Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Answer questions about this agent's own token spend, usage limits and burn.
Install Agentburn
$ npx skills add Socialpranker/agentburn --skill agentburn -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Socialpranker/agentburn agentburn --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/Socialpranker/agentburn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill/agentburn .claude/skills/agentburn && 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 "agentburn" agent skill from https://github.com/Socialpranker/agentburn/tree/main/skill/agentburn into .claude/skills/agentburn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentburn", 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/Socialpranker/agentburn/tree/main/skill/agentburnType 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 Socialpranker/agentburn --skill agentburn -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Socialpranker/agentburn agentburn --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Socialpranker/agentburn.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skill/agentburn .agents/skills/agentburn && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agentburn" agent skill from https://github.com/Socialpranker/agentburn/tree/main/skill/agentburn into .agents/skills/agentburn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentburn", 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 Socialpranker/agentburn --skill agentburn -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Socialpranker/agentburn agentburn --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Socialpranker/agentburn.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skill/agentburn .cursor/skills/agentburn && 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 "agentburn" agent skill from https://github.com/Socialpranker/agentburn/tree/main/skill/agentburn into .cursor/skills/agentburn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentburn", 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/Socialpranker/agentburn.git --path skill/agentburn--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 Socialpranker/agentburn --skill agentburn -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Socialpranker/agentburn agentburn --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Socialpranker/agentburn.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skill/agentburn .gemini/skills/agentburn && 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 "agentburn" agent skill from https://github.com/Socialpranker/agentburn/tree/main/skill/agentburn into .gemini/skills/agentburn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentburn", 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 Socialpranker/agentburn agentburnInstalls 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 Socialpranker/agentburn --skill agentburn -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Socialpranker/agentburn.git skills-src && mkdir -p .github/skills && cp -r skills-src/skill/agentburn .github/skills/agentburn && 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 "agentburn" agent skill from https://github.com/Socialpranker/agentburn/tree/main/skill/agentburn into .github/skills/agentburn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentburn", 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 Socialpranker/agentburn --skill agentburn -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Socialpranker/agentburn agentburn --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Socialpranker/agentburn.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skill/agentburn .opencode/skills/agentburn && 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 "agentburn" agent skill from https://github.com/Socialpranker/agentburn/tree/main/skill/agentburn into .opencode/skills/agentburn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentburn", 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
agentburn- GitHub stars
- 112
- Token cost
- ~982 tokens
- SKILL.md length
- 477 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Answer questions about this agent's own token spend, usage limits and burn.
- Works in 4 steps: Make sure the CLI exists: run uvx… → For "how much / where does it burn" → For "what have you been doing / why is… → …
- The user asks how much am I spending
- SKILL.md covers How to answer a cost question, Fixing things and Honesty rules (do not skip)
- Calls uvx, pipx and pip
What it does
Agentburn is an agent skill from Socialpranker/agentburn. Answer questions about this agent's own token spend, usage limits and burn. Use when the user asks "how much am I spending", "where do my tokens go", "why do I keep hitting my limit", "what ate my 5-hour window", "what did you burn while I slept", "почему так дорого", "сколько я трачу", "почему упёрся в лимит", asks for a cost/usage breakdown, wants to cut the agent's bill, or asks what the agent has been doing (functions, loops, failures). Runs the local agentburn profiler (zero-dependency, read-only, nothing…
Its SKILL.md is about 980 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 Development, covering Performance optimization. It works with Model Context Protocol and Python. The repository describes itself as: Which 5-hour window took you out — and where the money goes. Local profiler for Claude Code, OpenClaw & Hermes Agent: usage windows, burn by source (cron/chats/subagents), the… The licence is MIT.
When your agent uses it
- The user asks how much am I spending
- Where do my tokens go
- Why do I keep hitting my limit
- What ate my 5-hour window
Example prompts
- “s own token spend, usage limits and burn. Use when the user asks”
- “where do my tokens go”
- “why do I keep hitting my limit”
- “/agentburn”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Make sure the CLI exists: run uvx agentburn --version
- For "how much / where does it burn"
- For "what have you been doing / why is it expensive"
- For "why did I hit my limit / what ate my window" (subscriptions —
What it can do on your machine
Read from SKILL.md and the folder at commit 638226c. 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
Shell commands in SKILL.md call:
uvxpipxpip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uvx, pipx and pip, which can reach the network depending on how they are called.
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
Agentburn loads about 982 tokens when it runs. Until then it costs about 137 tokens; SKILL.md has 477 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 Socialpranker/agentburn at commit 638226c, republished under its MIT licence (© Socialpranker). 477 words, ~982 tokens.
Download SKILL.mdSave it as
.claude/skills/agentburn/SKILL.md (or your agent's skills folder).- name
- agentburn
- description
- Answer questions about this agent's own token spend, usage limits and burn. Use when the user asks "how much am I spending", "where do my tokens go", "why do I keep hitting my limit", "what ate my 5-hour window", "what did you burn while I slept", "почему так дорого", "сколько я трачу", "почему упёрся в лимит", asks for a cost/usage breakdown, wants to cut the agent's bill, or asks what the agent has been doing (functions, loops, failures). Runs the local agentburn profiler (zero-dependency, read-only, nothing leaves the machine).
agentburn — the agent answers for its own bill
You have access to a local profiler that reads THIS agent's own accounting database read-only. Use it instead of guessing about costs.
How to answer a cost question
- Make sure the CLI exists: run
uvx agentburn --version(fallbacks:pipx run agentburn --version,pip install agentburn). - For "how much / where does it burn":
run
uvx agentburn --jsonand read:total,monthly_projection,by_source(cron / heartbeat / gateway:* / subagent / cli),night,overhead_per_call,recommendations. - For "what have you been doing / why is it expensive":
run
uvx agentburn why --jsonand read:functions,rereads,storms,idle_heartbeats,failure_cost,observations. - For "why did I hit my limit / what ate my window" (subscriptions —
Claude Code Pro/Max — where the invoice is fixed and the window is not):
run
uvx agentburn limits --jsonand read:peak(the worst rolling 5-hour window),typical_window,peak_by_model,peak_by_source,mix,tips. Lead with peak ÷ typical: a wall is hit by the peak.ceilingis measured from cut-offs Claude Code recorded itself (ceiling_source: recorded,ceiling_hits);minutes_to_wallis at the pace of the last 30 minutes. If there is no ceiling and the user remembers when they were cut off, re-run with--hit "YYYY-MM-DD HH:MM". Never state an absolute limit: the provider's formula is not public. Codex CLI:ceiling_source: providermeans the ceiling comes from theused_percentCodex records itself — an estimate, other devices on the account count too;provider_usedis the latest raw reading. Gemini CLI and opencode: tokens only (opencode carries its own costs when the provider is priced); no cut-offs are recorded, soceilingis absent unless--hitnames one. 4b. For "why is my context so big / should I /clear / what does skill X cost": runuvx agentburn context --jsonand readbands,savings(clear_at→share_not_spent),longest_sessions,by_effort,skills(tokens_per_load, measured). Recommend the lowestclear_atthat keeps most of the best saving. 4c. For "what did that commit / PR cost": runuvx agentburn commits --jsonand readtop(costliest commits) andrepos(median per repository). - For one channel ("what did you do in telegram?"):
add
--source telegram(or cron / heartbeat / subagent / cli). - Answer in the user's language, lead with the verdict (pace + dominant source), quote at most 3 numbers, then the single highest-impact change. Mark estimated costs with "~".
Show full SKILL.md (99 more words)Show less
Fixing things
- Offer
uvx agentburn fix— it prints ready-to-paste config patches and NEVER applies them. Show the patch; apply only if the user explicitly confirms, and re-check withagentburn --compareafterwards (baseline first:agentburn --save-baseline).
Honesty rules (do not skip)
- If the output warns about zero-usage sessions, say the totals are a
LOWER BOUND and suggest
uvx agentburn doctor. - Numbers come from the agent's own accounting; do not invent prices or savings beyond what the tool prints.
- Never paste raw session titles or file paths into public channels;
categories and counters only (the
--sharecard is safe by design).
© Socialpranker, 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 skill/agentburn of Socialpranker/agentburn.
Open the folder on GitHubat commit 638226c
Compare with similar skills
Agentburn 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 |
|---|---|---|---|---|---|---|
| Agentburn this skillSocialpranker/agentburn | 112 | — | ~982 | Automated safety check: Pass | MIT | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT | |
| LangBot Plugin Developmentlangbot-app/LangBot | 18k | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | |
| Pycrazyguitar/pysheeet | 8.2k | — | ~886 | Automated safety check: Pass | MIT | |
| Python Performance Optimizationwshobson/agents | 40k | 13 repos | ~814 | Automated safety check: Pass | MIT | |
| LangBot Core Developmentlangbot-app/LangBot | 18k | — | ~1.4k | Automated safety check: Notes | Apache-2.0 |
Similar skills
LangBot Plugin Development
langbot-app/LangBot
Guides building, debugging and testing LangBot plugins: components, SDK calls, README and locale rules, SDK pitfalls and WebSocket-based testing.
Py
crazyguitar/pysheeet
Comprehensive Python programming reference covering syntax, concurrency, networking, databases, ML/LLM development, and HPC.
Python Performance Optimization
wshobson/agents
Profiles slow Python code with cProfile and memory profilers, then applies targeted fixes for CPU, memory, I/O and query bottlenecks.
LangBot Core Development
langbot-app/LangBot
Covers developing the LangBot core backend and web UI: dev setup, repo layout, API auth types, adding endpoints, migrations and keeping the MCP server in step.
Keybase RPC Log Analysis
keybase/client
Captures a clean Keybase service log and analyzes it for redundant, duplicated or looping RPCs, then checks whether a caching fix reduced the calls.
Related
Works with
Categories
Questions about Agentburn
What does Agentburn do?
Answer questions about this agent's own token spend, usage limits and burn. Agentburn is an agent skill from Socialpranker/agentburn. Answer questions about this agent's own token spend, usage limits and burn.
When should I use Agentburn?
Agentburn fits situations like: the user asks how much am I spending; where do my tokens go; why do I keep hitting my limit; what ate my 5-hour window.
How do I install Agentburn in Claude Code?
Run `npx skills add Socialpranker/agentburn --skill agentburn -a claude-code`. Or copy the skill folder (skill/agentburn in Socialpranker/agentburn) into .claude/skills/agentburn in your project. Claude Code loads it when a task matches its description.
How do I install Agentburn in Codex?
Run `npx skills add Socialpranker/agentburn --skill agentburn -a codex`. Or copy the skill folder (skill/agentburn in Socialpranker/agentburn) into .agents/skills/agentburn in your project. Codex loads it when a task matches its description.
Can I use Agentburn 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 Socialpranker/agentburn --skill agentburn -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentburn, .gemini/skills/agentburn, .github/skills/agentburn and .opencode/skills/agentburn in your project.
What does Agentburn need to run?
Going by SKILL.md and its folder, Agentburn needs the command-line tools its instructions call (uvx, pipx and pip). Our summary lists: Python 3.
Does Agentburn access the network?
SKILL.md contains no URLs. Its commands use uvx and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Agentburn 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 Agentburn use?
Agentburn 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 Agentburn use?
About 982 tokens (SKILL.md is roughly 3.9k 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 Agentburn?
Skills that share tags, products or a category with Agentburn: Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), LangBot Plugin Development (langbot-app/LangBot, 18k stars), Py (crazyguitar/pysheeet, 8.2k stars) and Python Performance Optimization (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agentburn?
Socialpranker (a GitHub user) maintains it in Socialpranker/agentburn, which has 112 GitHub stars. The repository was last updated on October 5, 2026.
Source: Socialpranker/agentburn on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.