer is an agent skill from bgauryy/octocode. Use when an agent prompt, tool schema, policy, or handoff needs to get clearer, safer, easier to trigger, cheaper in context, or measurable against real behavior. For SKILL.md folder install/review/structure, use octocode-skills.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 19 other files, including reference files (for example `README.md`, `references/agent-communication.md` and `references/attention.md`).
It sits in AI & LLM Engineering, covering Prompt engineering. It works with Model Context Protocol and GitHub. The repository describes itself as: Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI. The licence is MIT.
When your agent uses it
- An agent prompt
- Handoff needs to get clearer
- Easier to trigger
- Cheaper in context
Example prompts
- “/octocode-prompt-optimizer”
What it can do on your machine
Read from SKILL.md and the folder at commit c265e3f. 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
Octocode Prompt Optimizer loads about 1k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 474 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 bgauryy/octocode at commit c265e3f, republished under its MIT licence (© bgauryy). 474 words, ~1,028 tokens.
Download SKILL.mdSave it as
.claude/skills/octocode-prompt-optimizer/SKILL.md (or your agent's skills folder). This skill also uses 18 other files; get the full folder from GitHub.- name
- octocode-prompt-optimizer
- description
- Use when an agent prompt, tool schema, policy, or handoff needs to get clearer, safer, easier to trigger, cheaper in context, or measurable against real behavior. For SKILL.md folder install/review/structure, use octocode-skills.
Octocode Prompt Optimizer
Optimize instruction behavior, not prose aesthetics.
Flow: READ → UNDERSTAND → RATE → FIX → VALIDATE → OUTPUT.
Lobby rules and gates
- READ: inspect the whole input and its type; UNDERSTAND: map goal, parts, flow, assumptions, and unknowns.
- RATE: record evidenced issues, severity, and baseline; FIX: address Critical/High issues and name deliberate deferrals.
- VALIDATE: prove intent and required behavior remain correct; OUTPUT: provide the requested artifact and truthful delta.
- Use the full path for multi-section, ambiguous, tool-facing, or high-risk work; combine adjacent steps only for short, low-risk text. Never skip VALIDATE.
- Preserve intent, working branches, identifiers, commands, and required metadata; ask before changing them.
- Verify cited commands, flags, paths, tool names, and schemas before rewriting; flag unverified claims.
- Make only critical behavior mandatory; retain preference language for real preferences. Mutate files only with authority.
- Stop when: a material unknown would change intent, scope, or risk (ask one focused question and pause); instruction authority is ambiguous, or resolving a conflict would override user intent; an edit changed intent or working logic (revert it and return to UNDERSTAND); write authority is missing (deliver a patch-style delta instead of a file change); a VALIDATE check fails twice on the same section (report the weakest branch instead of forcing a pass); a reliability gain has no held-out evidence (report it as unmeasured).
Show full SKILL.md (258 more words)Show less
Smart routes — load only what the current step needs
- READ and UNDERSTAND: load
references/gates.md— read every section and map intent before judging or drafting. - RATE: load
references/rate.md; FIX: loadreferences/fix.md; VALIDATE: loadreferences/validate.md; OUTPUT: loadreferences/output.md— load only the active gate so later-step advice cannot bias the current decision. - When instructions conflict or a fix needs a compact instruction pattern, load
references/patterns.md— apply the higher authority and log the resolution in one line. - When reducing noise, load
references/conciseness-toolkit.md; when fixing priority/hierarchy loadreferences/attention.md; when choosing a technique for an observed failure loadreferences/prompt-techniques.md— match technique to failure mechanism. - When optimizing tool or MCP contracts, load
references/tool-contracts.md; for agent handoffs loadreferences/agent-communication.md; for typed packet boundaries loadreferences/zod-agent-contracts.md— make inputs, outputs, authority, and failure states explicit. - When context can overflow, load
references/context-budget.md; when repeated calls share stable prefixes loadreferences/prompt-caching.md— control relevance, pagination, latency, and cost. - When reliability must be measured, load
references/evaluation-data.md— build realistic held-out scenarios, verifiers, metrics, and a failure ledger. - When instructions consume retrieved or user-supplied content, load
references/untrusted-content.md— preserve the boundary between data and authority. - When improving this skill, prefer
octocode-graph-eval; otherwise loadreferences/improve-loop.md— require measurable acceptance instead of intuition.
Related routes
- Use
octocode-skillsfor skill-folder architecture/review;octocode-researchto verify cited contracts;octocode-graph-evalfor held-out behavior. - Use
octocode-subagentfor delegation topology.
Done gate
- This skill ships no scripts: every gate above is model-driven, so never report a check you did not actually perform.
- Done requires VALIDATE passed, the OUTPUT variant matching the request, and the reported before/after score, changed files, and deferrals all matching reality.
© bgauryy, 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 18 other files (references) in skills/octocode-prompt-optimizer of bgauryy/octocode.
- SKILL.md
- README.md
- references/agent-communication.md
- references/attention.md
- references/conciseness-toolkit.md
- references/context-budget.md
- references/evaluation-data.md
- references/fix.md
- references/gates.md
- references/improve-loop.md
- references/output.md
- references/patterns.md
- references/prompt-caching.md
- references/prompt-techniques.md
- references/rate.md
- references/tool-contracts.md
- references/untrusted-content.md
- references/validate.md
- references/zod-agent-contracts.md
Open the folder on GitHubat commit c265e3f
Compare with similar skills
Octocode Prompt Optimizer 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 |
|---|---|---|---|---|---|---|
| Octocode Prompt Optimizer this skillbgauryy/octocode | 949 | — | ~1k | Automated safety check: Pass | MIT | |
| Agents Best PracticesDenisSergeevitch/agents-best-practices | 2.4k | — | ~7.4k | Automated safety check: Pass | MIT | |
| Create Simple Promptpnp/copilot-prompts | 893 | — | ~2.6k | Automated safety check: Pass | MIT | |
| AI Project Copilotsun461941-hub/ai-project-copilot | 97 | — | ~3k | Automated safety check: Pass | MIT | |
| Homepage Generatorwanshuiyin/ARIS-in-AI-Offer | 582 | — | ~4.8k | Automated safety check: Notes | MIT | |
| Agent Prompt Engineeringagentailor/fullstack-langgraph-nextjs-agent | 132 | — | ~3.6k | Automated safety check: Pass | MIT |
Similar skills
Create Simple Prompt
pnp/copilot-prompts
This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…
AI Project Copilot
sun461941-hub/ai-project-copilot
A skill your agent uses to turn an AI idea or existing repository into a credible open-source product and to run evidence-first repository engineering across codebase discovery, context-efficient…
Homepage Generator
wanshuiyin/ARIS-in-AI-Offer
Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory.
Agent Prompt Engineering
agentailor/fullstack-langgraph-nextjs-agent
Comprehensive guide for designing, refining, and auditing system prompts for autonomous AI agents based on Anthropic's production practices.
Opik
comet-ml/opik-mcp
Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python, TypeScript, REST).
More from bgauryy/octocode
All 12 skills in this repoOctocode Benchmark Runner
bgauryy/octocode
Runs blind pairwise comparisons of Octocode against a gh-based baseline over markdown research questions, scored by total characters through the model rather than self-report.
Octocode Code Research
bgauryy/octocode
Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.
Evidence-Backed Documentation Writer
bgauryy/octocode
Writes, repairs and copyedits project docs against the Google developer documentation style guide, verifying claims in the repository before stating them.
Octocode Mannequin
bgauryy/octocode
Poses and animates a 22-bone anatomical humanoid rig with joint range-of-motion limits, using a Node CLI, a Three.js viewer and WebMCP tools an agent can drive live.
Octocode Skills Manager
bgauryy/octocode
Finds, rates, reviews, creates, improves, installs and syncs Agent Skill folders from local workspaces, registries or remote sources, with a user gate before any write.
Octocode Brainstorming
bgauryy/octocode
Walks an idea through framing, diverging into options, researching evidence and stress-testing before converging on a build, prototype, narrow or park decision.
Related
Works with
Categories
Questions about Octocode Prompt Optimizer
What does Octocode Prompt Optimizer do?
A skill your agent uses when an agent prompt, tool schema, policy, or handoff needs to get clearer, safer, easier to trigger, cheaper in context, or measurable against real behavior. Octocode Prompt Optimizer is an agent skill from bgauryy/octocode. Use when an agent prompt, tool schema, policy, or handoff needs to get clearer, safer, easier to trigger, cheaper in context, or measurable against real behavior.
When should I use Octocode Prompt Optimizer?
Octocode Prompt Optimizer fits situations like: an agent prompt; handoff needs to get clearer; easier to trigger; cheaper in context.
How do I install Octocode Prompt Optimizer in Claude Code?
Run `npx skills add bgauryy/octocode --skill octocode-prompt-optimizer -a claude-code`. Or copy the skill folder (skills/octocode-prompt-optimizer in bgauryy/octocode) into .claude/skills/octocode-prompt-optimizer in your project. Claude Code loads it when a task matches its description.
How do I install Octocode Prompt Optimizer in Codex?
Run `npx skills add bgauryy/octocode --skill octocode-prompt-optimizer -a codex`. Or copy the skill folder (skills/octocode-prompt-optimizer in bgauryy/octocode) into .agents/skills/octocode-prompt-optimizer in your project. Codex loads it when a task matches its description.
Can I use Octocode Prompt Optimizer 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 bgauryy/octocode --skill octocode-prompt-optimizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/octocode-prompt-optimizer, .gemini/skills/octocode-prompt-optimizer, .github/skills/octocode-prompt-optimizer and .opencode/skills/octocode-prompt-optimizer in your project.
What does Octocode Prompt Optimizer need to run?
SKILL.md names no scripts, command-line tools or credentials: Octocode Prompt Optimizer is instructions for the agent only.
Does Octocode Prompt Optimizer 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 Octocode Prompt Optimizer 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 Octocode Prompt Optimizer use?
Octocode Prompt Optimizer 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 Octocode Prompt Optimizer use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.
What are the alternatives to Octocode Prompt Optimizer?
Skills that share tags, products or a category with Octocode Prompt Optimizer: Agents Best Practices (DenisSergeevitch/agents-best-practices, 2.4k stars), Create Simple Prompt (pnp/copilot-prompts, 893 stars), AI Project Copilot (sun461941-hub/ai-project-copilot, 97 stars) and Homepage Generator (wanshuiyin/ARIS-in-AI-Offer, 582 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Octocode Prompt Optimizer?
bgauryy (a GitHub user) maintains it in bgauryy/octocode, which has 949 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 9, 2026.
Source: bgauryy/octocode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.