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.
“Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.”
Install Loop Token Budget Guard
$ npx skills add cobusgreyling/loop-engineering --skill loop-budget -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-budget --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/cobusgreyling/loop-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/loop-budget .claude/skills/loop-budget && 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 "loop-budget" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-budget into .claude/skills/loop-budget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-budget", 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/cobusgreyling/loop-engineering/tree/main/skills/loop-budgetType 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 cobusgreyling/loop-engineering --skill loop-budget -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-budget --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/loop-budget .agents/skills/loop-budget && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "loop-budget" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-budget into .agents/skills/loop-budget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-budget", 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 cobusgreyling/loop-engineering --skill loop-budget -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-budget --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/loop-budget .cursor/skills/loop-budget && 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 "loop-budget" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-budget into .cursor/skills/loop-budget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-budget", 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/cobusgreyling/loop-engineering.git --path skills/loop-budget--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 cobusgreyling/loop-engineering --skill loop-budget -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-budget --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/loop-budget .gemini/skills/loop-budget && 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 "loop-budget" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-budget into .gemini/skills/loop-budget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-budget", 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 cobusgreyling/loop-engineering loop-budgetInstalls 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 cobusgreyling/loop-engineering --skill loop-budget -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/loop-budget .github/skills/loop-budget && 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 "loop-budget" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-budget into .github/skills/loop-budget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-budget", 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 cobusgreyling/loop-engineering --skill loop-budget -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-budget --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/loop-budget .opencode/skills/loop-budget && 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 "loop-budget" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-budget into .opencode/skills/loop-budget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-budget", 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
loop-budget- GitHub stars
- 11k
- Used in
- 1 other repo
- Token cost
- ~376 tokens
- SKILL.md length
- 145 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
- Works in 6 steps: Read loop-budget.md for daily caps and… → Read recent entries in loop-run-log.md… → Sum tokens_estimate for the active… → …
- SKILL.md covers Start of run, End of run and Rules
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
About this skill
Loop Token Budget Guard is a skill in cobusgreyling/loop-engineering (11k stars). Its SKILL.md is about 376 tokens, and copies of it appear in 1 other owners' repositories. Licence: MIT.
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Read loop-budget.md for daily caps and kill-switch flags.
- Read recent entries in loop-run-log.md (last 24h).
- Sum tokens_estimate for the active pattern today.
- If spend ≥ 80% of the pattern's daily cap → report-only mode (no sub-agents, no auto-fix).
- If spend ≥ 90% and High Priority items remain in STATE.md, yield to the budget-negotiator skill (if installed). Otherwise, if spend ≥ 100%…
- If watchlist/state has no actionable items → exit in <5k tokens (do not spawn sub-agents).
What it can do on your machine
Read from SKILL.md and the folder at commit 87c5e9c. 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 (its code samples are json).
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
Loop Token Budget Guard loads about 376 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 145 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 cobusgreyling/loop-engineering at commit 87c5e9c, republished under its MIT licence (© cobusgreyling). 145 words, ~376 tokens.
Download SKILL.mdSave it as
.claude/skills/loop-budget/SKILL.md (or your agent's skills folder).- name
- loop-budget
- description
- Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.
Loop Budget Guard
Run at the start and end of every loop iteration.
Start of run
- Read
loop-budget.mdfor daily caps and kill-switch flags. - Read recent entries in
loop-run-log.md(last 24h). - Sum
tokens_estimatefor the active pattern today. - If spend ≥ 80% of the pattern's daily cap → report-only mode (no sub-agents, no auto-fix).
- If spend ≥ 90% and High Priority items remain in
STATE.md, yield to the budget-negotiator skill (if installed). Otherwise, if spend ≥ 100% orloop-pause-allis set → exit immediately with a one-line note in STATE.md. - If watchlist/state has no actionable items → exit in <5k tokens (do not spawn sub-agents).
End of run
Append one JSON object to loop-run-log.md:
{
"run_id": "<ISO8601>",
"pattern": "<pattern-id>",
"duration_s": <number>,
"items_found": <number>,
"actions_taken": <number>,
"escalations": <number>,
"tokens_estimate": <number>,
"outcome": "no-op | report-only | fix-proposed | escalated"
}Rules
- Never exceed
max sub-agent spawns/runfromloop-budget.md. - High-cadence patterns (CI Sweeper, PR Babysitter) must early-exit when nothing is actionable.
- On self-throttle, append a line to
loop-budget.mdunder Alerts This Period.
© cobusgreyling, 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/loop-budget of cobusgreyling/loop-engineering.
Open the folder on GitHubat commit 87c5e9c
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in cobusgreyling/loop-engineering, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Loop Token Budget Guard 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 |
|---|---|---|---|---|---|---|
| Loop Token Budget Guard this skillcobusgreyling/loop-engineering | 11k | 1 repos | ~376 | Automated safety check: Pass | MIT | |
| Agents Best PracticesDenisSergeevitch/agents-best-practices | 2.4k | — | ~7.4k | Automated safety check: Pass | MIT | |
| Context Compressionguanyang/open-agent-hub | 975 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Amazon Bedrockaws/agent-toolkit-for-aws | 2.8k | — | ~8.6k | Automated safety check: Pass | Apache-2.0 | |
| Long Horizon Promptingguanyang/open-agent-hub | 975 | 1 repos | ~6.4k | Automated safety check: Pass | MIT | |
| RAG Architectalirezarezvani/claude-skills | 28k | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Context Compression
guanyang/open-agent-hub
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…
- Official
Amazon Bedrock
aws/agent-toolkit-for-aws
Builds generative AI applications on Amazon Bedrock. An agent skill from aws/agent-toolkit-for-aws.
Long Horizon Prompting
guanyang/open-agent-hub
This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal…
RAG Architect
alirezarezvani/claude-skills
A skill your agent uses when the user asks to design a RAG pipeline, choose a chunking strategy or embedding model, pick a vector database, or evaluate retrieval quality (precision@k, recall@k, NDCG).
Swarms Multi-Agent Framework
kyegomez/swarms
Teaches the Swarms Python framework: the Agent class, tools, loops, memory and multi-agent structures such as sequential, concurrent and graph workflows.
More from cobusgreyling/loop-engineering
All 21 skills in this repoInstall Loop Engineering
cobusgreyling/loop-engineering
Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score.
Loop Constraints Enforcer
cobusgreyling/loop-engineering
Loads a project's loop-constraints.md before any other action and blocks pushes, edits or merges that violate the rules it defines.
Release Notes Drafter
cobusgreyling/loop-engineering
Turns a structured list of changes from changelog-scan into a categorized, user-facing release notes draft file, and never publishes anything.
Issue Triage Loop
cobusgreyling/loop-engineering
Scans open GitHub issues and discussions, flags duplicates, scores priority and proposes labels into issue-triage-state.md without ever labeling or closing.
Loop Triage Report
cobusgreyling/loop-engineering
Turns CI failures, open issues, recent commits and chat threads into a prioritized markdown report that an automation loop can act on without inventing architecture work.
PR Review Triage
cobusgreyling/loop-engineering
Tracks open pull requests and records CI state, staleness, merge conflicts and unanswered review comments in a state file, then lists the top three actions for a human.
Related
Categories
Questions about Loop Token Budget Guard
How do I install Loop Token Budget Guard in Claude Code?
Run `npx skills add cobusgreyling/loop-engineering --skill loop-budget -a claude-code`. Or copy the skill folder (skills/loop-budget in cobusgreyling/loop-engineering) into .claude/skills/loop-budget in your project. Claude Code loads it when a task matches its description.
How do I install Loop Token Budget Guard in Codex?
Run `npx skills add cobusgreyling/loop-engineering --skill loop-budget -a codex`. Or copy the skill folder (skills/loop-budget in cobusgreyling/loop-engineering) into .agents/skills/loop-budget in your project. Codex loads it when a task matches its description.
Can I use Loop Token Budget Guard 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 cobusgreyling/loop-engineering --skill loop-budget -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loop-budget, .gemini/skills/loop-budget, .github/skills/loop-budget and .opencode/skills/loop-budget in your project.
What does Loop Token Budget Guard need to run?
SKILL.md names no scripts, command-line tools or credentials: Loop Token Budget Guard is instructions for the agent only.
Does Loop Token Budget Guard 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 Loop Token Budget Guard 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 Loop Token Budget Guard use?
Loop Token Budget Guard 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 Loop Token Budget Guard use?
About 376 tokens (SKILL.md is roughly 1.5k 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 Loop Token Budget Guard?
Skills that share tags, products or a category with Loop Token Budget Guard: Agents Best Practices (DenisSergeevitch/agents-best-practices, 2.4k stars), Context Compression (guanyang/open-agent-hub, 975 stars), Amazon Bedrock (aws/agent-toolkit-for-aws, 2.8k stars) and Long Horizon Prompting (guanyang/open-agent-hub, 975 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Loop Token Budget Guard?
cobusgreyling (a GitHub user) maintains it in cobusgreyling/loop-engineering, which has 11,440 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 8, 2026.
Source: cobusgreyling/loop-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.