github
Skill5.7k starsChanged 37 days agoApache-2.0View on GitHub
Use when interacting with GitHub repositories, authentication, remotes, pushes, or repository creation through the GitHub CLI and related git workflows.
- Reads credentials
166 other projects use a version of this.
Trending
Quiet since September.about the whole repository
Most recently taken up by
- Moriarty33/jb-kaizentheir own version, first seen Nov 8, 2026
- GradScalerTeam/claude_clitheir own version, first seen Nov 8, 2026
- artivilla/agent-skillstheir own version, first seen Nov 8, 2026
- DmacMcgreg/psibottheir own version, first seen Nov 8, 2026
- ashleysbrain/skillstheir own version, first seen Nov 8, 2026
- sidmanale643/pekka-bottheir own version, first seen Nov 8, 2026
Who's talking about the-open-agent/openagent
- @golangoss.bsky.social“openagent (⭐️ 5515) ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting …”Bluesky · Aug 16, 2026 · 2 likes
- @golangoss.bsky.social“openagent (⭐️ 5334) ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting …”Bluesky · Jul 4, 2026 · 1 likes
- @golangoss.bsky.social“openagent (⭐️ 5309) ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting …”Bluesky · Jun 27, 2026 · 1 likes
- @golangoss.bsky.social“openagent (⭐️ 5086) ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting …”Bluesky · May 30, 2026 · 1 likes
- Shubhamsaboo/awesome-llm-apps“Add OpenAgent — self-hostable AI assistant platform with LLM, RAG, agent loops & MCP”GitHub · May 3, 2026 · 1 reactions
The biggest 5 of 30 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 30
Talked about on GitHub and Bluesky (30 times).
On GitHub · 26
- May 3, 2026Add OpenAgent — self-hostable AI assistant platform with LLM, RAG, agent loops & MCP — Shubhamsaboo/awesome-llm-apps1 reaction · 1 comment
- Sep 20, 2026[开源自荐] OpenAgent:一个 exe 就能跑的自托管 AI Agent 平台 — 521xueweihan/HelloGitHub0 reactions
- Sep 20, 2026【开源自荐】OpenAgent:一个 exe 就能跑的自托管 AI Agent 平台,Agent 能开浏览器、跑命令、写 Office — GitHubDaily/GitHubDaily0 reactions
- Sep 20, 2026【开源自荐】OpenAgent:Go 写的自托管 AI Agent 平台,单二进制、Windows 原生跑,工具权限用 Casbin — polaris1119/golangweekly0 reactions
- Aug 2, 2026feat: detect OpenAgent — casdoor/casdoor-aiguard0 reactions
21 more on GitHub
- Aug 2, 2026[feature] detect OpenAgent — casdoor/casdoor-aiguard0 reactions
- Jul 8, 2026test: add MCP intranet scan unit tests — Ayush7614/openagent0 reactions · 3 comments
- Jul 8, 2026fix: Ollama embeddings URL + safer i18n errors — Ayush7614/openagent0 reactions · 3 comments
- Jul 8, 2026fix: robust SKILL.md front-matter parsing + new Ollama skill — Ayush7614/openagent0 reactions · 3 comments
- Jul 5, 2026feat: add SendNotification API — casdoor/casdoor-go-sdk0 reactions
- Jun 24, 2026[feature] remove Conf.js config — casosorg/casos0 reactions · 1 comment
- Jun 6, 2026[Add] Casibase / OpenAgent (the-open-agent/openagent) — PyTorchKR/landscape0 reactions
- May 26, 2026【开源自荐】OpenAgent:一个二进制文件跑起来的 AI Agent 平台(4900+ Star) — ruanyf/weekly0 reactions · 1 comment
- May 18, 2026feat: add shell tool for command execution and background sessions — AidenAI-IO/aico-link0 reactions · 1 comment
- May 5, 2026Add OpenAgent to Agent Frameworks (General Purpose) — caramaschiHG/awesome-ai-agents-20260 reactions
- May 5, 2026Add OpenAgent to Autonomous Agent Task Solver Projects — Jenqyang/Awesome-AI-Agents0 reactions
- May 5, 2026Add OpenAgent to open-source projects — e2b-dev/awesome-ai-agents0 reactions
- May 5, 2026Add OpenAgent between OpenAGI and OpenAI — slavakurilyak/awesome-ai-agents0 reactions · 1 comment
- May 5, 2026Add OpenAgent (data/openagent.yml) — alternbits/awesome-ai-agents0 reactions
- May 5, 2026Add OpenAgent to Browser & Computer Use Agents section — tysoncung/awesome-ai-agents0 reactions
- May 3, 2026Add OpenAgent — open-source personal AI assistant with LLM, RAG, agent loops & MCP Body: — slavakurilyak/awesome-ai-agents0 reactions · 2 comments
- May 3, 2026Add OpenAgent — self-hostable AI assistant platform with LLM, RAG, agent loops & MCP — av/awesome-llm-services0 reactions
- May 3, 2026Add OpenAgent — open-source AI assistant platform with built-in LLMOps observability, usage analytics & admin dashboard — tensorchord/Awesome-LLMOps0 reactions
- May 3, 2026Add OpenAgent — open-source personal AI assistant platform with LLM, RAG, agent loops & MCP — taishi-i/awesome-ChatGPT-repositories0 reactions · 1 comment
- May 3, 2026Add OpenAgent — open-source personal AI assistant with LLM, RAG, agent loops & MCP — e2b-dev/awesome-ai-agents0 reactions · 2 comments
- Apr 26, 2026[Trend Scout] the-open-agent/openagent — magicpro97/copilot-session-knowledge0 reactions · 1 comment
On Bluesky · 4
- Aug 16, 2026openagent (⭐️ 5515) ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and… — @golangoss.bsky.social2 likes and reposts
- Jul 4, 2026openagent (⭐️ 5334) ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and… — @golangoss.bsky.social1 likes and repost
- Jun 27, 2026openagent (⭐️ 5309) ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and… — @golangoss.bsky.social1 likes and repost
- May 30, 2026openagent (⭐️ 5086) ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and… — @golangoss.bsky.social1 likes and repost
Used with
Projects with it also use discord-e2e, openclaw-repair-sweep and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
molt-botSkilldiscord-e2e
Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.
Also in 10 projects that use this
molt-botSkillopenclaw-repair-sweep
Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.
Also in 10 projects that use this
clawdbotSkillopenclaw-performance
Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.
Also in 7 projects that use this
clawdbotSkillplugin-sdk-impact
Count Plugin SDK consumers across live ClawHub releases and bundled OpenClaw plugins before deprecation, removal, or behavior changes; supports public release-date filters.
Also in 7 projects that use this
- +2 more from molt-bot
Other versions166 projects use a version of this.
Word for word · 1
- casibase/casibase★ 5.7k100% same
Edited · 0
None found.
Wrote their own version · 165
- moltbot/clawdbot★ 394ksame name
- steipete/warelay★ 394ksame name
- steipete/clawdis★ 394ksame name
- moltbot/moltbot★ 394ksame name
- clawdbot/clawdbot★ 394ksame name
- openclaw/openclaw★ 394ksame name
- molt-bot/clawdbot★ 391ksame name
- NousResearch/hermes-agent★ 262ksame name
- spinabot/brigade★ 11ksame name
- linuxhsj/openclaw-zero-token★ 5.2ksame name
155 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository54 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- 1passwordSkill
- apple-notesSkill
- apple-remindersSkill
- bear-notesSkill
- blogwatcherSkill
- blucliSkill
- bluebubblesSkill
- camsnapSkill
- canvasSkill
- clawhubSkill
- coding-agentSkill
- discordSkill
- eightctlSkill
- geminiSkill
- gh-issuesSkill
- gifgrepSkill
- gogSkill
- goplacesSkill
- healthcheckSkill
- himalayaSkill
- imsgSkill
- mcporterSkill
- model-usageSkill
- nano-pdfSkill
- node-connectSkill
- notionSkill
- obsidianSkill
- openai-whisper-apiSkill
- openai-whisperSkill
- openhueSkill
- oracleSkill
- ordercliSkill
- peekabooSkill
- powerpointSkill
- sagSkill
- session-logsSkill
- sherpa-onnx-ttsSkill
- skill-creatorSkill
- slackSkill
- songseeSkill
- sonoscliSkill
- spotify-playerSkill
- summarizeSkill
- taskflow-inbox-triageSkill
- taskflowSkill
- things-macSkill
- tmuxSkill
- trelloSkill
- video-framesSkill
- voice-callSkill
- wacliSkill
- weatherSkill
- xurlSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
74 rules. 0 are common, 53 are distinctive, and 21 are very specific to this project.
0
Common
Most of the 150 edited versions we read keep these.
53
Distinctive
This author's own choices. Worth a look.
21
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 15
Prefer gh for all GitHub operations.
- Distinctive: line 17
Never ask the user to manually perform a long GitHub setup if the agent can check, reuse, or finish it directly.
- Very specific: line 21
Prefer gh over raw GitHub API calls.
- Distinctive: line 22
Prefer existing authenticated state over asking for new credentials.
- Distinctive: line 23
Prefer non-interactive checks before prompting the user.
- Distinctive: line 24
Prefer the smallest unblock request:
- Very specific: line 29
Do not ask the user to manually create the repository if gh can do it.
- Distinctive: line 30
Do not ask the user to manually add remotes, initialize Git, or push if the agent can do it.
- Distinctive: line 31
Never print, echo, log, summarize, or restate secrets.
- Distinctive: line 32
Never store secrets in files, commits, repo config, docs, examples, or chat summaries.
- Distinctive: line 33
Never switch credential strategy unless the current one actually fails.
- Very specific: line 37
When using gh auth login through a shell session, do not assume the browser login step has started after the first prompt or after sending …
- Distinctive: line 48
keep polling the session after each input
- Very specific: line 50
use minimal inputs such as enter, arrow keys, y, n, or short submitted text as needed
- Distinctive: line 51
do not stop after only one successful prompt response
- Distinctive: line 52
do not tell the user that the browser has opened unless the command output explicitly indicates that a browser login or web flow has started
- Distinctive: line 53
do not tell the user that login is complete unless the command output explicitly indicates success
- Distinctive: line 62
If the shell session remains running but only shows that an earlier prompt was answered, continue polling instead of summarizing the state …
- Distinctive: line 64
Only ask the user to act when the output clearly shows an external action is now required.
- Very specific: line 66
When the user says they completed browser or device authorization, do not start a new gh auth login flow immediately.
- Distinctive: line 71
wait for explicit success or failure from that same session
- Very specific: line 72
only if that session has exited or is unrecoverable, then check gh auth status
- Distinctive: line 73
only start a brand-new login flow if the previous login session has clearly failed or been closed
- Distinctive: line 75
If the shell output contains prompts like:
- Distinctive: line 83
Do not stop at that prompt.
- Distinctive: line 84
Do not ask the user to confirm completion yet.
- Distinctive: line 85
Do not start a new login flow while this session is still running.
- Very specific: line 91
Check whether gh exists and is already authenticated.
- Distinctive: line 93
Use this path when possible:
- Distinctive: line 96
if authenticated, continue directly with:
- Very specific: line 102
If gh is authenticated, do not ask the user for tokens, passwords, SSH keys, or browser login.
- Very specific: line 106
If gh is installed but not authenticated, use gh auth login directly and continue the GitHub flow after login succeeds.
- Very specific: line 116
do not switch away from gh login unless it actually fails
- Distinctive: line 117
do not ask the user to manually create repositories or configure git
- Distinctive: line 118
do not ask the user to perform a long GitHub setup outside the login itself
- Distinctive: line 121
When login requires user interaction:
- Distinctive: line 123
ask for only the smallest possible action
- Distinctive: line 129
After login succeeds, continue directly with:
- Very specific: line 138
If gh is missing:
- Distinctive: line 141
prefer non-interactive installation methods when available
- Very specific: line 142
after installation, re-check whether gh exists and continue with the normal gh-first flow
- Very specific: line 143
only fall back away from gh if installation actually fails, is blocked by the environment, or would require disproportionate user effort
- Very specific: line 153
do not ask the user to install gh manually before you have tried a reasonable automatic install path
- Very specific: line 154
do not switch to a different credential strategy just because gh is missing initially
- Distinctive: line 155
if installation fails, summarize the blocker briefly and then continue to the fallback path below
- Distinctive: line 162
prefer existing Git credential helpers or existing SSH authentication
- Distinctive: line 165
Check for likely reusable auth:
- Distinctive: line 172
Only if those paths fail should the user be asked for one minimal credential input.
- Distinctive: line 176
When user input is required, ask for only one concrete item at a time.
- Distinctive: line 194
Treat PATs, device codes, auth tokens, cookies, and SSH private keys as secrets.
- Distinctive: line 195
Never echo secrets back to the user.
- Distinctive: line 196
Never include secrets in command output summaries.
- Distinctive: line 197
Never write secrets into repo files or examples.
- Very specific: line 198
Never commit .env, token files, or copied credentials.
- Distinctive: line 199
If a command might expose a secret in stdout/stderr, avoid reproducing that output verbatim.
- Distinctive: line 200
If the user gives a token, use it only for the current task unless explicitly told otherwise.
- Distinctive: line 206
Check in this order:
- Very specific: line 212
If not using gh, does Git already have usable auth?
- Distinctive: line 216
If the repo already has a valid GitHub remote and push access works:
- Distinctive: line 218
do not recreate the repo
- Distinctive: line 219
do not replace auth
- Very specific: line 226
create the GitHub repo with gh repo create
- Distinctive: line 230
Only ask the user for:
- Distinctive: line 238
Do the setup directly:
- Distinctive: line 242
create initial commit if needed
- Distinctive: line 247
Do not ask the user to perform these steps manually.
- Very specific: line 251
When gh is available and authenticated, prefer commands in this shape:
- Very specific: line 259
Use plain Git only for local repository operations or when gh cannot complete the GitHub-side action.
- Distinctive: line 263
Only use this fallback when:
- Distinctive: line 283
If PAT is required:
- Distinctive: line 285
ask only for a token with the minimum needed scope, usually repo write access
- Distinctive: line 286
use it only to complete the push flow
- Distinctive: line 287
avoid leaving it in shell history, files, process args, or remote URLs when possible
- Distinctive: line 299
no secret was exposed or persisted unsafely
“Common” is measured: kept by at least 6 in 10 of the 150 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GitHub
Overview
Prefer gh for all GitHub operations. The default goal is to complete the full GitHub flow with the least possible user effort: detect existing authentication first, reuse it if available, and only ask the user for the smallest missing step.
Never ask the user to manually perform a long GitHub setup if the agent can check, reuse, or finish it directly.
Core Rules
- Prefer
ghover raw GitHub API calls. - Prefer existing authenticated state over asking for new credentials.
- Prefer non-interactive checks before prompting the user.
- Prefer the smallest unblock request:
- paste a one-time code
- confirm browser login
- provide a PAT
- confirm repository visibility
- Do not ask the user to manually create the repository if
ghcan do it. - Do not ask the user to manually add remotes, initialize Git, or push if the agent can do it.
- Never print, echo, log, summarize, or restate secrets.
- Never store secrets in files, commits, repo config, docs, examples, or chat summaries.
- Never switch credential strategy unless the current one actually fails.
Interactive login driving rules
When using gh auth login through a shell session, do not assume the browser login step has started after the first prompt or after sending one key.
You must continue driving the interactive flow until there is explicit evidence of one of these states:
- GitHub CLI has clearly started browser/device authentication
- GitHub CLI is explicitly waiting for the user to complete external authentication
- GitHub CLI reports that authentication succeeded
- GitHub CLI reports a real error and cannot continue
While driving the login flow:
- keep polling the session after each input
- handle intermediate prompts such as protocol selection, SSH/HTTPS choice, credential helper confirmation, browser/device flow confirmation, or similar setup questions
- use minimal inputs such as
enter, arrow keys,y,n, or short submitted text as needed - do not stop after only one successful prompt response
- do not tell the user that the browser has opened unless the command output explicitly indicates that a browser login or web flow has started
- do not tell the user that login is complete unless the command output explicitly indicates success
Acceptable evidence that browser or external auth has actually started includes output such as:
- a message that a browser is being opened
- a URL to visit
- a device code to enter
- explicit wording that GitHub authentication is waiting for completion
If the shell session remains running but only shows that an earlier prompt was answered, continue polling instead of summarizing the state prematurely.
Only ask the user to act when the output clearly shows an external action is now required.
When the user says they completed browser or device authorization, do not start a new gh auth login flow immediately.
Instead:
- continue polling the existing shell session if it is still running
- wait for explicit success or failure from that same session
- only if that session has exited or is unrecoverable, then check
gh auth status - only start a brand-new login flow if the previous login session has clearly failed or been closed
If the shell output contains prompts like:
- "Press Enter to open ..."
- "Press Enter to continue"
- similar one-step local confirmation prompts
then send enter automatically and continue polling the same session.
Do not stop at that prompt. Do not ask the user to confirm completion yet. Do not start a new login flow while this session is still running.
Credential Handling Priority
1. Reuse gh authentication first
Check whether gh exists and is already authenticated.
Use this path when possible:
gh auth status- if authenticated, continue directly with:
- repo detection
gh repo create- remote setup
- push
If gh is authenticated, do not ask the user for tokens, passwords, SSH keys, or browser login.
2. If gh exists but is not authenticated, log in with gh directly
If gh is installed but not authenticated, use gh auth login directly and continue the GitHub flow after login succeeds.
Preferred order:
- browser/web login via
gh auth login -h github.com -w - standard interactive
gh auth login -h github.com - PAT-based login only if the normal
ghlogin path is unavailable or fails
Rules:
- do not switch away from
ghlogin unless it actually fails - do not ask the user to manually create repositories or configure git
- do not ask the user to perform a long GitHub setup outside the login itself
- continue automatically as soon as login succeeds
When login requires user interaction:
- ask for only the smallest possible action
- examples:
- “Please complete the GitHub browser login that just opened.”
- “Please finish the GitHub CLI login prompts.”
- “Please paste a GitHub PAT with repo access.”
After login succeeds, continue directly with:
- repo detection
gh repo create- remote setup
- push
3. If gh is unavailable, try to install it first
If gh is missing:
- first try to install
ghautomatically using the platform's normal package manager or a reasonable official installation path - prefer non-interactive installation methods when available
- after installation, re-check whether
ghexists and continue with the normalgh-first flow - only fall back away from
ghif installation actually fails, is blocked by the environment, or would require disproportionate user effort
Acceptable install attempts include examples like:
- Homebrew on macOS
apt,dnf, or similar package managers on Linuxwingetor other normal package-manager paths on Windows
Rules:
- do not ask the user to install
ghmanually before you have tried a reasonable automatic install path - do not switch to a different credential strategy just because
ghis missing initially - if installation fails, summarize the blocker briefly and then continue to the fallback path below
4. If gh is still unavailable, fall back to Git
If gh is missing:
- continue with plain
git - prefer existing Git credential helpers or existing SSH authentication
- inspect the environment before asking for credentials
Check for likely reusable auth:
- existing
originremote - existing Git credential helper
- working SSH auth to GitHub
- existing authenticated HTTPS remote behavior
Only if those paths fail should the user be asked for one minimal credential input.
Minimal-Interruption Prompting
When user input is required, ask for only one concrete item at a time.
Good prompts:
- “Please confirm whether the repo should be public or private.”
- “Please complete the GitHub login in your browser.”
- “Please paste a GitHub PAT with repo access.”
- “Please confirm the GitHub owner/org name.”
Bad prompts:
- asking the user to manually create a repo
- asking the user to configure Git from scratch without first checking
- asking for multiple credentials at once
- asking the user to inspect local config manually if the agent can inspect it
Safe Credential Rules
- Treat PATs, device codes, auth tokens, cookies, and SSH private keys as secrets.
- Never echo secrets back to the user.
- Never include secrets in command output summaries.
- Never write secrets into repo files or examples.
- Never commit
.env, token files, or copied credentials. - If a command might expose a secret in stdout/stderr, avoid reproducing that output verbatim.
- If the user gives a token, use it only for the current task unless explicitly told otherwise.
Standard Execution Flow
A. Detect environment
Check in this order:
- Is this already a Git repo?
- Is there already a remote?
- Is
ghinstalled? - Is
ghauthenticated? - If not using
gh, does Git already have usable auth?
B. If already connected to GitHub
If the repo already has a valid GitHub remote and push access works:
- do not recreate the repo
- do not replace auth
- just push
C. If Git repo exists but no GitHub repo exists yet
Preferred:
- create the GitHub repo with
gh repo create - set or update
origin - push the current branch
Only ask the user for:
- owner/org if ambiguous
- public vs private if not specified
- authentication only if required
D. If not a Git repo yet
Do the setup directly:
- initialize Git
- add files
- create initial commit if needed
- create GitHub repo
- add remote
- push
Do not ask the user to perform these steps manually.
gh-First Behavior
When gh is available and authenticated, prefer commands in this shape:
- inspect auth
- create repo
- set remote if needed
- push branch
- optionally enable features like description/homepage/topics later
Use plain Git only for local repository operations or when gh cannot complete the GitHub-side action.
Git / API Fallback Behavior
Only use this fallback when:
ghis not installed and cannot be installed reasonably- or
ghis installed but unusable for the required operation - or the environment blocks the normal
ghflow in a way that cannot be resolved with minimal user input
Fallback order:
- direct GitHub API + local
git - plain
gitwith existing SSH or credential-helper auth - HTTPS + PAT only if no better reusable auth exists
Fallback rules:
- still minimize user effort
- still prefer reusing existing credentials
- still never ask the user to create the repository manually if the agent can do it through the API
- still avoid exposing or persisting secrets
- still continue automatically once the minimal missing credential or confirmation is provided
If PAT is required:
- ask only for a token with the minimum needed scope, usually repo write access
- use it only to complete the push flow
- avoid leaving it in shell history, files, process args, or remote URLs when possible
Success Criteria
A successful run means:
- the local project is a valid Git repo if needed
- the GitHub repo exists
- the correct remote is configured
- the current branch is pushed
- credentials were reused when possible
- user involvement was limited to the smallest truly necessary action
- no secret was exposed or persisted unsafely
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

