agent-onboarding
Skill153 starsChanged 44 days agoMITView on GitHub
Onboard yourself to a repo where several agents work in parallel, syncing through a shared TODO.md. Use when joining the team on a shared codebase.
8 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- AndrewBrown-USDA/aigb-skills-usdatheir own version, first seen Oct 31, 2026
- brightdata/skillstheir own version, first seen Oct 29, 2026
- PL-Coding-GmbH/Skillstheir own version, first seen Oct 25, 2026
- Nunchi-trade/agent-clitheir own version, first seen Oct 8, 2026
- conjure-3301/skillsedited, first seen Aug 17, 2026
- zinan92/skills-repotheir own version, first seen Mar 15, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- conjure-3301/skills★ 086% same
Wrote their own version · 7
- Nunchi-trade/agent-cli★ 521same name
- brightdata/skills★ 270same name
- PL-Coding-GmbH/Skills★ 18same name
- skyil7/agent-onboarding★ 9same name
- AndrewBrown-USDA/aigb-skills-usda★ 7same name
- zinan92/agent-core★ 1same name
- zinan92/skills-repo★ 1same name
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 repository41 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- broken-access-controlSkill
- cdn-peekSkill
- http-request-smugglingSkill
- jwt-attacksSkill
- ssrf-oobSkill
- webapp-probeSkill
- blockchain-forensicsSkill
- foundry-pocSkill
- safe-huntSkill
- smart-contract-auditSkill
- cloud-bucket-bruteSkill
- infrastructure-auditSkill
- dylib-hijack-scanSkill
- endpoint-threat-huntSkill
- parse-securitySkill
- agentic-seoSkill
- context-window-to-skillSkill
- git-commitSkill
- keen-eyesSkill
- no-aispeakSkill
- secure-1pass-accessSkill
- self-improveSkill
- shadow-partnerSkill
- training-guideSkill
- variant-tableSkill
- auditor-quizSkill
- audit-scopeSkill
- evidence-captureSkill
- external-enumerationSkill
- gdocs-audit-reportSkill
- hackerone-reportSkill
- nuclei-suggestSkill
- pre-bountySkill
- sandboxed-audit-runnerSkill
- tiny-auditorSkill
- vm-labSkill
- llm-fuzz-toolsSkill
- mcp-server-pentestSkill
- prompt-injection-auditSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
If you had preexisting work assignments, give yourself an identity, like refractor-george or unit-testing-lary, otherwise ask the user why …
- Distinctive: line 9
If there are existing TODO.md categories register yourself under one or more of them based on tasks at hand
- Distinctive: line 12
DON'T fill data outside what the user had, except for your name and tasks
- Distinctive: line 13
DON'T give yourself unmeaningfull name like "copilot-hal", either understand by context or ask the user
- Distinctive: line 14
If onboarded after some work, you have your context already so no need to go looking for it, and same for your identity
- Distinctive: line 17
Use the TODO.md to avoid conflicting in your actions with other members, and check back every time you are working on something to indicate …
- Distinctive: line 18
If you are doing tasks under both categories just register yourself under both of them with the relevant tasks
“Common” is measured: kept by at least 6 in 10 of the 8 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
- You are now a part of a working force and you should be aware of the codebase, whats happening here and what are the docs and maybe some of the Makefile for extra context.
- If you had preexisting work assignments, give yourself an identity, like refractor-george or unit-testing-lary, otherwise ask the user why he brought you to name yourself based on your first task
- Find the repo's TODO.md file where all the other team members are, if you are the first, setup what is needed to get this started for future agents including yourself
- If there are existing TODO.md categories register yourself under one or more of them based on tasks at hand
- Whenever you are in the decision making, check back to TODO.md to see you are complimentary, and not contradictory or duplicative, of another agent/team members work
- TODO.md should be gitignored if not already
- DON'T fill data outside what the user had, except for your name and tasks
- DON'T give yourself unmeaningfull name like "copilot-hal", either understand by context or ask the user
- If onboarded after some work, you have your context already so no need to go looking for it, and same for your identity
- We want quick and effective context understanding and team registration
- a copilot / claude code session can only have one identity at a time
- Use the TODO.md to avoid conflicting in your actions with other members, and check back every time you are working on something to indicate to other agents not to conflict with you
- If you are doing tasks under both categories just register yourself under both of them with the relevant tasks
The structure should be:
# TODO.md
## Some task category
### [refractor-george]
- [ ] Refractoring what the user asked regarding the x structure
- [ ] Task you were given when interacting with the human
- [ ] Another task
- [ ] Task you just completed
## Another task category
[possibly other agents or team members]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.

