Cco Overhead
egorfedorov/claude-context-optimizer
Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage
This skill should be used when the user asks to "reflect on this conversation", "optimize my agent setup", "improve agent instructions", "analyze chat patterns", "audit AGENTS.md", "suggest agent…
Install Reflect
$ npx skills add shepherdjerred/monorepo --skill reflect -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shepherdjerred/monorepo reflect --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/shepherdjerred/monorepo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/reflect .claude/skills/reflect && 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 "reflect" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/reflect into .claude/skills/reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect", 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/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/reflectType 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 shepherdjerred/monorepo --skill reflect -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shepherdjerred/monorepo reflect --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/reflect .agents/skills/reflect && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "reflect" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/reflect into .agents/skills/reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect", 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 shepherdjerred/monorepo --skill reflect -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shepherdjerred/monorepo reflect --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/reflect .cursor/skills/reflect && 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 "reflect" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/reflect into .cursor/skills/reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect", 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/shepherdjerred/monorepo.git --path packages/dotfiles/dot_agents/skills/reflect--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 shepherdjerred/monorepo --skill reflect -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shepherdjerred/monorepo reflect --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/reflect .gemini/skills/reflect && 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 "reflect" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/reflect into .gemini/skills/reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect", 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 shepherdjerred/monorepo reflectInstalls 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 shepherdjerred/monorepo --skill reflect -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/reflect .github/skills/reflect && 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 "reflect" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/reflect into .github/skills/reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect", 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 shepherdjerred/monorepo --skill reflect -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shepherdjerred/monorepo reflect --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/reflect .opencode/skills/reflect && 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 "reflect" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/reflect into .opencode/skills/reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect", 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
reflect- GitHub stars
- 112
- Token cost
- ~899 tokens
- SKILL.md length
- 436 words
- Files
- 6 (incl. references)
- Skills in repo
- 63
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
This skill should be used when the user asks to "reflect on this conversation", "optimize my agent setup", "improve agent instructions", "analyze chat patterns", "audit AGENTS.md", "suggest agent…
- Works in 5 steps: Read the relevant conversation or… → Read the active global, root, and… → Inventory applicable skills, client… → …
- Asks to reflect on this conversation
- SKILL.md covers Inspect first, Choose the owner, Budget and quality and Recommend or implement
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Reflect is an agent skill from shepherdjerred/monorepo. This skill should be used when the user asks to "reflect on this conversation", "optimize my agent setup", "improve agent instructions", "analyze chat patterns", "audit AGENTS.md", "suggest agent improvements", "fix agent misunderstandings", or mentions "prompt optimization", "instruction tuning", or "agent configuration audit". Analyzes chat history and configuration to identify improvements for AGENTS.md files, skills, MCPs, hooks, and permissions.
Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `examples/sample-analysis-output.md`, `references/analysis-patterns.md` and `references/automation-options.md`).
It sits in Agent Workflows, covering Agent instruction files, MCP servers and Prompt engineering. The repository describes itself as: Monorepo for all of my projects. The licence is GPL-3.0.
When your agent uses it
- Asks to reflect on this conversation
- Optimize my agent setup
- Improve agent instructions
- Analyze chat patterns
Example prompts
- “reflect on this conversation”
- “optimize my agent setup”
- “improve agent instructions”
- “/reflect”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read the relevant conversation or bounded history excerpt.
- Read the active global, root, and nearest nested AGENTS.md hierarchy.
- Inventory applicable skills, client adapters, hooks, MCPs, and permissions.
- Identify the mismatch between intended and observed behavior. Separate
- Check whether the behavior is already enforced in code or tests. Do not add
What it can do on your machine
Read from SKILL.md and the folder at commit 46ddf2f. 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
Reflect loads about 899 tokens when it runs, and up to ~7.4k if it reads all its reference files. Until then it costs about 116 tokens; SKILL.md has 436 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 shepherdjerred/monorepo at commit 46ddf2f, republished under its GPL-3.0 licence (© shepherdjerred). 436 words, ~899 tokens.
Download SKILL.mdSave it as
.claude/skills/reflect/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- reflect
- description
- This skill should be used when the user asks to "reflect on this conversation", "optimize my agent setup", "improve agent instructions", "analyze chat patterns", "audit AGENTS.md", "suggest agent improvements", "fix agent misunderstandings", or mentions "prompt optimization", "instruction tuning", or "agent configuration audit". Analyzes chat history and configuration to identify improvements for AGENTS.md files, skills, MCPs, hooks, and permissions.
Reflect on agent configuration
Diagnose repeated behavior from evidence, then put the smallest durable fix in the correct layer. Do not turn one awkward exchange into a universal rule.
Inspect first
- Read the relevant conversation or bounded history excerpt.
- Read the active global, root, and nearest nested
AGENTS.mdhierarchy. - Inventory applicable skills, client adapters, hooks, MCPs, and permissions.
- Identify the mismatch between intended and observed behavior. Separate missing context, bad routing, unclear authority, stale facts, tool failure, and model judgment.
- Check whether the behavior is already enforced in code or tests. Do not add prose for a mechanically guaranteed rule.
Choose the owner
- Personal, always-on preference across repositories: global
AGENTS.md. - Repository-wide, non-obvious invariant: root
AGENTS.md. - Package-only invariant or dangerous trap: nested
AGENTS.md. - Repeatable, task-triggered procedure: a skill.
- Human architecture or rationale: README or Diátaxis wiki.
- Deterministic safety or shape requirement: code, schema, lint, hook, or test.
- Temporary plan, follow-up, or review queue: work tracker or PR.
- Client compatibility: symlink or tiny pointer, never another prose copy.
For homelab-first repositories, state the deployment boundary precisely: first-party hosted workloads use the repo-owned infrastructure and GitOps path; native clients, extensions, libraries, packages, and external services do not.
Show full SKILL.md (237 more words)Show less
Budget and quality
Treat entrypoints as routing context, not handbooks:
- global and root
AGENTS.md: at most 200 lines and 16 KiB; - nested maintained
AGENTS.md: at most 120 lines and 8 KiB; - repository or runtime
SKILL.md: at most 160 lines and 12 KiB; - a discoverable repository skill catalog: at most 24 KiB of names and
descriptions, and that ceiling is a runaway-growth alarm. Never shorten a
descriptionto fit it: the trigger clause is what an agent matches on, so truncating it drops the skill out of discovery silently. Prune unused skills instead.
Preserve purpose, ownership boundaries, dangerous traps, focused commands, and acceptance requirements. Move API reference, topology, runbooks, and historical detail to their durable owners. Delete guidance that is stale, duplicated, obvious, or no longer package-specific.
Skill names use lowercase kebab-case and match their directories. Descriptions must make routing clear without exhaustive lists. Keep conditional detail in references and read it only when relevant.
Recommend or implement
For each proposed change, cite the observed behavior it corrects and explain why the chosen layer owns it. Preserve the user's scope and do not broaden permissions. If asked to implement, make focused edits, run the repository's guidance validator, and test discovery in the clients actually used.
Evaluate improvement by behavior: can a fresh agent find the right instruction, avoid contradictory copies, and complete a representative task? File size and wording checks support that test but do not replace it.
© shepherdjerred, GPL-3.0. 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 5 other files (references) in packages/dotfiles/dot_agents/skills/reflect of shepherdjerred/monorepo.
- SKILL.md
- examples/sample-analysis-output.md
- references/analysis-patterns.md
- references/automation-options.md
- references/improvement-categories.md
- references/tiered-config-guide.md
Open the folder on GitHubat commit 46ddf2f
Compare with similar skills
Reflect 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 |
|---|---|---|---|---|---|---|
| Reflect this skillshepherdjerred/monorepo | 112 | — | ~899 | Automated safety check: Pass | GPL-3.0 | |
| Cco Overheadegorfedorov/claude-context-optimizer | 114 | — | ~606 | Automated safety check: Pass | MIT | |
| Microsoft Foundrymicrosoft/GitHub-Copilot-for-Azure | 255 | 1 repos | ~6.7k | Automated safety check: Pass | MIT | |
| Agent Setup Health Audittw93/Waza | 7.2k | — | ~5.2k | Automated safety check: Notes | MIT | |
| Workflow Schema Tuningbreaking-brake/cc-wf-studio | 5.4k | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Agentforce GenerateSalesforceAIResearch/agentforce-adlc | 112 | 1 repos | ~7.4k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Microsoft Foundry
microsoft/GitHub-Copilot-for-Azure
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end.
Agent Setup Health Audit
tw93/Waza
Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.
Workflow Schema Tuning
breaking-brake/cc-wf-studio
Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.
Agentforce Generate
SalesforceAIResearch/agentforce-adlc
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script.
Semantix Guide
Gnosil/semantix
Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project…
More from shepherdjerred/monorepo
All 63 skills in this repoBun Runtime Best Practices
shepherdjerred/monorepo
Bun runtime APIs and current operational patterns for files, processes, modules, networking, databases, tests, and deployment.
Bun Test Patterns
shepherdjerred/monorepo
Current Bun test runner guidance for discovery, isolation, parallelism, sharding, changed tests, mocks, timers, snapshots, coverage, DOM Testing Library, and integration teardown.
Bun Workspaces
shepherdjerred/monorepo
Current Bun workspace guidance for isolated and hoisted linkers, catalogs, filters, scripts, dependency classes, lockfiles, lifecycle trust, caches, publishing, TypeScript package exports, and…
Deep Research
shepherdjerred/monorepo
This skill should be used when the user asks to "deep research", "research this topic", "investigate thoroughly", "do a deep dive on", "comprehensive research on", "find everything about", "survey…
Figma Use
shepherdjerred/monorepo
This skill should be used when the user asks to "create a Figma design", "design in Figma", "make a Figma mockup", "create an app icon", "design UI", "render JSX to Figma", "export from Figma"…
Fish Helper
shepherdjerred/monorepo
Current Fish shell scripting, functions, abbreviations, completions, variables, events, configuration, plugins, testing, and safety guidance.
Related
Categories
Questions about Reflect
What does Reflect do?
This skill should be used when the user asks to "reflect on this conversation", "optimize my agent setup", "improve agent instructions", "analyze chat patterns", "audit AGENTS.md", "suggest agent…. Reflect is an agent skill from shepherdjerred/monorepo.md", "suggest agent improvements", "fix agent misunderstandings", or mentions "prompt optimization", "instruction tuning", or "agent configuration audit".
When should I use Reflect?
Reflect fits situations like: asks to reflect on this conversation; optimize my agent setup; improve agent instructions; analyze chat patterns.
How do I install Reflect in Claude Code?
Run `npx skills add shepherdjerred/monorepo --skill reflect -a claude-code`. Or copy the skill folder (packages/dotfiles/dot_agents/skills/reflect in shepherdjerred/monorepo) into .claude/skills/reflect in your project. Claude Code loads it when a task matches its description.
How do I install Reflect in Codex?
Run `npx skills add shepherdjerred/monorepo --skill reflect -a codex`. Or copy the skill folder (packages/dotfiles/dot_agents/skills/reflect in shepherdjerred/monorepo) into .agents/skills/reflect in your project. Codex loads it when a task matches its description.
Can I use Reflect 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 shepherdjerred/monorepo --skill reflect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reflect, .gemini/skills/reflect, .github/skills/reflect and .opencode/skills/reflect in your project.
What does Reflect need to run?
SKILL.md names no scripts, command-line tools or credentials: Reflect is instructions for the agent only.
Does Reflect 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 Reflect 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 Reflect use?
Reflect is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Reflect use?
About 899 tokens (SKILL.md is roughly 3.6k 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 6.5k tokens, read only when the agent opens those files.
What are the alternatives to Reflect?
Skills that share tags, products or a category with Reflect: Cco Overhead (egorfedorov/claude-context-optimizer, 114 stars), Microsoft Foundry (microsoft/GitHub-Copilot-for-Azure, 255 stars), Agent Setup Health Audit (tw93/Waza, 7.2k stars) and Workflow Schema Tuning (breaking-brake/cc-wf-studio, 5.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Reflect?
shepherdjerred (a GitHub user) maintains it in shepherdjerred/monorepo, which has 112 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 7, 2026.
Source: shepherdjerred/monorepo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.